Pipecat vs telli

Agent ops

1. ai-native userMy coding agent can provision a complete voice agent end to end — create the agent, attach a number, and place a call — through the API, CLI, or MCP without touching the dashboard

   weight 3 · round to telli
   Pipecat~partialprobed3/10

   Pipecat provides a CLI (`pipecat init`, `pipecat cloud`, `pipecat context-hub`) and code-level telephony hooks (`python bot.py -t twilio -x ngrok...`) that let a coding agent scaffold and run a bot, and the context-hub can register an MCP server for coding-agent tooling, but there is no documented single API/CLI/MCP flow that creates the agent, provisions/attaches a phone number, and places a call — telephony setup still relies on the carrier's (Twilio/Telnyx) own console/API for number purchase and webhook config. missing for 10: a unified provisioning API or CLI command that attaches a phone number and places a call, MCP-driven agent creation (context-hub only builds a docs index, not agent provisioning), evidence of number attachment without touching a carrier dashboard.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”
   • [claimed-docs] “pipecat init quickstart # Change to the project directory cd pipecat-quickstart”
   • [claimed-docs] “pipecat init quickstart”
   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli~partialprobed5/10

   telli's REST API documents endpoints for scheduling calls and importing/attaching phone numbers (telli-docs-17, telli-docs-19), and the MCP server lets AI tools talk to Charlie, who can 'build and refine agents' (telli-docs-11, telli-docs-22), suggesting agent creation is possible without the dashboard. However, there is no explicit API/CLI 'create agent' endpoint documented, no CLI tool is mentioned at all, and the MCP-driven agent creation is only described as an assistant chat capability rather than a deterministic API call — so a full end-to-end create→attach-number→place-call pipeline via one consistent interface is not clearly evidenced. Missing for 10: a documented create-agent API/CLI endpoint, confirmation MCP/Charlie can fully provision agents without any dashboard step, and an example combining all three steps in one flow.

   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

2. ai-native userThe platform's own AI helps me author agents — generating or improving prompts, flows, and test cases from a description

   weight 1 · round to telli
   Pipecat—none0/10

   Evidence shows Pipecat has a context-hub that registers as an MCP server so external coding agents (e.g. Claude) can get context about the framework, and an Evals system for testing agent behavior — but these rely on the user writing prompts/flows/tests and connecting third-party AI tools, not Pipecat's own AI generating or improving prompts, flows, or test cases from a description. No evidence of an in-platform AI assistant that authors agent configs.

   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “Pipecat Evals is the framework's built-in system for testing agent behavior. You describe a conversation and the behavior you expect, and Pi…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”

   proof ↗⚑ flag

   telli~partialprobed5/10

   Charlie, telli's built-in AI assistant, is documented as helping to 'build and refine agents, automate workflows, and analyze your calls,' which supports the core idea of AI-assisted agent authoring, and the MCP server lets external AI tools interact with Charlie too. However there's no concrete evidence of generating test cases from a description, or detailed examples of prompt/flow generation output. missing for 10: documented examples of Charlie generating/improving prompts or flows from a natural-language description, evidence of AI-generated test case creation, and independent/hands-on confirmation of these capabilities in practice.

   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

Build

1. developerBuild a working phone voice agent — prompt, voice, and phone number — and take my first live call within an hour

   weight 3 · round to Pipecat
   Pipecat~partialprobed7/10

   Pipecat's quickstart gets a browser voice bot running in ~5 minutes with prompt+voice configurable across 200+ providers, and the telephony guide shows the same bot file working with real carriers (Twilio/Telnyx/Plivo) via a one-line command with ngrok tunneling, so all three pieces (prompt, voice, phone number) are documented and connectable to the same codebase. However, the telephony path is a separate 'production' doc requiring carrier account setup/ngrok tunneling not folded into the 5-minute quickstart, and there's no first-party or independent account of someone going from zero to a live phone call within an hour. Missing for 10: an end-to-end timed walkthrough combining phone-number provisioning with the quickstart, and independent hands-on confirmation of the 'first live call within an hour' claim.

   • [claimed-docs] “Build and run your first Pipecat voice AI bot in under 5 minutes”
   • [claimed-docs] “Build and run your first Pipecat voice AI bot in under 5 minutes: a simple conversational agent you can talk to in a browser.”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “Swap speech, language, and vision services from any of 200+ integrated providers and services — usually one line of code.”
   • [claimed-docs] “Any Transport: WebRTC, SIP, PSTN”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   telli provides agent builder, test call feature, voice cloning, and phone number setup (forwarding or SIP trunk import) which together support building and testing a voice agent with prompt, voice, and number, but there's no explicit walkthrough or evidence confirming a full end-to-end setup can be completed within an hour or that phone number provisioning is instant/self-serve for new numbers. missing for 10: a documented quick-start/time-to-first-call benchmark, evidence of instant/native number provisioning (vs SIP/forwarding setup), and independent/hands-on confirmation of the full flow's speed.

   • [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
   • [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
   • [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”
   • [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
   • [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”
   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”

   proof ↗⚑ flag

2. developerRun conversations in multiple languages, including detecting and switching language mid-call

   weight 2 · round drawn
   Pipecat—none0/10

   The evidence mentions swapping speech/language services across providers (one line of code) but nothing about detecting a spoken language mid-call or dynamically switching STT/TTS/LLM language settings within an active conversation. No docs, community reports, or runtime probes address multilingual or language-switching behavior. missing for 10: language detection mechanism, mid-call language switching mechanism, any docs/demo showing multilingual conversation handling.

   • [claimed-docs] “Swap speech, language, and vision services from any of 200+ integrated providers and services — usually one line of code.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack mentions multilingual support, language detection, or mid-call language switching for telli's voice agents; all documented features concern scheduling, webhooks, tools, analytics, and MCP integration.

   ⚑ flag

3. founderDesign multi-step conversation flows in a visual builder with branching, states, and handoffs without writing code

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat Flows lets you define branching conversation states via Python functions/config (docs-6, docs-22, docs-39), but this is a code-first framework with a CLI and Python SDK, not a visual drag-and-drop builder — no evidence pack item mentions any GUI/no-code flow designer. Since competing voice-agent platforms do offer visual builders, this is a fair axis to ask about, and Pipecat's evidence shows the opposite (functions/config authored in code).

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”
   • [claimed-docs] “Flows auto-derives the function's metadata — name, description, parameter properties (with their descriptions), and which parameters are req…”
   • [claimed-docs] “Hand off to subagents for long-running tools and complex tasks, and use Pipecat Flows when a conversation needs to follow a defined path.”

   proof ↗⚑ flag

   telli~partialclaimed4/10

   telli has an 'agent builder' with test-call and versioning, and workflow triggers (scheduled, SMS/WhatsApp) suggesting some no-code workflow configuration, plus tool-calls like transfer to another agent implying handoffs. But there's no evidence of a visual flow builder with branching/state diagrams — evidence only shows agent settings, tools, and triggers, not a drag-and-drop conversation flow canvas. missing for 10: explicit visual builder UI with branching/state nodes, evidence of designing multi-step flows with conditional paths, and documentation of handoff logic beyond simple 'transfer tool'.

   • [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
   • [claimed-docs] “Transfer tools | Move the call to another agent or number.”
   • [claimed-docs] “Choose SMS and WhatsApp workflow recipients from contact properties, collected values, or a fixed number”
   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”

   proof ↗⚑ flag

Personalization

1. developerInject dynamic variables and per-caller context at call time so each conversation is personalized

   weight 2 · round drawn
   Pipecat—none0/10

   Evidence shows Pipecat Flows functions can process data and transition conversation state, and telephony bots receive caller info via webhook, but nothing documents a mechanism for injecting per-caller dynamic variables/context into the bot's prompt or state at call start for personalization. This is a fair capability to expect from a voice-agent framework, but no citation directly demonstrates it.

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “Flows auto-derives the function's metadata — name, description, parameter properties (with their descriptions), and which parameters are req…”

   proof ↗⚑ flag

   telli—none0/10

   The evidence describes contact properties and collected values being used to select SMS/WhatsApp recipients (telli-docs-5) and APIs to manage contacts and schedule calls (telli-docs-12, telli-docs-17), but nowhere does it document injecting dynamic variables or per-caller context into an agent's voice call script/persona at call time. Missing for 10: explicit documentation of variable placeholders in agent prompts, a mechanism for passing per-call custom data via the schedule-call API, and any example of personalized call content driven by caller-specific fields.

   • [claimed-docs] “Choose SMS and WhatsApp workflow recipients from contact properties, collected values, or a fixed number”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”

   proof ↗⚑ flag

2. developerGround the agent on my documents with a built-in knowledge base or RAG so it answers from my content

   weight 2 · round drawn
   Pipecat—none0/10

   Pipecat's docs describe voice/multimodal pipeline orchestration, function calling via Flows, telephony, evals, and a context-hub for coding-agent tooling — but nothing about a built-in knowledge base or RAG mechanism for grounding the agent on user documents. The closest hit (context-hub) indexes Pipecat's own docs/API for coding assistants, not user content for the voice agent.

