Bolna vs Deepgram Voice Agent

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 Bolna
   Bolna✓fullprobed8/10

   Bolna offers all three surfaces needed for agent-native provisioning: a documented API quickstart to create an agent, attach a number, and place a call (bolna-docs-14, bolna-docs-15), a native Go CLI to manage agents, calls, and phone numbers from the terminal (bolna-docs-16, bolna-probe-4), and an official MCP server to connect Claude/Cursor/Windsurf clients (bolna-docs-17, bolna-probe-3), all without requiring dashboard interaction. missing for 10: independent/hands-on confirmation that MCP or CLI can complete the full create-attach-call flow end-to-end (only vendor docs), and no OpenAPI spec was resolvable (bolna-probe-2) to verify API completeness.

   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialprobed5/10

   Deepgram documents agent creation via reusable agent configs (UUID-based), telephony connectivity for inbound/outbound calls, and a CLI with a built-in MCP server giving AI coding tools API access — the building blocks for programmatic provisioning exist. However, the evidence shows phone-call handling is done via a Twilio bridge (server code required) rather than a native Deepgram 'attach number/place call' API, and no doc shows the CLI or MCP server actually exposing agent-create + number-attach + call-place as a single end-to-end flow. Missing for 10: explicit CLI/MCP commands for provisioning a phone number and placing a call, and confirmation that this full workflow avoids external glue code/dashboard steps.

   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”

   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 drawn
   Bolna—none0/10

   No evidence shows Bolna's own platform AI generating or improving prompts, flows, or test cases from a description; the closest feature (build-with-ai/mcp) is an MCP server that lets external AI clients like Claude or Cursor manage the account via API, not the platform itself authoring agents. Templates can be cloned, but that's static copying, not AI-generated authoring.

   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [claimed-docs] “Clone any template and customize it for your business.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence covers building agents manually (prompting, function calling, reusable configs, MCP server for coding tools) but there is no mention of the platform's own AI generating or improving prompts, flows, or test cases from a description; the MCP server exposes Deepgram APIs to external coding assistants rather than being an AI author within the platform itself.

   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

   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 Bolna
   Bolna✓fullclaimed8/10

   Docs directly support the story: templates can be cloned and customized, build/deploy claimed under 5 minutes, voice/accent selection, phone number and telephony setup (BYOT/SIP), and a quickstart walking through key verification, agent creation, placing a call, and fetching a transcript in ~5 minutes. This covers prompt (agent config/templates), voice (voice/provider selection), and phone number (telephony/SIP) end-to-end for a first live call within an hour. Missing for 10: independent/hands-on confirmation of the 'under 5 minutes' or 'first call in an hour' claims beyond vendor docs, and no third-party success report.

   • [claimed-docs] “Build and deploy in under 5 minutes”
   • [claimed-docs] “Clone any template and customize it for your business.”
   • [claimed-docs] “You can choose different voices, accents, and speaking styles to match your brand.”
   • [claimed-docs] “Bring Your Own Telephony (BYOT) lets you connect any standards-compliant SIP trunk to the Bolna platform.”
   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Bolna supports Deepgram, Azure, ElevenLabs, and more.”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Deepgram provides all core building blocks — prompting, voice/LLM selection, telephony via Twilio bridging, and a single WebSocket API — that together could plausibly get a developer to a first live call quickly. However, the telephony path requires standing up your own server to bridge Twilio audio to the Voice Agent WebSocket, which is nontrivial integration work rather than a turnkey 'phone number in one hour' flow, and there's no first-party quickstart or time-to-first-call benchmark cited. missing for 10: an end-to-end quickstart/tutorial demonstrating full setup within an hour, evidence of a managed/no-code telephony number provisioning path, and independent hands-on confirmation of setup speed.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
   • [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”

   proof ↗⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialclaimed6/10

   Docs claim the agent "detects and switches mid-call on its own" and marketing mentions "multilingual intelligence" for thousands of calls, directly supporting the story, but there's no detail on supported languages, configuration options, or independent/hands-on verification of mid-call switching reliability. Missing for 10: language list/configuration docs, hands-on or third-party confirmation of switching accuracy, and edge-case handling details.