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”

   proof ↗⚑ flag

   telli—none0/10

   No evidence of a built-in knowledge base or RAG feature for grounding agents on uploaded documents; the docs describe custom tools for API integration and a web_search tool for public information, but nothing about ingesting documents or content for retrieval-based answers.

   ⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Pipecat✓fullprobed9/10

   Pipecat provides a working llms.txt endpoint (confirmed HTTP 200 with agent-oriented summary) plus an explicit context-hub CLI feature that registers docs as an MCP server for coding agents and builds a local index, directly enabling agents to consume its docs programmatically. missing for 10: no independent/community confirmation of an agent successfully using llms.txt or context-hub end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.pipecat.ai/llms.txt # Pipecat > Pipecat is an open source ecosystem for building voice and multimo…”
   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli✓fullprobed9/10

   telli hosts a live llms.txt file (confirmed via probe, HTTP 200) plus machine-readable OpenAPI spec explicitly intended for coding agents, and docs also mention agent-oriented context for downloading API specs. missing for 10: no independent/third-party confirmation of an agent successfully consuming llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.telli.com/llms.txt # telli Documentation > telli is the AI voice platform for agents that sell, su…”
   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Pipecat~partialprobed6/10

   Pipecat is a Python framework that is pip-installable with no key required and runs bots as scripts (bot.py) with a CLI supporting init, cloud deploy, and eval subcommands, which supports headless/CI-friendly automation; the Evals system explicitly runs conversations against the real agent programmatically, suitable for CI. However there is no explicit CI/CD example, no documented headless flag or non-interactive mode guidance, and the development runner is framed around local dev/demo UI rather than CI. missing for 10: explicit CI pipeline documentation/example, confirmation that pipecat.runner.run or bot.py can run fully headless without any UI/browser dependency, independent hands-on report of running Pipecat in an automated CI environment.

   • [claimed-docs] “Pipecat Evals is the framework's built-in system for testing agent behavior. You describe a conversation and the behavior you expect, and Pi…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [claimed-docs] “Pipecat ships a built-in development runner (pipecat.runner.run) that handles the server-side glue most bots need during development: creati…”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”

   proof ↗⚑ flag

   telli~partialprobed6/10

   telli exposes a full REST API (with OpenAPI spec) to programmatically schedule calls, manage contacts, and trigger workflows, plus webhooks for event-driven automation and scheduled/recurring workflow triggers — all of which support headless, non-UI automation suitable for CI-like pipelines. However there is no explicit CI/CD example, CLI tool, or documented automated pipeline integration beyond the API/webhook primitives. Missing for 10: dedicated CI/CD documentation or examples, a CLI for scripted invocation, and independent confirmation of headless use in production pipelines.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   Pipecat—none0/10

   The evidence only shows Pipecat's context-hub CLI *exposing itself* as an MCP server to a coding agent (docs-11/38) — the reverse of what the story asks (Pipecat consuming external MCP servers to gain their tools inside its voice-agent pipelines). No evidence shows Pipecat's Flows/function-calling system connecting to arbitrary MCP servers as a client.

   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”

   proof ↗⚑ flag

   telli—none0/10

   Telli's documented MCP support only runs in the opposite direction — it exposes an MCP server so external AI tools (Claude, ChatGPT, Codex) can talk to its Charlie assistant (telli-docs-22, telli-probe-3), not a mechanism for telli's own voice agents to consume external MCP servers' tools. Custom Tools (telli-docs-14, telli-docs-20) let agents call external APIs but are described as custom integrations, not MCP-based tool ingestion.

   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
   • [claimed-docs] “Custom Tools: Extend telli's capabilities with custom integrations and workflows.”
   • [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to telli
   Pipecat~partialprobed6/10

   Pipecat ships an official `pipecat context-hub install` CLI command that registers itself as an MCP server with a coding agent, building a local docs/examples index — confirmed both in docs and via a runtime CLI probe showing the `context-hub` subcommand exists. This is a genuine official MCP server for agent connection, but it's scoped narrowly to indexing Pipecat's own docs/examples for coding assistants rather than exposing Pipecat's runtime voice-agent capabilities to arbitrary MCP clients. Missing for 10: independent/hands-on confirmation that the MCP server actually functions end-to-end (only CLI help text was probed, not live MCP protocol behavior), and broader documentation of what tools/resources the MCP server exposes.

   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli✓fullprobed8/10

   telli documents an official MCP server that lets external AI tools (Claude, ChatGPT, Codex) connect over the Model Context Protocol to interact with Charlie, telli's assistant, confirmed both in docs and via a live probe of the integrations/mcp page. Missing for 10: no independent/hands-on corroboration beyond first-party docs and the probe, and no detail on server setup/auth specifics.

   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Pipecat
   Pipecat✓fullprobed9/10

   Pipecat ships an official CLI (pip-installable pipecat-ai[cli], confirmed via runtime probe) supporting init/scaffolding, cloud deploy, eval, and context-hub (MCP registration for coding agents), well documented at docs.pipecat.ai/api-reference/cli/overview. This directly supports AI-native agentic workflows (context-hub install registers as MCP server, writes AGENTS.md/CLAUDE.md for coding agents). missing for 10: independent/third-party review of the CLI's robustness beyond vendor docs and a single runtime probe.

   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [probe] “official CLI documented at https://docs.pipecat.ai/api-reference/cli/overview”
   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “Install the Pipecat CLI and scaffold the quickstart project (also writes AGENTS.md + CLAUDE.md)”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”

   proof ↗⚑ flag

   telli—none0/10

   telli offers a REST API, webhooks, and an MCP server for AI assistants, but there is no mention anywhere in the evidence of an official CLI tool for telli. missing for 10: any documentation or reference to a telli CLI, its commands, or installation instructions.

   ⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round to telli
   Pipecat~partialprobed7/10

   Pipecat exposes a well-documented programmatic surface — a Python framework API (frame processors, Flows functions with auto-derived metadata), a runner API, and an official CLI (init/cloud/eval/context-hub) confirmed to work keylessly via runtime probe — giving AI-native users a documented, scriptable way to drive the product. However, probing shows no REST/OpenAPI spec (all openapi.json candidates 404'd), so there's no conventional network-callable public API, only the code-level Python/CLI surface. Missing for 10: a formal REST/OpenAPI-documented HTTP API, and independent hands-on confirmation of driving a full pipeline purely via that public API surface.

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Pipecat ships a built-in development runner (\`pipecat.runner.run\`) that handles the server-side glue most bots need during development”
   • [claimed-docs] “Pipecat ships a built-in development runner (pipecat.runner.run) that handles the server-side glue most bots need during development: creati…”
   • [claimed-docs] “Flows auto-derives the function's metadata — name, description, parameter properties (with their descriptions), and which parameters are req…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.pipecat.ai/openapi.json, https://docs.pipecat.ai/swagger.json, https://docs.pipecat.ai/…”
   • [probe] “official CLI documented at https://docs.pipecat.ai/api-reference/cli/overview”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli✓fullprobed9/10

   telli documents a REST API with endpoints (schedule-call, import-phone-number), API key/bearer auth, webhooks, and a downloadable OpenAPI spec (confirmed live at openapi.json), plus an MCP server for AI tool access — enabling full programmatic/agentic control. missing for 10: independent third-party validation of API robustness beyond vendor docs.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round drawn
   Pipecat—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   telli—none0/10

   telli documents a single API key (bearer token) generated in Settings > Developer, but there's no evidence of scoped permissions, role-based keys, or least-privilege credential issuance for agents specifically.

   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Pipecat
   Pipecat✓fullprobed9/10

   Pipecat is itself an official open-source Python SDK/framework (pip-installable, verified via runtime probe to install and import cleanly), and it also ships a family of official 'Pipecat Client' SDKs for web/mobile integration plus pre-built React components, all documented on the official site. Missing for 10: independent/third-party confirmation of the client SDKs' quality beyond docs (only the core Python framework was hands-on verified).

   • [claimed-docs] “Pipecat Clients are a family of SDKs that connect users to your Pipecat agents through web and mobile applications.”
   • [claimed-docs] “Pipecat Clients are a family of SDKs that connect users to your Pipecat agents through web and mobile applications. They handle real-time au…”
   • [claimed-docs] “Pre-built React components for voice AI interfaces.”
   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”
   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [github] “Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, l…”

   proof ↗⚑ flag

   telli~partialprobed5/10

   telli provides a REST API with an OpenAPI spec that can be used to generate client libraries, plus webhooks, custom tools, and an MCP server for agent integration, but there is no evidence of telli-maintained official SDKs in specific languages (e.g., Python/JS packages published by telli) — only self-generated clients from the OpenAPI spec. missing for 10: dedicated first-party SDK packages/repos, language-specific SDK documentation, versioning/release notes for such SDKs.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to telli
   Pipecat—none0/10

   Webhooks appear only as an inbound mechanism (a telephony carrier calling Pipecat's webhook to signal an incoming call), not as an outbound event-subscription system that lets a user register a webhook to receive Pipecat's own events (e.g., call end, transcript ready, errors). No evidence of a webhook subscription API or configurable event notifications for consumers.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”

   proof ↗⚑ flag

   telli✓fullclaimed8/10

   telli documents a webhooks system that pushes real-time POST notifications about call events, status changes, and outcomes, explicitly described as event-driven subscription for external systems (telli-docs-13, telli-docs-21). Missing for 10: no evidence of configurable event-type filtering/subscription granularity or independent third-party confirmation of reliability.

   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to telli
   Pipecat—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   telli~partialclaimed6/10

   telli ships a built-in AI assistant (Charlie) that can 'analyze your calls' and help build/refine agents, plus dashboards for reach rate, call duration, success rate, and per-call transcript/outcome analysis, which together provide AI-driven insight into product data. However, the docs don't detail proactive, autonomous 'suggestions' surfaced to the user (e.g., recommended actions, anomaly detection) beyond on-demand analysis via Charlie or manual dashboard review. Missing for 10: concrete examples of Charlie proactively surfacing insights/recommendations, independent user corroboration of insight quality.

   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
   • [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
   • [claimed-docs] “Submit feedback on calls to continuously improve your agent.”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to telli
   Pipecat~partialclaimed4/10

   Pipecat supports multi-agent systems where 'specialists hand off, fan out in parallel, and coordinate over a shared bus, locally or distributed' and can 'hand off to subagents for long-running tools and complex tasks,' plus telephony bots that start autonomously when a carrier calls a webhook rather than a user request — suggesting some background/autonomous agent operation. But Pipecat's core model is a live, turn-based conversational pipeline tied to an active voice/video session, not a scheduler or cron-like background automation runner independent of a live interaction. Missing for 10: explicit scheduling/triggering mechanisms for unattended background jobs, evidence of agents running without any live session, and independent confirmation of autonomous multi-agent orchestration in production.

   • [github] “Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, l…”
   • [claimed-docs] “Hand off to subagents for long-running tools and complex tasks, and use Pipecat Flows when a conversation needs to follow a defined path.”
   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”

   proof ↗⚑ flag

   telli✓fullclaimed7/10

   telli supports Scheduled triggers so workflows run automatically without a call event, plus retry/dialing-window configuration, webhooks, and an AI assistant (Charlie) to build/automate workflows — together enabling background autonomous automations. Missing for 10: independent/hands-on verification of scheduled automations running reliably in production, and more detail on monitoring/error-handling for autonomous runs beyond docs claims.

   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
   • [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to telli
   Pipecat—none0/10

   Pipecat's docs describe a framework/CLI for building voice AI agents, a context-hub that exposes Pipecat's own docs as an MCP server to external coding agents, and dev tooling (runner, evals, Flows) — but none of this is a built-in assistant inside Pipecat's own product surface that a user delegates tasks to. Missing for 10: any first-party 'chat with an assistant' feature in the CLI/dashboard/docs site, evidence of task delegation to an embedded assistant, or independent confirmation of such a feature.

   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli✓fullprobed8/10

   telli documents "Charlie," a built-in AI assistant that can build/refine agents, automate workflows, and analyze calls, and this assistant is also exposed via an MCP server for external AI tools to interact with. This directly matches delegating tasks to a built-in assistant within the product. Missing for 10: independent/hands-on verification of Charlie's task delegation in practice and more detail on the scope of tasks it can autonomously execute.

   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round drawn
   Pipecat~partialprobed6/10

   Pipecat's entire raison d'être is building voice agents that end users control via natural spoken language — turn detection, interruption/barge-in, and Flows functions that progress conversations based on NL input (pipecat-docs-9, pipecat-docs-19, pipecat-docs-6/22/30) all support NL-driven operation of the *bots* it produces. However, the story is ambiguous about whether it's the bots or the Pipecat tooling itself; Pipecat's own developer-facing surfaces (CLI init/cloud/eval/context-hub) are traditional structured commands, not natural-language commands (pipecat-probe-rt-1, pipecat-docs-34/37). Missing for 10: evidence that the Pipecat framework/CLI itself (not just end-user bots) can be operated by an AI-native user via natural-language instructions rather than code/CLI syntax.

   • [claimed-docs] “Smart Turn Detection uses an advanced machine learning model to determine when a user has finished speaking and your bot should respond.”
   • [claimed-docs] “Interruptions (also called barge-in) let the user talk over the bot. When the user starts speaking while the bot is talking, the bot stops i…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data by interfacing with external systems and APIs... 2. Progress the conversa…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [claimed-docs] “pipecat init quickstart # Change to the project directory cd pipecat-quickstart”

   proof ↗⚑ flag

   telli~partialprobed6/10

   telli offers Charlie, a built-in AI assistant that can build/refine agents, automate workflows, and analyze calls via natural language, plus an MCP server letting external AI tools (Claude, ChatGPT, Codex) converse with Charlie — both point to natural-language operation. However, most of the product surface (workflows, scheduling, dialing windows, phone number setup) is described as configured through UI/API rather than conversational commands, and there's no independent/hands-on evidence of Charlie's NL command scope or reliability. missing for 10: hands-on evidence of Charlie executing complex natural-language commands, documentation detailing the breadth of actions controllable purely via NL, independent corroboration beyond vendor docs.

   • [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat's docs are static markdown pages (get-started, fundamentals, flows, CLI reference) with no evidence of an interactive API reference or runnable code examples; a direct probe for OpenAPI/Swagger endpoints returned 404 on all candidate paths, indicating no interactive API explorer exists.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.pipecat.ai/openapi.json, https://docs.pipecat.ai/swagger.json, https://docs.pipecat.ai/…”
   • [probe] “official CLI documented at https://docs.pipecat.ai/api-reference/cli/overview”

   proof ↗⚑ flag

   telli~partialprobed5/10

   telli publishes an OpenAPI spec (openapi.json) and API docs with downloadable schemas for generating client libraries or feeding coding agents, but there is no evidence of an interactive reference with runnable/'try it' examples in-browser. missing for 10: an interactive try-it console, live runnable code samples, or sandboxed request execution within the docs site.

   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to telli
   Pipecat—none0/10

   A direct probe for OpenAPI/swagger specs at all standard locations (openapi.json, swagger.json, etc.) on docs.pipecat.ai returned 404s, and no evidence pack item shows a downloadable machine-readable API spec despite Pipecat having an api-reference docs section and cloud service.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.pipecat.ai/openapi.json, https://docs.pipecat.ai/swagger.json, https://docs.pipecat.ai/…”

   proof ↗⚑ flag

   telli✓fullprobed9/10

   telli provides a downloadable OpenAPI spec confirmed live at /openapi.json, and docs explicitly state it can be downloaded to generate client libraries, import into tools, or give coding agents machine-readable API context. Missing for 10: no independent third-party confirmation of spec completeness/versioning beyond first-party docs and probe.

   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to Pipecat
   Pipecat~partialclaimed5/10

   Pipecat provides a local development runner (`pipecat.runner.run`) and CLI scaffolding that let developers run and iterate on bots entirely locally, plus a built-in Evals system that runs described conversations against 'your real agent' pipeline for behavior testing — both usable without deploying to Pipecat Cloud or touching a production instance. However, there's no explicit 'sandbox environment' concept with data isolation from production (e.g. no staging vs prod data separation, no test-data seeding, no mention of production data at all since Pipecat doesn't store conversational data centrally). Missing for 10: explicit sandbox/production data isolation, documented data classification for dev vs prod, hands-on confirmation that Evals or local runner never touch live production resources.

   • [claimed-docs] “Pipecat ships a built-in development runner (\`pipecat.runner.run\`) that handles the server-side glue most bots need during development”
   • [claimed-docs] “Pipecat ships a built-in development runner (pipecat.runner.run) that handles the server-side glue most bots need during development: creati…”
   • [claimed-docs] “Pipecat ships a built-in development runner (`pipecat.runner.run`) that handles the server-side glue most bots need during development: crea…”
   • [claimed-docs] “Pipecat Evals is the framework's built-in system for testing agent behavior. You describe a conversation and the behavior you expect, and Pi…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”
   • [claimed-docs] “This is the property that makes the same bot file portable across the development runner, Pipecat Cloud, and most production self-hosting se…”

   proof ↗⚑ flag

   telli~partialclaimed4/10

   telli's agent builder includes a 'Test call' feature that lets users dial a draft or saved agent version and review the recording/transcript before going live, which functions as a lightweight test mode (telli-docs-28, telli-docs-29). However, there is no documentation of a dedicated sandbox environment, separate test dataset, or explicit guarantee that test calls don't write to production contacts/analytics. missing for 10: explicit sandbox/staging environment separate from production, confirmation that test calls don't affect production data/metrics, and any mention of test API keys or isolated test accounts.

   • [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
   • [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Pipecat—none0/10

   No evidence pack item discusses API versioning scheme, version numbers surfaced in docs, or any documented deprecation policy/timeline for Pipecat's SDKs or APIs; the only version datum (pip package 1.8.1) shows a version exists but nothing about a deprecation policy is documented.