   • [claimed-docs] “the agent detects and switches mid-call on its own”
   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed5/10

   Deepgram's docs confirm multilingual voice agent support, noting that STT and TTS model choices must be configured for the target language (deepgram-docs-10), but the evidence pack does not explicitly document automatic language detection or dynamic switching mid-call — only static multilingual configuration is described. Missing for 10: explicit documentation of automatic language detection, mid-call language switching mechanics, and independent/hands-on confirmation of this behavior in production.

   • [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Bolna—none0/10

   Evidence shows Bolna is built around APIs, CLI, and MCP server for defining agents and multi-step outreach sequences (bolna-docs-12, bolna-docs-16, bolna-docs-17), but there is no mention of a visual/no-code builder with branching, states, or handoffs; workflows are described as 'driven entirely through the Bolna API.' Missing for 10: any visual flow-builder UI, drag-and-drop branching/state design, no-code handoff configuration.

   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [github] “Bolna is the end-to-end open source production ready framework for quickly building LLM based voice driven conversational applications.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   All evidence describes a code/API-first architecture (WebSocket connections, JSON Settings messages, system prompts, function calling, CLI/SDK) rather than a visual no-code builder; there is no mention of a drag-and-drop flow designer, branching UI, or state-machine editor. missing for 10: any visual builder UI, no-code branching/state design, or drag-and-drop handoff configuration.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
   • [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”

   proof ↗⚑ flag

Personalization

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

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   The evidence pack covers agent creation, extraction categories, call summaries, workflows, and providers, but nothing documents passing per-caller dynamic variables or context payloads at call time to personalize a conversation.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Deepgram supports prompting, reusable agent configs (passed at call time via UUID), function calling, and mid-call message injection, which together allow injecting per-call context/variables into agent behavior; A/B testing of configs also implies runtime parameterization. However there is no explicit documented mechanism for templated dynamic variables (e.g., {{caller_name}}) or a dedicated per-caller context API akin to other platforms. missing for 10: explicit dynamic variable templating syntax, dedicated per-caller metadata injection API, hands-on example of personalizing a call with caller-specific data.

   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
   • [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
   • [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”

   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
   Bolna—none0/10

   Bolna is a voice AI agent platform (telephony, TTS/STT, LLM providers, workflows) but the evidence pack contains no mention of a knowledge base, document ingestion, or RAG capability for grounding agent responses in custom content. This axis clearly applies to conversational agent-building platforms, so absence of evidence yields 'none'.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers architecture, function calling, multi-agent handoff, telephony, prompting, and LLM providers, but nowhere documents a built-in knowledge base or RAG feature for grounding the agent on user documents. Function calling ([deepgram-docs-2]) could theoretically be wired to an external retrieval system, but that is not the same as a built-in KB/RAG capability, and no such feature is described.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round drawn
   Bolna✓fullprobed9/10

   A probe confirms llms.txt is live and returns 200 with structured agent-oriented doc links (bolna-probe-1), and Bolna also documents an official MCP server for connecting AI clients like Claude/Cursor to its docs/account (bolna-docs-17, bolna-probe-3), directly enabling agent-native consumption of its documentation. Missing for 10: no independent third-party confirmation that agents successfully use llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.bolna.ai/llms.txt # Bolna Docs > Quickly build and deploy conversational Voice AI agents - [Home]…”
   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullprobed9/10

   Direct probe confirms llms.txt exists at developers.deepgram.com/llms.txt (HTTP 200) with explicit AI-agent instructions, and docs pages support .md suffix for clean markdown retrieval, both verified by live probes. missing for 10: no independent third-party confirmation of an agent actually consuming this in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown …”
   • [probe] “PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL.…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Bolna~partialprobed6/10

   Bolna offers a CLI (single Go binary) for managing agents, calls, phone numbers, and batches from the terminal, plus a REST API for scripted call creation and transcript retrieval — both usable in CI/automation pipelines without a GUI. However, there's no explicit CI/pipeline example, headless-mode documentation, or exit-code/automation-specific guidance. missing for 10: explicit CI integration examples/guides, documented non-interactive/headless flags or exit codes, third-party confirmation of CI usage.