   ⚑ flag

   telli—none0/10

   Evidence shows an OpenAPI spec and API key auth exist, but nothing in the pack mentions API versioning (e.g., v1/v2 paths, version headers) or any documented deprecation/sunset policy for endpoints. Missing for 10: explicit API version scheme, changelog of breaking changes, and a stated deprecation/sunset policy.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to telli
   Pipecat~partialclaimed3/10

   Pipecat supports 'unlimited concurrency' for running many simultaneous voice sessions and multi-agent fan-out ('fan out in parallel... coordinate over a shared bus'), which could support bulk-style parallel processing of many calls/agents at once. However, there is no explicit bulk-operation tooling (e.g., batch APIs, bulk data import/export, mass-edit of items) documented anywhere in the evidence pack. Missing for 10: explicit bulk/batch operation APIs or workflows, evidence of processing many discrete 'items' (not just concurrent voice sessions) in one operation, and any hands-on confirmation of this at scale.

   • [claimed-docs] “Pipecat Cloud supports unlimited concurrency.”
   • [github] “Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, l…”

   proof ↗⚑ flag

   telli~partialprobed6/10

   Telli's platform is built around calling large contact lists (dialing windows, calling strategies, retry behavior, reach-rate metrics) and its REST API lets users 'programmatically manage contacts, schedule calls' at scale, implying bulk campaign operations. However, there is no explicit documentation of a bulk-upload/bulk-schedule endpoint or UI for acting on many items simultaneously — the schedule-call endpoint documented is single-call oriented. Missing for 10: explicit bulk-contact import/schedule endpoint, documented batch size limits, and independent evidence of large-scale bulk execution.

   • [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.telli.com/llms.txt # telli Documentation > telli is the AI voice platform for agents that sell, su…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Pipecat
   Pipecat~partialclaimed6/10

   Pipecat's frame-based pipeline is inherently event-driven — interruption events automatically halt bot output when the user speaks, and Pipecat Flows functions can process data and automatically transition conversation nodes based on function-call events. This gives a real automation layer, but it's scoped to conversation/pipeline events rather than a general-purpose rules engine for arbitrary triggers/actions. Missing for 10: a documented generic rule-definition system (arbitrary trigger→action bindings outside conversation flow), and independent/hands-on evidence of custom event-rule automation beyond the built-in interruption/Flows mechanics.

   • [claimed-docs] “When the user starts speaking while the bot is talking, the bot stops immediately, in-flight work is cancelled, and the pipeline is ready fo…”
   • [claimed-docs] “Interruptions (also called barge-in) let the user talk over the bot. When the user starts speaking while the bot is talking, the bot stops i…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data by interfacing with external systems and APIs... 2. Progress the conversa…”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”

   proof ↗⚑ flag

   telli~partialclaimed5/10

   telli's workflows can be triggered by call events (implied default) and now by a recurring schedule, and webhooks notify external systems on call events, showing some event-driven automation. However there's no documented rule-definition interface (conditions, event-type selection, if/then logic) for arbitrary events beyond calls/schedule. Missing for 10: explicit rule/condition builder, broader event-type coverage beyond calls, and evidence of user-defined trigger logic rather than fixed schedule/call triggers.

   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to telli
   Pipecat—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   telli✓fullclaimed7/10

   telli documents scheduled triggers that let workflows run recurringly on an interval/start time without a call event, directly matching the recurring-workflow story, and also supports scheduling individual calls via API. missing for 10: independent/hands-on corroboration of recurrence reliability and detail on editing/monitoring scheduled workflow runs.

   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Optional flag to bypass dialing window restrictions for the scheduled call. When true, calls at the scheduled time regardless of dialing win…”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to telli
   Pipecat—none0/10

   Pipecat's docs describe building pipelines/Flows in Python code but no evidence of built-in versioning, review workflows, or rollback capabilities for automations (Flows or pipelines) — no changelog, diff, or rollback tooling is mentioned anywhere in the evidence pack.

   ⚑ flag

   telli~partialclaimed3/10

   The only hint of versioning is in agent testing, where you can pick 'your draft with unsaved changes or any saved revision' (telli-docs-28), implying saved agent versions exist. However there is no documented review interface for comparing versions, no explicit rollback/restore action, and no versioning mentioned for broader automations/workflows (only agents). Missing for 10: explicit rollback UI/API, version diff/review tooling, and versioning coverage for workflows beyond agent test calls.

   • [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”

   proof ↗⚑ flag

Compliance

1. founderMeet call-recording consent and disclosure obligations with per-call recording controls and configurable data retention

   weight 2 · round to telli
   Pipecat~partialclaimed3/10

   Pipecat provides an AudioBufferProcessor that developers can use to capture call recordings, which is a building block a founder could use to implement recording, but there's no documented feature for per-call consent/disclosure toggles or configurable data-retention policies — those would have to be built entirely by the developer. missing for 10: consent/disclosure mechanisms, retention-policy configuration, compliance-specific controls, any documentation tying recording to legal/consent obligations.

   • [claimed-docs] “Pipecat's \`AudioBufferProcessor\` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's AudioBufferProcessor makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's `AudioBufferProcessor` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   telli documents conditional recording based on caller consent and a configurable data-retention policy that auto-deletes contacts and call data after a defined age, directly addressing the founder's compliance need. However, evidence lacks detail on per-call granular controls (e.g., pause/resume, jurisdiction-specific disclosure scripts), audit logging of consent events, or independent verification that these features work as described. Missing for 10: per-call recording toggle/audit trail details, jurisdiction-specific disclosure templates, retention configuration granularity (e.g., per-data-type settings), and independent/hands-on confirmation of compliance behavior.

   • [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”
   • [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”

   proof ↗⚑ flag

2. platform-engineerRun regulated workloads with HIPAA/BAA support, SOC 2, and data-residency options

   weight 2 · round drawn
   Pipecat—none0/10

   No evidence in the pack mentions HIPAA/BAA, SOC 2 certification, or data-residency options for Pipecat or Pipecat Cloud; the pack covers pipeline features, telephony, CLI, and dev tooling but nothing on compliance/regulatory posture. missing for 10: HIPAA/BAA documentation, SOC 2 attestation, data-residency configuration options.

   ⚑ flag

   telli—none0/10

   No evidence in the pack mentions HIPAA, BAA, SOC 2, or data-residency options; only data retention and consent-based recording are covered, which don't establish formal compliance certifications.

   ⚑ flag

Scale

1. platform-engineerSee documented concurrency limits and scale to many simultaneous calls without manual capacity begging

   weight 2 · round to Pipecat
   Pipecat~partialcommunity4/10

   Pipecat Cloud's pricing page asserts 'unlimited concurrency' and offers multiple agent profiles for compute needs, giving a vendor-level answer to scaling, but there is no documented capacity planning guide, per-instance concurrency limits, or benchmarks for self-hosted deployments. Community commentary (a developer porting Pipecat to avoid Python's GIL for 'real concurrency') suggests self-hosted scaling is not frictionless and may require manual work to reach high concurrency. Missing for 10: documented concurrency ceilings/benchmarks for self-hosted deployments, load-testing data, and detail behind the 'unlimited concurrency' claim beyond a pricing-page bullet.

   • [claimed-docs] “Pipecat Cloud supports unlimited concurrency.”
   • [claimed-docs] “Pipecat Cloud offers different agent profiles, to best support your use case and compute needs.”
   • [community] “I got tired of running Python servers for voice agents, so I started porting Pipecat over. The design is Pipecat's, frames and processors an…”

   proof ↗⚑ flag

   telli—none0/10

   No evidence pack item documents concurrency limits, per-account call caps, or scaling guarantees for simultaneous calls; docs mention dialing windows/retry strategy but not concurrency ceilings or auto-scaling behavior. This is a fair question for a voice-calling platform (scaling many simultaneous calls is core to the product's value), so 'none' applies rather than 'na'.

   ⚑ flag

Self host

1. platform-engineerSelf-host the voice agent runtime from open-source code on my own infrastructure

   weight 3 · round to Pipecat
   Pipecat✓fullprobed9/10

   Pipecat is confirmed as a pip-installable, BSD-2 open-source Python framework that runs keylessly with no vendor lock-in, ships a development runner and CLI, and docs explicitly state bot files are portable across the dev runner, Pipecat Cloud, and 'most production self-hosting setups.' Runtime probes confirm the package installs and imports successfully outside any managed cloud, and community evidence corroborates real-world self-hosted usage (local inference via Ollama/Whisper, custom ports of the framework). Missing for 10: a first-party detailed production self-hosting deployment guide (e.g., Docker/Kubernetes reference architecture) beyond the telephony/local-runner docs.

   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [claimed-docs] “This is the property that makes the same bot file portable across the development runner, Pipecat Cloud, and most production self-hosting se…”
   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”
   • [community] “Local inference is already supported via Pipecat, you can use ollama or any custom OpenAI endpoint. Local STT is also supported via whisper,…”
   • [community] “Yes, Pipecat already supports that natively, so this can be done easily with ollama... Also, check out any provider they support, and it can…”
   • [github] “Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, l…”

   proof ↗⚑ flag

   telli—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

Latency

1. platform-engineerSee documented end-to-end voice latency numbers or tuning guidance backing the platform's speed claims

   weight 3 · round to Pipecat
   Pipecat~partialclaimed6/10

   Pipecat documents a dedicated STT-latency-tuning guide describing measured P99 latency values per service and a TTFS (Time To Final Segment) metric, plus a built-in metrics system for enabling latency instrumentation — real tuning guidance exists. However, this is scoped to STT stage latency rather than a comprehensive end-to-end voice round-trip latency benchmark, and no actual published numbers/tables or independent corroboration of the claimed P99 figures are shown. Missing for 10: published end-to-end latency benchmark numbers (not just STT), tuning guidance across the full voice pipeline (TTS/LLM/turn-taking), and independent verification of the claimed latency figures.

   • [claimed-docs] “Pipecat ships with measured P99 latency values for each supported service so that turn detection can account for this delay automatically.”
   • [claimed-docs] “Time To Final Segment (TTFS) measures how long it takes from the moment a user stops speaking until the STT service delivers the final trans…”
   • [claimed-docs] “Pipecat offers built-in metrics for both, which can be enabled with straightforward configuration options.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence pack item mentions latency numbers, turn-taking performance, or tuning guidance for voice response speed; documentation covers workflows, API, webhooks, and agent building but nothing on end-to-end latency benchmarks or tuning.

   ⚑ flag

Turn taking

1. developerRely on the agent to handle interruptions (barge-in) gracefully — stopping speech, updating context, and recovering the turn

   weight 3 · round to Pipecat
   Pipecat✓fullclaimed8/10

   Pipecat has explicit, dedicated documentation on interruptions/barge-in describing immediate speech stop, cancellation of in-flight work, and pipeline readiness for new input, plus Smart Turn Detection for natural turn-taking and Krisp-based false-interruption suppression in Pipecat Cloud. Missing for 10: independent hands-on validation of graceful context/turn recovery specifically (community evidence is about debugging/latency tooling, not barge-in correctness) and no explicit documentation of how conversation context is updated/rolled back after an interruption.

   • [claimed-docs] “When the user starts speaking while the bot is talking, the bot stops immediately, in-flight work is cancelled, and the pipeline is ready fo…”
   • [claimed-docs] “Interruptions (also called barge-in) let the user talk over the bot. When the user starts speaking while the bot is talking, the bot stops i…”
   • [claimed-docs] “Smart Turn Detection uses an advanced machine learning model to determine when a user has finished speaking and your bot should respond.”
   • [claimed-docs] “Smart Turn Detection recognizes natural conversational cues like intonation patterns and linguistic signals for more natural conversations.”
   • [claimed-docs] “Eliminates background noise and voices that cause false interruptions, powered by Krisp.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack addresses barge-in, interruption handling, speech-stopping, or turn recovery mechanics; the docs cover scheduling, workflows, analytics, and integrations but never mention conversational turn-taking behavior.

   ⚑ flag

2. developerEnable noise suppression or audio filtering so the agent stays coherent on noisy real-world calls

   weight 1 · round to Pipecat
   Pipecat✓fullclaimed8/10

   Pipecat Cloud explicitly ships Krisp-powered noise/background-voice suppression to eliminate false interruptions, and the framework's Smart Turn Detection complements this by recognizing genuine speech cues, keeping the agent coherent on noisy calls. Missing for 10: no first-party docs on self-hosted (non-cloud) noise suppression configuration, and no independent hands-on validation of suppression quality in real noisy environments.

   • [claimed-docs] “Eliminates background noise and voices that cause false interruptions, powered by Krisp.”
   • [claimed-docs] “Smart Turn Detection uses an advanced machine learning model to determine when a user has finished speaking and your bot should respond.”
   • [claimed-docs] “Smart Turn Detection recognizes natural conversational cues like intonation patterns and linguistic signals for more natural conversations.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence pack item mentions noise suppression, audio filtering, or any mechanism for handling noisy call environments; documentation covers scheduling, workflows, analytics, and voice cloning but not audio quality/noise handling.

   ⚑ flag

3. developerUse model-based end-of-turn detection beyond simple VAD silence timeouts so the agent doesn't talk over slow speakers

   weight 2 · round to Pipecat
   Pipecat✓fullclaimed8/10

   Pipecat documents 'Smart Turn Detection' as an ML model that determines end-of-turn based on intonation and linguistic cues, going beyond simple VAD silence timeouts, directly matching the story (pipecat-docs-9, pipecat-docs-31). Additional STT latency-tuning docs show the framework accounts for provider-specific delays to avoid premature cutoffs (pipecat-docs-15, pipecat-docs-20). Missing for 10: independent/hands-on evidence validating the model's accuracy on slow speakers in production, and no third-party benchmark of false-interruption reduction.

   • [claimed-docs] “Smart Turn Detection uses an advanced machine learning model to determine when a user has finished speaking and your bot should respond.”
   • [claimed-docs] “Smart Turn Detection recognizes natural conversational cues like intonation patterns and linguistic signals for more natural conversations.”
   • [claimed-docs] “Pipecat ships with measured P99 latency values for each supported service so that turn detection can account for this delay automatically.”
   • [claimed-docs] “Time To Final Segment (TTFS) measures how long it takes from the moment a user stops speaking until the STT service delivers the final trans…”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack discusses turn-taking, end-of-turn detection, VAD, or interruption handling in telli's voice agent; the docs cover scheduling, workflows, tools, and integrations but not conversational latency/turn-taking mechanics.

   ⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to telli
   Pipecat~partialprobed4/10

   Pipecat is fundamentally code-first: the CLI covers init/scaffolding, cloud deploy, evals, and context-hub (pipecat-probe-rt-1, pipecat-docs-16/34/37), and the framework itself is the primary interface. But evidence never explicitly confirms that Pipecat Cloud's web dashboard (agent profiles, concurrency settings, monitoring) exposes no exclusive UI-only functionality, nor does it document a full REST/OpenAPI surface (probe shows no discoverable OpenAPI spec, pipecat-probe-2) for programmatic parity with any cloud console. Missing for 10: explicit UI/API parity statement, documented OpenAPI/REST API for Pipecat Cloud console features, and confirmation no dashboard-only settings exist.

   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [claimed-docs] “Install the Pipecat CLI and scaffold the quickstart project (also writes AGENTS.md + CLAUDE.md)”
   • [claimed-docs] “pipecat init quickstart # Change to the project directory cd pipecat-quickstart”
   • [claimed-docs] “Pipecat Cloud offers different agent profiles, to best support your use case and compute needs.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.pipecat.ai/openapi.json, https://docs.pipecat.ai/swagger.json, https://docs.pipecat.ai/…”
   • [claimed-docs] “Pipecat ships a built-in development runner (pipecat.runner.run) that handles the server-side glue most bots need during development: creati…”

   proof ↗⚑ flag

   telli~partialprobed6/10

   telli exposes a REST API (with OpenAPI spec) covering contacts, scheduling calls, phone number import, custom tools, and webhooks, and also offers an MCP server so external AI tools can interact with Charlie. However, several UI-native features—agent builder/test-call dialog, live monitoring dashboard, side-by-side transcript/recording view, voice cloning setup, workflow trigger/recurring schedule configuration UI, and analytics dashboards—are not documented as API-accessible endpoints, so full UI/API parity is not evidenced. missing for 10: API endpoints for agent building/testing, live monitoring, voice cloning, workflow scheduling configuration, and analytics/reporting equivalent to UI dashboards.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
   • [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
   • [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Pipecat
   Pipecat~partialprobed5/10

   Pipecat is open-source (BSD-2) and self-hostable, meaning users inherently retain full control of their data (audio, transcripts, logs) rather than it being locked in a vendor's system — recordings via AudioBufferProcessor and transcripts via turn events are captured directly in the developer's own infrastructure. However, there's no explicit documentation of an 'export' feature, standardized open data formats, or migration tooling for leaving a hosted deployment (e.g., Pipecat Cloud). missing for 10: explicit data-export/format documentation, Pipecat Cloud data portability/exit guarantees, independent confirmation of format openness.

   • [claimed-docs] “Pipecat's \`AudioBufferProcessor\` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”
   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence of a bulk data-export feature or open-format data portability; only API endpoints to manage/read specific records and a data-retention deletion policy are documented, not a full self-service export/leave capability. Missing for 10: documented full-account export tool/endpoint, open-format (CSV/JSON) bulk export, and any explicit data-portability statement.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Pipecat
   Pipecat✓fullprobed9/10

   Pipecat is explicitly documented as an 'Open source Python framework' with a public GitHub repo, and a runtime probe confirms the pip package is BSD-2 licensed and installable/importable without any key, confirming genuine open-source source access. Missing for 10: no explicit citation of a LICENSE file or license text itself, only the probe's characterization.

   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”
   • [github] “Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, l…”
   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”

   proof ↗⚑ flag

   telli—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Pipecat
   Pipecat✓fullprobed8/10

   Pipecat is an open-source Python framework (BSD-2 licensed), pip-installable and runnable with no key/cloud dependency, with a documented dev runner and explicit note that the same bot file is portable to self-hosting setups; local inference (Ollama, Whisper) further confirms self-hosting without vendor lock-in. missing for 10: no dedicated self-hosting/production deployment guide (e.g., Docker/Kubernetes reference architecture) or independent case study of a large-scale self-hosted deployment.