   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”
   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialprobed6/10

   The Voice Agent is a WebSocket API (no GUI dependency) and Deepgram ships a terminal-based `dg` CLI for scripting Deepgram operations (transcribe, synthesize, manage account) which is inherently automatable/CI-friendly, and temporary tokens support secure automated auth. However, there is no explicit documentation of running the Voice Agent itself headlessly in CI pipelines, no CI/CD examples, and the CLI's primary use-cases described are transcription/synthesis rather than orchestrating full voice-agent sessions programmatically. Missing for 10: dedicated CI/headless automation guide for Voice Agent sessions, example CI pipeline configs, and confirmation the CLI can drive the Agent API end-to-end rather than just STT/TTS.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
   • [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Bolna—none0/10

   Evidence shows Bolna ships an MCP *server* so external clients like Claude, Cursor, or Windsurf can control a Bolna account (bolna-docs-17, bolna-probe-3) — this is the reverse direction from the story, which asks whether Bolna's own agents can plug in external MCP servers to gain their tools. No evidence describes Bolna voice agents consuming or calling external MCP servers.

   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram Voice Agent supports function calling for custom tool use, but there is no evidence the Voice Agent can act as an MCP client to consume external MCP servers' tools. The only MCP-related evidence is a built-in MCP *server* in the `dg` CLI that lets coding tools access Deepgram's APIs — the opposite direction of the story.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

   proof ↗⚑ flag

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

   weight 3 · round to Bolna
   Bolna✓fullprobed8/10

   Bolna documents an official MCP server that lets Claude, Cursor, Windsurf, or any MCP client connect to a Bolna account, confirmed by both docs and an independent probe hitting the live page. Missing for 10: independent hands-on validation or community confirmation of the MCP server working in practice beyond the docs/probe.

   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullprobed7/10

   Deepgram ships an official MCP server (bundled in the dg CLI) that lets AI coding tools/agents connect directly to Deepgram's APIs, confirmed both in docs and via a dedicated agentic-tools page. This directly satisfies the story of connecting an agent to Deepgram via an official MCP server. Missing for 10: independent/hands-on verification that the MCP server works reliably in practice, and more detail on which Voice Agent capabilities specifically are exposed through it.

   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
   • [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Bolna✓fullprobed8/10

   Bolna documents an official CLI (single Go binary) letting users manage agents, calls, phone numbers, and batches from the terminal, corroborated by a live docs probe confirming the page exists. missing for 10: no independent/hands-on community usage reports or version/release history confirming real-world adoption beyond first-party docs.

   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullprobed8/10

   Deepgram ships an official 'dg' CLI for transcribing files, streaming audio, synthesizing speech, and managing accounts from the terminal, and it even embeds an MCP server for AI coding tools, directly supporting agentic/AI-native workflows. Missing for 10: independent/hands-on corroboration beyond first-party docs and more detail on CLI coverage of Voice Agent-specific features.

   • [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

   proof ↗⚑ flag

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

   weight 3 · round to Deepgram Voice Agent
   Bolna✓fullprobed8/10

   Bolna provides a documented public API with quickstart, authentication, agent/call/extraction endpoints, and workflow automation entirely through the API, plus a CLI and MCP server built on top of it. Missing for 10: a discoverable OpenAPI/Swagger spec (probe found all standard OpenAPI paths 404) and independent third-party corroboration of API robustness.