   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”
   • [claimed-docs] “This is the property that makes the same bot file portable across the development runner, Pipecat Cloud, and most production self-hosting se…”
   • [community] “Local inference is already supported via Pipecat, you can use ollama or any custom OpenAI endpoint. Local STT is also supported via whisper,…”
   • [community] “Yes, Pipecat already supports that natively, so this can be done easily with ollama... Also, check out any provider they support, and it can…”

   proof ↗⚑ flag

   telli—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

Pricing

1. founderSee published per-minute or usage pricing and estimate cost per call before committing

   weight 2 · round drawn
   Pipecat—none0/10

   The evidence pack references a Pipecat Cloud pricing page (concurrency, agent profiles) but never shows actual per-minute/usage rates, a pricing table, or a cost calculator that would let a founder estimate cost per call; the core open-source framework itself is free/self-hosted with no billing model at all.

   • [claimed-docs] “Pipecat Cloud supports unlimited concurrency.”
   • [claimed-docs] “Pipecat Cloud offers different agent profiles, to best support your use case and compute needs.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack mentions pricing, per-minute rates, usage costs, or any cost calculator/estimator; the docs cover features (workflows, appointments, API, MCP, etc.) but nothing about published pricing.

   ⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round to Pipecat
   Pipecat~partialprobed3/10

   Pipecat is an open-source, self-hostable framework (pip-installable, runs locally or on your own infrastructure), which implicitly lets an operator choose where data/compute resides by choosing their own deployment location; however there is no explicit documentation of region/residency selection controls, especially for the hosted Pipecat Cloud offering. Missing for 10: explicit region-selection UI/API for Pipecat Cloud, data-residency compliance documentation (GDPR/SOC2 region guarantees), and confirmation that self-hosting is the only path to residency control.

   • [probe] “PROBE runtime (recorded 2026-09-05): pypi pipecat-ai 1.8.1 (BSD-2 OSS) installs and `import pipecat` succeeds with no key, printing its star…”
   • [claimed-docs] “Pipecat ships a built-in development runner (pipecat.runner.run) that handles the server-side glue most bots need during development: creati…”
   • [claimed-docs] “This is the property that makes the same bot file portable across the development runner, Pipecat Cloud, and most production self-hosting se…”
   • [claimed-docs] “Pipecat Cloud offers different agent profiles, to best support your use case and compute needs.”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack mentions data residency, region selection, or data storage location controls; data retention (deletion timing) is covered but that is a different capability from choosing storage region.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Pipecat—none0/10

   The evidence pack contains no mention of data-training opt-outs, data-usage policies, or privacy commitments regarding customer data and AI model training for either the open-source Pipecat framework or the hosted Pipecat Cloud service. Since Pipecat Cloud is a real hosted product where such a policy could plausibly exist, this axis applies, but no evidence supports it. Missing for 10: any privacy policy, ToS clause, or documentation stating customer data is not used to train models, and no independent corroboration.

   ⚑ flag

   telli—none0/10

   No evidence in the pack addresses AI training data usage or opt-out policies; data retention docs cover deletion of contacts/call data but not model-training exclusion.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat is a self-hostable open-source framework and also offers a hosted Pipecat Cloud option that processes voice/audio data, so data-retention/deletion controls are a fair question for this product category, but the evidence pack contains no documentation of retention policies, deletion APIs, or data lifecycle controls — only unrelated features like recording/transcription and metrics.

   ⚑ flag

   telli~partialclaimed6/10

   telli documents automatic data retention deletion (contacts and call data purged once they reach a defined age) and conditional consent-based recording, giving users some control over data lifecycle and privacy. However, there's no evidence of user-initiated manual deletion, export/right-to-access tools, or granular per-record deletion controls beyond the age-based policy. missing for 10: manual/on-demand deletion controls, data export capability, independent verification of retention enforcement.

   • [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”
   • [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Pipecat—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   telli—none0/10

   telli is a voice-agent platform, not a developer tool where telemetry opt-out is typically discussed, but the axis is still fair to ask (does the product track usage, and can a user disable it). The evidence pack (data retention, consent-based recording, etc.) never mentions any telemetry/usage-tracking opt-out mechanism for the product itself. Missing for 10: any documentation of telemetry collection practices or an opt-out setting/toggle.

   ⚑ flag

Call control

1. developerEscalate a live call to a human with warm or blind transfer, passing context along

   weight 2 · round to telli
   Pipecat—none0/10

   The evidence pack covers Pipecat's telephony deployment (webhook/carrier integration for Twilio, Telnyx, etc.), conversation flow transitions via Pipecat Flows, and subagent hand-off for tasks, but nothing addresses call transfer to a human agent (warm or blind) or passing call context/metadata during such a transfer. This is a reasonable telephony axis for a voice AI framework, but no citation demonstrates or documents this capability.

   ⚑ flag

   telli~partialclaimed4/10

   Docs confirm a transfer tool that can move a call to another agent or number, matching the core escalation-to-human idea, but there's no mention of distinct warm vs. blind transfer modes or explicit context-passing to the human recipient. missing for 10: explicit warm/blind transfer distinction, evidence of context/data hand-off during transfer, hands-on confirmation of the feature in practice.

   • [claimed-docs] “Transfer tools | Move the call to another agent or number.”

   proof ↗⚑ flag

2. developerMy agent can send DTMF keypresses, navigate IVR menus, and detect or leave voicemail

   weight 1 · round drawn
   Pipecat—none0/10

   Pipecat clearly supports telephony transports (Twilio, Telnyx, Plivo, Exotel, SIP) for building call-handling bots, so this axis applies, but the evidence pack contains no mention of DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving capabilities anywhere in the docs or community sources.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “Any Transport: WebRTC, SIP, PSTN”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”

   proof ↗⚑ flag

   telli—none0/10

   No evidence in the pack mentions DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving; telli's docs cover scheduling, transfers, web search tool, and webhooks but nothing about touch-tone or answering machine handling.

   ⚑ flag

Campaigns

1. founderRun batch outbound call campaigns with scheduling and throughput controls

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat's telephony docs cover per-call webhook-driven session handling (inbound/outbound single calls via Twilio/Telnyx/etc.) and unlimited concurrency on Pipecat Cloud, but there is no evidence of batch campaign management, call scheduling, pacing/throughput controls, or dialer-list orchestration for outbound campaigns — this is a fair ask for a telephony-capable voice AI framework but no such capability is documented.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”
   • [claimed-docs] “Pipecat Cloud supports unlimited concurrency.”
   • [claimed-docs] “Any Transport: WebRTC, SIP, PSTN”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   telli documents dialing windows, calling strategies, and retry behavior (telli-docs-9) plus a schedule-call API endpoint that respects dialer windows or can bypass them (telli-docs-17, telli-docs-18) and reach-rate/success metrics (telli-docs-7), which together support scheduled, throughput-controlled outbound calling. However there is no explicit mention of a 'campaign' concept, bulk contact upload, or concurrency/rate limits for large batches. Missing for 10: explicit batch/campaign creation UI or endpoint, bulk contact import for calling, and documented concurrency/throughput limits beyond dialing windows.

   • [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Optional flag to bypass dialing window restrictions for the scheduled call. When true, calls at the scheduled time regardless of dialing win…”
   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
   • [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”

   proof ↗⚑ flag

Numbers

1. developerProvision phone numbers and run both inbound and outbound calls through the platform's API

   weight 3 · round to telli
   Pipecat~partialclaimed4/10

   Docs show Pipecat integrates with telephony carriers (Twilio, Telnyx, Plivo, Exotel, SIP) to receive inbound call webhooks and run bots over PSTN/SIP transports, and CLI examples show running a bot against Twilio (`python bot.py -t twilio -x ...`), covering the 'run calls' half of the story. However, there is no evidence Pipecat itself exposes an API to provision/purchase phone numbers — that is left to the carrier's own console/API, not documented as a Pipecat capability. Missing for 10: native phone-number provisioning API/CLI, outbound call initiation API details, and any first-party number-management workflow.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “Any Transport: WebRTC, SIP, PSTN”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”

   proof ↗⚑ flag

   telli~partialprobed7/10

   telli's docs show a REST API with a schedule-call endpoint for outbound calls, an import-phone-number endpoint to bring SIP-trunk numbers under API control, webhooks for call events, and an OpenAPI spec confirming the API surface. However, inbound handling is documented mainly as manual forwarding/SIP trunk setup rather than a clear 'provision a new number via API' flow, and there's no explicit doc of purchasing/creating a fresh telli-hosted number through the API. missing for 10: a documented endpoint to provision/purchase brand-new phone numbers (not just import existing SIP trunk numbers), and clearer API-driven inbound call handling beyond forwarding.

   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
   • [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

Sip

1. platform-engineerConnect my own carrier or PBX via SIP trunking (or import Twilio/Telnyx numbers) instead of being locked to bundled telephony

   weight 2 · round to telli
   Pipecat✓fullclaimed7/10

   Docs explicitly describe telephony bots being invoked by carrier webhooks including 'Twilio, Telnyx, Plivo, Exotel, or your SIP provider,' and highlight 'Any Transport: WebRTC, SIP, PSTN' plus a working CLI example (`python bot.py -t twilio -x ...ngrok.io`), showing genuine carrier/SIP flexibility rather than lock-in to one bundled provider. Missing for 10: concrete walkthrough of raw SIP trunk/PBX configuration (vs. just carrier webhooks), and independent/hands-on confirmation of a non-Twilio/Telnyx SIP trunk actually working in production.