   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”
   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullprobed9/10

   Deepgram publishes a documented public API (WebSocket-based Voice Agent API plus OpenAPI spec confirmed live), extensive docs covering endpoints, function calling, LLM providers, telephony, and auth, and even a CLI/MCP server for programmatic/agentic access, making it clearly drivable by an AI-native user. Missing for 10: independent third-party corroboration of API usage beyond vendor docs.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
   • [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
   • [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”

   proof ↗⚑ flag

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

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   Bolna documents API key creation but there is no evidence of scoped or least-privilege credential controls (e.g., role-based permissions, scoped tokens, restricted access levels) — only a single account-wide key generation flow is described.

   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed4/10

   Deepgram documents temporary, short-lived tokens as an alternative to traditional API keys for secure, limited-duration access (deepgram-docs-14), which partially satisfies a least-privilege credential story, but there is no evidence of granular scopes/permissions (e.g., restricting a key to specific endpoints or agent capabilities) or role-based access control for agents. Missing for 10: documented scope/permission granularity, per-agent key restriction, and evidence of enforcement/verification of least-privilege in practice.

   • [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Bolna~partialprobed5/10

   Bolna documents an official Web Call SDK (bolna-docs-18) under a 'developer-resources/sdks' path, plus a CLI and MCP server, giving AI-native builders some official tooling to build against, but there is no evidence of broader language SDKs (e.g., Python, Node, Go client libraries) beyond the browser-based Web Call SDK. missing for 10: multi-language server-side SDKs, independent/hands-on verification of SDK usability, breadth beyond the single web-call SDK.

   • [claimed-docs] “The Web Call SDK connects a browser tab directly to a Bolna voice agent for a live, two-way conversation.”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”
   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialprobed5/10

   Evidence shows an official 'Browser Agent SDK' with composable packages, plus an OpenAPI spec, CLI, and MCP server for developer tooling, indicating some official SDK/build tooling exists. However, evidence does not mention broader server-side/language SDKs (Python, Node, Go, etc.) commonly expected for building agentic applications, nor independent corroboration of SDK quality. Missing for 10: multi-language SDK documentation, independent/hands-on developer reports, broader agentic build examples beyond browser.

   • [claimed-docs] “Browser Agent SDK: add voice AI to any web application via four composable packages.”
   • [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Bolna—none0/10

   No evidence in the pack mentions webhooks or event subscription for Bolna; the docs cover agents, calls, CLI, MCP, SIP, pricing, and security but nothing about outbound event notifications. Missing for 10: any webhook registration/config API, event payload documentation, or third-party confirmation of webhook delivery.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack shows Deepgram Voice Agent operates via a persistent WebSocket connection for real-time audio streaming, not webhook-based event subscription; no documentation mentions webhooks for event notifications (e.g., call completion, transcript ready, errors). Absence of evidence for an applicable capability yields 'none'.

   ⚑ flag

Agentic features

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

   weight 2 · round to Bolna
   Bolna~partialclaimed5/10

   Bolna offers agent-level call_summary_enabled to auto-generate AI summaries and an extraction-categories API to pull structured insights out of call data, both of which are AI-generated insights derived from user data (calls). However, there's no evidence of broader cross-call analytics, trend insights, or proactive suggestions surfaced in a dashboard beyond per-call outputs. Missing for 10: aggregated/dashboard-level insights across multiple calls, proactive recommendation surfacing, and independent confirmation of quality of generated summaries/extractions.

   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers Deepgram Voice Agent's API capabilities (function calling, multi-agent orchestration, telephony, LLM providers, prompting) but contains no mention of an in-product analytics dashboard, conversation insights, or AI-generated suggestions derived from a user's own data. While such a feature (e.g., call analytics/insights) is plausible for a voice AI platform, no evidence shows Deepgram surfaces this.

   ⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialprobed6/10

   Bolna's workflows feature lets users build multi-step outreach sequences (voice calls, WhatsApp, API calls, waits, retries) driven entirely through the API, which supports background automation, and the CLI can manage batches of calls autonomously. However there's no documented evidence of scheduling/triggers, monitoring/alerting on autonomous runs, or a dashboard for managing long-running background jobs beyond the API-driven workflow primitives. missing for 10: scheduling/trigger mechanisms, autonomous-run monitoring/alerting, independent hands-on confirmation of unattended long-running workflows.