   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”
   • [claimed-docs] “Any Transport: WebRTC, SIP, PSTN”
   • [claimed-docs] “python bot.py -t twilio -x your-name.ngrok.io”

   proof ↗⚑ flag

   telli✓fullclaimed8/10

   Docs explicitly support importing numbers from a customer's own SIP trunk provider via a dedicated API endpoint, plus general SIP trunk connection for incoming/outgoing calls and call forwarding from an existing PBX/provider number. This directly matches the platform-engineer's need to bring their own carrier rather than being locked into bundled telephony. Missing for 10: no explicit mention of native Twilio/Telnyx number import (only generic SIP trunk import), and no independent/hands-on confirmation of the SIP trunk setup working in practice.

   • [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
   • [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
   • [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”

   proof ↗⚑ flag

Analytics

1. ai-native userThe platform's AI reviews my calls for me — scoring quality, flagging failures, and analyzing resolution automatically

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat ships developer-facing dev-time Evals (describe expected conversation, run against real agent) plus metrics/transcripts/audio-recording primitives, but there is no evidence of an AI system that automatically reviews production calls, scores quality, flags failures, or analyzes resolution after the fact — Evals is a pre-deployment testing tool, not post-call analytics.

   • [claimed-docs] “Pipecat Evals is the framework's built-in system for testing agent behavior. You describe a conversation and the behavior you expect, and Pi…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”
   • [claimed-docs] “Pipecat offers built-in metrics for both, which can be enabled with straightforward configuration options.”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”

   proof ↗⚑ flag

   telli~partialclaimed5/10

   telli provides analytics like reach rate, success rate, call outcome fields, transcripts, and manual feedback submission for agent improvement, but there's no evidence of automated AI-driven quality scoring, failure flagging, or resolution analysis performed autonomously by the platform's AI — feedback and analysis appear human-driven rather than AI-automated review. missing for 10: automated AI scoring of call quality, automatic failure/anomaly flagging, AI-generated resolution analysis without human review.

   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
   • [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
   • [claimed-docs] “Submit feedback on calls to continuously improve your agent.”

   proof ↗⚑ flag

2. founderSee call analytics — success rates, durations, outcomes, sentiment — in dashboards without building my own

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat exposes low-level building blocks (metrics, transcripts, audio recording, evals) that a developer could use to construct analytics, and a community debugging tool (Whisker) for pipeline tracing — but there is no evidence of a built-in dashboard surfacing success rates, call durations, outcomes, or sentiment without the founder building it themselves.

   • [claimed-docs] “Pipecat offers built-in metrics for both, which can be enabled with straightforward configuration options.”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”
   • [claimed-docs] “Pipecat's \`AudioBufferProcessor\` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [community] “With Whisker you can: View a live graph of your pipeline, watch frame processors flash in real time, select a processor to inspect its frame…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   telli's docs describe built-in dashboards tracking reach rate, call duration, and success rate, plus per-call analysis of transcripts and outcome fields, and a live monitoring overview—covering most of the story without needing custom tooling. However, there is no explicit mention of sentiment analysis in dashboards. missing for 10: sentiment scoring/analysis in dashboards, independent/hands-on corroboration of dashboard usability.

   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
   • [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
   • [claimed-docs] “Live Monitoring > Real-time call overview of your contacts”

   proof ↗⚑ flag

Monitoring

1. platform-engineerMonitor live calls in production and get alerts when agents misbehave or error rates spike

   weight 1 · round to telli
   Pipecat~partialcommunity4/10

   Pipecat provides building blocks for observability — built-in metrics (docs-5), turn-event transcripts (docs-4), audio recording (docs-3/21/29), and the community-highlighted Whisker tool that shows a live pipeline graph and frame-level debugger (pipecat-comm-3/4/5) — but these are development/debugging aids, not a production monitoring or alerting system. There is no evidence of dashboards for live production calls, error-rate-spike detection, or alert/notification integrations (e.g., PagerDuty, Slack alerts) for misbehaving agents. Missing for 10: production-grade dashboards for live call monitoring, automated error-rate/anomaly alerting, and integration with on-call/alerting systems.

   • [claimed-docs] “Pipecat offers built-in metrics for both, which can be enabled with straightforward configuration options.”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”
   • [community] “As someone who spends a lot of time looking at timestamped log lines to debug Pipecat pipelines, I'm a big fan of this work... For 1 and 3 […”
   • [community] “With Whisker you can: View a live graph of your pipeline, watch frame processors flash in real time, select a processor to inspect its frame…”
   • [community] “I had been thinking of working on something like this recently as a way to debug Pipecat pipelines. But the work Aleix has done goes far bey…”

   proof ↗⚑ flag

   telli~partialclaimed5/10

   telli offers a real-time Live Monitoring call overview (telli-docs-32) and webhooks that push real-time notifications on call events/status/outcomes (telli-docs-13, telli-docs-21), which a platform engineer could wire into an alerting pipeline, plus metric tracking like success/reach rate (telli-docs-7). However there is no documented built-in alerting mechanism, error-rate-spike detection, or agent-misbehavior alerting system. Missing for 10: native alert/notification thresholds, anomaly or error-rate-spike detection, and evidence of alert delivery (email/Slack/PagerDuty) tied to live monitoring.

   • [claimed-docs] “Live Monitoring > Real-time call overview of your contacts”
   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”

   proof ↗⚑ flag

Testing

1. developerTest agents with simulated conversations or evals before putting them on real phone calls

   weight 2 · round to Pipecat
   Pipecat✓fullprobed8/10

   Pipecat Evals is a documented, built-in framework feature letting developers describe conversations/expected behavior and run them against the real agent pipeline before deployment, and the runtime probe confirms a working `pipecat eval` CLI subcommand exists alongside `init`/`cloud`. This directly addresses simulated-conversation testing before real phone calls, though evidence doesn't show telephony-specific eval scenarios or third-party validation of eval accuracy. Missing for 10: independent/community corroboration of Evals in practice, and explicit examples of testing telephony-specific call flows via evals.

   • [claimed-docs] “Pipecat Evals is the framework's built-in system for testing agent behavior. You describe a conversation and the behavior you expect, and Pi…”
   • [claimed-docs] “You describe a conversation and the behavior you expect, and Pipecat runs it against your real agent (the same pipeline, the same services, …”
   • [probe] “PROBE runtime (recorded 2026-09-05): the official Pipecat CLI (pypi pipecat-ai[cli]) ran keylessly via uvx — `pipecat --help` lists init (pr…”

   proof ↗⚑ flag

   telli~partialclaimed5/10

   telli's agent builder includes a 'Test call' feature to trial a draft or saved agent version and review the recording/transcript side-by-side before going live, which covers pre-production testing, and feedback submission helps iterate on agent quality. However, there is no evidence of simulated/synthetic conversation runs, automated eval suites, or scripted test scenarios independent of an actual phone call. Missing for 10: automated evals framework, non-call simulated conversation testing, batch/regression testing tools.

   • [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
   • [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
   • [claimed-docs] “Submit feedback on calls to continuously improve your agent.”

   proof ↗⚑ flag

Post call

1. developerExtract structured data from every call — outcomes, entities, dispositions — delivered via API or webhook after the call

   weight 2 · round to telli
   Pipecat~partialclaimed4/10

   Pipecat provides building blocks that a developer could use to build this — Flows functions can 'process data by interfacing with external systems and APIs' (function calling) and turn events/transcripts capture user and assistant messages, plus telephony webhooks for call events — but there is no documented turnkey feature for automatic post-call structured extraction (outcomes/entities/dispositions) delivered via a dedicated API or webhook. Missing for 10: a built-in post-call summary/disposition-extraction pipeline, a documented structured-output schema for call outcomes, and an out-of-box webhook delivery mechanism specifically for post-call analytics (only inbound-call webhooks and generic function-calling/transcript primitives are documented).

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data by interfacing with external systems and APIs... 2. Progress the conversa…”
   • [claimed-docs] “Flows auto-derives the function's metadata — name, description, parameter properties (with their descriptions), and which parameters are req…”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”
   • [claimed-docs] “Telephony bots have a different shape than WebRTC bots. The session doesn't start because a client sent your dispatcher an HTTP request — it…”
   • [claimed-docs] “the carrier (Twilio, Telnyx, Plivo, Exotel, or your SIP provider) is calling your webhook to tell you there's an inbound call”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   telli documents webhooks pushing real-time call event/status/outcome data and a REST API for programmatic access, plus conversation views showing appointment/outcome fields and call outcome analysis, supporting structured post-call data delivery. However, there's no explicit documentation of a structured schema for entities/dispositions extraction or example payloads showing the full breadth of structured fields promised. missing for 10: example webhook/API payload showing structured entities and disposition fields, documentation of a dedicated 'call outcomes' data model, independent/hands-on confirmation of data completeness.