   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent—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

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

   weight 3 · round drawn
   Bolna—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

   Deepgram Voice Agent—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 userOperate the product with natural-language commands

   weight 2 · round to Deepgram Voice Agent
   Bolna✓fullprobed7/10

   Bolna ships an official MCP server that lets AI-native tools like Claude, Cursor, or Windsurf connect to a Bolna account and operate it (manage agents, calls, etc.) via natural-language commands, confirmed both in docs and via a live probe. Missing for 10: independent/hands-on verification that the MCP integration works as described, and no additional natural-language control surfaces (e.g., chat-based dashboard) beyond MCP.

   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullclaimed8/10

   Deepgram Voice Agent is fundamentally a conversational system: users interact via natural spoken language, and the agent supports function calling to perform tasks, live prompting to shape behavior, and mid-call message injection—all driven by natural-language conversation rather than rigid commands. This is core, well-documented functionality (docs-2, docs-7, docs-11) directly matching the story's intent for an ai-native/agentic persona. Missing for 10: independent/hands-on validation of natural-language command accuracy and no evidence of complex multi-turn command chaining reliability from third-party sources.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
   • [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
   • [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Bolna—none0/10

   Bolna has an API reference doc listing basics like API key creation, but there is no evidence of an interactive reference with runnable/try-it examples, and a probe for a machine-readable OpenAPI spec (which typically powers such interactive docs) returned 404 on all checked paths.

   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence shows an OpenAPI spec exists and docs pages are available as clean Markdown, but there is no evidence of an interactive API reference with runnable/try-it-now examples (e.g., embedded playground, live code execution, or Swagger/Postman-style explorer). Missing for 10: interactive explorer UI, runnable/executable code snippets, live request/response testing.

   • [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown …”
   • [probe] “PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL.…”

   proof ↗⚑ flag

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

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   A direct probe for OpenAPI/Swagger spec files at all standard locations returned 404s, and no evidence pack item shows a downloadable machine-readable API spec despite having an API reference page.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”
   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”

   proof ↗⚑ flag

   Deepgram Voice Agent✓fullprobed9/10

   A probe confirms Deepgram publishes a machine-readable OpenAPI spec at openapi.json containing the 'openapi' key, directly satisfying the story. Missing for 10: no first-party docs page explicitly announcing/describing the OpenAPI spec's coverage or versioning.

   • [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Bolna—none0/10

   No evidence pack item mentions a sandbox environment, test mode, staging account, or separation from production data for Bolna; the closest concepts (self-hosting, BYOK, data residency) are about deployment/privacy, not a distinct sandbox/test mode. missing for 10: any mention of a sandbox/test environment, test API keys, or safe testing workflow that avoids production data.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence pack item mentions a sandbox environment, test/dev API keys, or a way to test without touching production data or usage; only production endpoints, EU endpoint, and opt-out flags are documented. Missing for 10: sandbox/test-mode environment, documentation of non-production keys or test credits, any guidance on isolating test traffic from production data.

   ⚑ flag

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

   weight 2 · round drawn
   Bolna—none0/10

   There is a changelog page referenced and an API reference, but no evidence of API versioning scheme or a documented deprecation policy anywhere in the pack; OpenAPI spec probes even returned 404s. Missing for 10: versioned API endpoints/headers, explicit deprecation policy documentation, migration/versioning changelog entries.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”
   • [claimed-docs] “Click the Create a new API Key button to generate your unique authentication credentials.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack shows extensive Voice Agent API documentation, an OpenAPI spec, CLI, and MCP server, but contains no mention of API versioning scheme or a documented deprecation policy for the Voice Agent API.

   ⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialclaimed5/10

   The CLI explicitly manages 'batches' of calls alongside agents and phone numbers (bolna-docs-16), and the platform claims to power 'thousands of inbound and outbound calls every minute' (bolna-docs-22), implying built-in bulk calling capability. However, there is no documentation of a specific bulk API endpoint, CSV/list upload, or bulk agent/category management workflow. Missing for 10: explicit bulk-operation API docs (e.g., batch call creation, bulk agent updates), a documented interface for uploading many items at once, and independent confirmation of bulk throughput.

   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”
   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”

   proof ↗⚑ flag

   Deepgram Voice Agent—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

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

   weight 3 · round to Deepgram Voice Agent
   Bolna~partialclaimed4/10

   Bolna's workflow feature lets users chain voice calls, WhatsApp messages, API calls, waits and retries via the API, which is a form of automation, but the docs never describe defining conditional 'if event X happens then do Y' rules or an event/trigger system — it's presented as sequential outreach flows rather than rule-based event triggers. Missing for 10: explicit event-trigger/rule definition syntax, conditional branching logic, and any webhook-or-event-driven automation examples beyond the sequential workflow description.

   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed5/10

   Deepgram Voice Agent supports function calling that lets the agent trigger actions during a live conversation, and features like InjectAgentMessage and multi-agent handoff suggest some event-driven behavior, but this is developer-defined logic (via function calling code) rather than a declarative rules engine for automatically triggering actions on arbitrary events. missing for 10: a documented rules/trigger engine (if-this-then-that style), event subscription system, or automation workflow builder distinct from manual function-calling code.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
   • [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Bolna—none0/10

   Bolna's workflow docs describe multi-step outreach sequences with waits and retries (bolna-docs-12), but there is no evidence of a scheduler for recurring/cron-based jobs or workflows that re-trigger automatically over time. missing for 10: recurring/scheduled trigger mechanism, cron-like job definitions, evidence of periodic re-execution.

   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”

   proof ↗⚑ flag

   Deepgram Voice Agent—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 userVersion, review, and roll back my automations

   weight 1 · round to Deepgram Voice Agent
   Bolna—none0/10

   Bolna is a voice AI agent platform (agent creation, calls, workflows, telephony) but the evidence pack shows no version control, review workflow, or rollback mechanism for automations/agents — no mention of agent versioning, change history, approval flows, or revert capability.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed3/10

   Deepgram's Reusable Agent Configurations let you persist a named agent config and reference it by UUID, and support A/B testing two configs in parallel, which is adjacent to versioning, but there is no documented version history, diff/review workflow, or explicit rollback mechanism. missing for 10: version history tracking, review/approval workflow, explicit rollback capability, changelog or diffing between config versions.

   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”

   proof ↗⚑ flag

Compliance

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

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   The evidence pack shows security/data-residency features and call-summary toggles, but nothing about call-recording consent, per-call recording enable/disable controls, disclosure/announcement features, or configurable retention periods for recordings/transcripts. No mention of recording consent mechanisms or retention settings anywhere in the docs pack.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed4/10

   Deepgram documents general data-privacy controls (per-request opt-out from retention via mip_opt_out, EU-region processing endpoint) that touch on data retention/residency, but there is no explicit documentation of per-call recording toggles, consent/disclosure workflows, or configurable retention windows tied to call recordings specifically. Missing for 10: explicit per-call recording enable/disable controls, documented retention period configuration for stored call audio/transcripts, and consent/disclosure feature support.

   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

   proof ↗⚑ flag

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

   weight 2 · round to Deepgram Voice Agent
   Bolna~partialclaimed3/10

   Bolna documents Indian data residency and self-hosting via Docker/Kubernetes for private enterprise deployments, but there is no mention of HIPAA/BAA support or SOC 2 certification anywhere in the evidence pack. missing for 10: HIPAA/BAA attestation, SOC 2 report or certification, broader multi-region data-residency options beyond India.

   • [claimed-docs] “Indian data residency is available for deployments where data must remain in India.”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed4/10

   Evidence shows EU data-residency endpoint and an opt-out from data retention/training, indicating some compliance/trust infrastructure, but there is no mention of HIPAA/BAA support or SOC 2 certification anywhere in the pack. missing for 10: HIPAA/BAA documentation, SOC 2 attestation evidence, broader regional residency options beyond EU.

   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

   proof ↗⚑ flag

Scale

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

   weight 2 · round to Bolna
   Bolna~partialclaimed3/10

   Bolna's marketing page claims it can 'power thousands of inbound and outbound calls every minute' and docs mention self-hosting via Docker/Kubernetes for 'scalable enterprise deployments,' but there are no documented concurrency limits, rate-limit tables, or self-serve capacity-scaling mechanisms (e.g., no API rate-limit docs, no autoscaling guide, no numeric SLA). missing for 10: documented numeric concurrency/rate limits, self-serve scale-up process, autoscaling architecture details, independent verification of claimed call volume.

   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence pack item mentions concurrency limits, rate limits, per-account call caps, scaling guidance, or capacity request processes for the Voice Agent API; the docs cover architecture, features, and integrations but nothing about scale/concurrency documentation.

   ⚑ flag

Self host

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

   weight 3 · round to Bolna
   Bolna✓fullclaimed8/10

   Bolna is explicitly an open-source framework on GitHub, and docs include dedicated enterprise instructions for self-hosting on Docker or Kubernetes for private/enterprise deployments. Missing for 10: independent hands-on reports confirming successful self-host deployment and more detail on infrastructure requirements/limitations of the self-hosted version vs SaaS.

   • [github] “Bolna is the end-to-end open source production ready framework for quickly building LLM based voice driven conversational applications.”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram Voice Agent is a hosted, cloud-only API accessed via WebSocket; nothing in the evidence indicates open-source runtime code that can be self-hosted on customer infrastructure. All references point to Deepgram-hosted endpoints (api.deepgram.com, api.eu.deepgram.com) and a CLI/SDK for calling the cloud service, not deploying the runtime itself.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”

   proof ↗⚑ flag

Latency

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

   weight 3 · round drawn
   Bolna—none0/10

   No evidence pack item provides documented latency numbers, benchmarks, or tuning guidance for end-to-end voice latency; only vague marketing claims like 'build in under 5 minutes' or 'power thousands of calls' appear, with no actual latency figures or turn-taking tuning documentation.

   • [claimed-docs] “Build and deploy in under 5 minutes”
   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers architecture, features (barge-in, telephony, function calling, multi-agent), and CLI/SDK tooling, but contains no documented latency numbers (e.g., ms end-to-end) or tuning guidance for reducing turn-taking latency. missing for 10: quantified latency benchmarks, latency tuning/configuration guidance, any performance dashboard or whitepaper on speed claims.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”

   proof ↗⚑ 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 Deepgram Voice Agent
   Bolna—none0/10

   No evidence pack item mentions barge-in, interruption handling, speech-stop, or turn recovery mechanics; the docs cover extraction categories, summaries, providers, CLI, MCP, pricing, etc., but nothing about turn-taking or interruption behavior. missing for 10: any documentation of barge-in/interruption detection, mid-speech stop mechanics, context update on interruption, turn recovery logic.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Docs explicitly claim barge-in support where users can talk over the agent and it stops instantly, plus mid-call context tools like InjectAgentMessage for updating conversation state. However, evidence lacks detail on how turn recovery/context updating works technically after interruption, and there's no independent/hands-on corroboration of graceful recovery in practice. missing for 10: technical details on context-state recovery post-interruption, independent verification of barge-in reliability, edge-case handling (e.g., rapid interruptions, latency of stop).