   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
   • [claimed-docs] “Conversations now show appointments saved during a call, including the time, status, hosts, and provider link.”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”

   proof ↗⚑ flag

Tools

1. ai-native userMy voice agent can plug in MCP servers as tool sources so one integration grants it whole toolsets mid-call

   weight 2 · round drawn
   Pipecat—none0/10

   The evidence only shows Pipecat's context-hub *acting as* an MCP server for coding-agent tooling (pipecat-docs-11/38), which is the opposite direction from what the story asks — a voice agent consuming external MCP servers as tool sources mid-call. Function/tool calling is documented via Pipecat Flows (pipecat-docs-6/22/30/39), but no evidence shows the voice agent connecting to or importing toolsets from external MCP servers during a call.

   • [claimed-docs] “pipecat context-hub install registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “pipecat context-hub install` registers the hub as an MCP server with your coding agent and builds the local index”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”

   proof ↗⚑ flag

   telli—none0/10

   telli documents custom tools connecting to external APIs (telli-docs-20) and even an MCP server (telli-docs-22, telli-probe-3), but that MCP server lets external AI tools like Claude/ChatGPT talk to telli's Charlie assistant — it is telli acting as an MCP server, not the voice agent consuming external MCP servers as a tool source mid-call. There is no evidence the voice agent itself can plug in MCP servers to gain toolsets during a call.

   • [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
   • [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
   • [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”

   proof ↗⚑ flag

2. developerMy agent can call external APIs and custom functions mid-conversation and speak the result without awkward dead air

   weight 3 · round to Pipecat
   Pipecat✓fullclaimed8/10

   Pipecat Flows functions explicitly support 'processing data by interfacing with external systems and APIs' mid-conversation and auto-derive function schemas from code, while interruption handling and turn detection docs describe how the pipeline manages timing/dead-air around such calls. Missing for 10: no concrete hands-on example/demo showing latency-masking (e.g., filler speech) during a live API call, and no independent benchmark of perceived dead-air during function execution.

   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data ... 2. Progress the conversation by transitioning between nodes”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: Process data by interfacing with external systems and APIs...Progress the conversation by…”
   • [claimed-docs] “Functions in Pipecat Flows serve two key purposes: 1. Process data by interfacing with external systems and APIs... 2. Progress the conversa…”
   • [claimed-docs] “Flows auto-derives the function's metadata — name, description, parameter properties (with their descriptions), and which parameters are req…”
   • [claimed-docs] “When the user starts speaking while the bot is talking, the bot stops immediately, in-flight work is cancelled, and the pipeline is ready fo…”
   • [claimed-docs] “Interruptions (also called barge-in) let the user talk over the bot. When the user starts speaking while the bot is talking, the bot stops i…”
   • [claimed-docs] “Smart Turn Detection uses an advanced machine learning model to determine when a user has finished speaking and your bot should respond.”

   proof ↗⚑ flag

   telli~partialclaimed6/10

   Docs confirm custom tools let agents call external APIs mid-call (telli-docs-20) and built-in tool calls like web_search operate during live calls (telli-docs-30), plus transfer tools show mid-call action execution (telli-docs-31). However, there is no documentation addressing latency masking or filler-speech to avoid 'dead air' while awaiting API responses. missing for 10: explicit evidence of latency-hiding/filler speech during tool calls, independent hands-on confirmation of smooth voice continuity.

   • [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
   • [claimed-docs] “For a Duo agent, open Tools > System and enable web_search to let the agent search the web for current public information during calls.”
   • [claimed-docs] “Transfer tools | Move the call to another agent or number.”

   proof ↗⚑ flag

Recording

1. platform-engineerRetrieve full call recordings and transcripts programmatically for every call

   weight 2 · round drawn
   Pipecat~partialclaimed5/10

   Pipecat provides building blocks — AudioBufferProcessor for capturing audio recordings and turn-event based transcript collection — that a platform engineer could wire into their own storage/retrieval system, but there's no documented built-in centralized recordings/transcripts store or query API for retrieving them programmatically across all calls. Missing for 10: a first-party recordings/transcripts storage service or retrieval API, evidence of per-call metadata/indexing, and any hands-on confirmation of retrieving historical call data at scale.

   • [claimed-docs] “Pipecat's \`AudioBufferProcessor\` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's AudioBufferProcessor makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's `AudioBufferProcessor` makes it easy to capture high-quality audio recordings of both the user and bot during interactions.”
   • [claimed-docs] “Pipecat's turn events make it easy to collect both user and assistant messages as they occur.”

   proof ↗⚑ flag

   telli~partialprobed5/10

   Docs confirm transcripts and recordings exist and can be reviewed in-app (side-by-side view, consent-based recording) and telli exposes a general REST API plus webhooks for call events, but no endpoint is documented that explicitly returns full call recordings or transcripts programmatically for every call. missing for 10: a documented GET/recording or GET/transcript API endpoint, confirmation of bulk/enumerable retrieval, and independent verification that recordings are accessible via the API rather than only in the UI.

   • [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
   • [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
   • [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”
   • [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
   • [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
   • [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

Transcription

1. developerGet accurate real-time transcription with control over the STT provider, language models, or key terms

   weight 2 · round to Pipecat
   Pipecat~partialcommunity6/10

   Docs and community evidence confirm Pipecat lets developers swap STT providers and language models with one line of code (200+ services, local Whisper/Ollama), and it exposes STT-specific latency metrics (TTFS, P99) for tuning accuracy/speed tradeoffs. However, there is no evidence of support for passing custom vocabulary or 'key terms'/boost-word lists to STT providers, and no independent benchmark validating transcription accuracy claims. Missing for 10: explicit key-terms/vocabulary-boost configuration support, and independent/hands-on accuracy validation.

   • [claimed-docs] “Swap speech, language, and vision services from any of 200+ integrated providers and services — usually one line of code.”
   • [claimed-docs] “Pipecat ships with measured P99 latency values for each supported service so that turn detection can account for this delay automatically.”
   • [claimed-docs] “Time To Final Segment (TTFS) measures how long it takes from the moment a user stops speaking until the STT service delivers the final trans…”
   • [community] “Local inference is already supported via Pipecat, you can use ollama or any custom OpenAI endpoint. Local STT is also supported via whisper,…”
   • [community] “Yes, Pipecat already supports that natively, so this can be done easily with ollama... Also, check out any provider they support, and it can…”

   proof ↗⚑ flag

   telli—none0/10

   telli documents transcript viewing and side-by-side playback (telli-docs-29) but provides no evidence of developer-facing control over STT provider selection, choice of underlying language models, or custom key-term/vocabulary boosting for transcription accuracy.

   • [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”

   proof ↗⚑ flag

Voices

1. founderClone a custom brand voice and use it for my agents, with a documented consent process

   weight 2 · round to telli
   Pipecat—none0/10

   Pipecat's evidence covers swapping among 200+ TTS/STT providers and general voice pipeline features, but nothing addresses custom voice cloning or any documented consent process for cloning a brand voice — this is a fair question since Pipecat is a voice-AI framework, but no evidence supports it being delivered.

   • [claimed-docs] “Swap speech, language, and vision services from any of 200+ integrated providers and services — usually one line of code.”
   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”

   proof ↗⚑ flag

   telli~partialclaimed5/10

   Voice cloning is documented as a real feature (telli-docs-27) letting founders give agents a custom voice, but the pack's only consent-related documentation concerns call recording consent (telli-docs-26), not a consent process specifically for cloning someone's voice. Missing for 10: explicit documented consent/authorization workflow for the voice being cloned (e.g., proof of rights from the voice owner), and any legal/compliance guardrails for cloning third-party voices.

   • [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”
   • [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”

   proof ↗⚑ flag

2. developerChoose from a broad voice library or plug in multiple TTS providers to get the voice I want

   weight 2 · round to Pipecat
   Pipecat✓fullcommunity8/10

   Docs and community evidence confirm Pipecat supports swapping speech services (TTS/STT) across 200+ integrated providers with typically one line of code, plus community confirmation of easy onboarding of any provider and local TTS/STT options (ollama, whisper). Missing for 10: an explicit enumerated 'voice library' list or curated voice catalog UI, and independent benchmark of ease/quality across providers beyond vendor/community anecdotes.

   • [claimed-docs] “Swap speech, language, and vision services from any of 200+ integrated providers and services — usually one line of code.”
   • [claimed-docs] “Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 150+ AI services with ultra-low latency.”
   • [community] “Local inference is already supported via Pipecat, you can use ollama or any custom OpenAI endpoint. Local STT is also supported via whisper,…”
   • [community] “Yes, Pipecat already supports that natively, so this can be done easily with ollama... Also, check out any provider they support, and it can…”
   • [claimed-docs] “Pipecat ships with measured P99 latency values for each supported service so that turn detection can account for this delay automatically.”

   proof ↗⚑ flag

   telli~partialclaimed3/10

   Docs mention voice cloning to give an agent a custom voice, but there is no evidence of a curated voice library to choose from or the ability to plug in multiple external TTS providers as the story requires. missing for 10: evidence of a selectable voice library, multi-provider TTS integration, developer API/config for switching TTS engines.

   • [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”

   proof ↗⚑ flag