   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
   • [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Bolna—none0/10

   No evidence pack item mentions noise suppression, background noise handling, or audio filtering settings for calls; the docs cover extraction categories, summaries, telephony, SDKs, and pricing but not audio quality/noise robustness features. Missing for 10: any mention of noise suppression/audio filtering configuration, VAD tuning for noisy environments, or documented handling of real-world call noise.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence pack item mentions noise suppression, background noise filtering, or audio denoising features for the Voice Agent; coverage focuses on barge-in, telephony, multi-agent orchestration, and LLM/TTS configuration instead.

   ⚑ 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 drawn
   Bolna—none0/10

   No evidence describes model-based end-of-turn/turn-taking detection distinct from VAD silence timeouts; evidence only covers mid-call model switching, extraction categories, and unrelated features. Missing for 10: any mention of endpointing model, semantic turn detection, or configurable end-of-turn logic beyond silence thresholds.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence only mentions barge-in (interrupting agent mid-speech) and generic prompting/architecture docs; there is no mention of model-based end-of-turn detection or endpointing that goes beyond VAD/silence timeouts to avoid cutting off slow speakers.

   ⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialprobed7/10

   Docs show the platform is API-first — agent creation, extraction categories, call summaries, workflows, and telephony are all described as configurable via the API, and a CLI and MCP server both wrap that same API, implying broad parity. However, there is no explicit documentation stating full UI/API feature parity, and probes found no discoverable OpenAPI/swagger spec (404s), leaving some doubt about completeness of coverage for every UI action. Missing for 10: explicit UI-API parity statement, published OpenAPI/swagger spec, independent confirmation that all UI actions have API equivalents.

   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”
   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bolna.ai/openapi.json, https://docs.bolna.ai/swagger.json, https://docs.bolna.ai/api/op…”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialprobed6/10

   Deepgram is fundamentally API-first — the Voice Agent is a WebSocket API with full configuration (prompting, function calling, multi-agent, telephony, reusable configs) exposed programmatically, and even the CLI/MCP server let AI-native users manage things from the terminal or via agentic tools rather than a GUI. However, evidence doesn't show a full-featured UI to compare against (e.g., a dashboard/console) nor confirm that every console feature (like A/B testing dashboards, analytics views) has a documented API equivalent. missing for 10: explicit mapping of console/UI-only features (analytics dashboards, A/B test result views) to API endpoints, and confirmation no UI-exclusive functionality exists.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
   • [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
   • [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
   • [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”

   proof ↗⚑ flag

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

   weight 3 · round to Bolna
   Bolna~partialclaimed3/10

   Bolna's API lets you fetch call transcripts (bolna-docs-14) and the platform can be self-hosted via Docker/Kubernetes (bolna-docs-9), with an open-source core framework (bolna-gh-1), which together provide some data portability, but there is no documented bulk 'export all data' feature or guarantee of open, standard export formats covering call recordings, agent configs, analytics, etc. Missing for 10: an explicit full-data export tool/endpoint, documented open format specification for exported data, and independent confirmation that a user can fully migrate away with all their data.

   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”
   • [github] “Bolna is the end-to-end open source production ready framework for quickly building LLM based voice driven conversational applications.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence describes any data export, account data portability, or open-format export/deletion workflow letting a user take their data and leave; docs cover retention opt-out and EU processing but not export tooling. missing for 10: data export mechanism, open-format export documentation, account closure/data portability guarantees.

   ⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialclaimed5/10

   The GitHub repo description explicitly calls Bolna 'the end-to-end open source production ready framework,' supporting that its source is publicly available under an open-license framing, but no specific license (e.g., MIT/Apache) is named or verified, and no independent corroboration exists. Missing for 10: explicit license identification (e.g., LICENSE file contents), confirmation the entire product (not just the framework) is open-sourced, and independent verification.

   • [github] “Bolna is the end-to-end open source production ready framework for quickly building LLM based voice driven conversational applications.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram Voice Agent is a proprietary cloud API/SDK product; no evidence anywhere in the pack points to an open-source license or public source repository for the core Voice Agent service. Only API docs, CLI, and SDK usage are documented, none of which imply open-licensed source availability.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Bolna
   Bolna✓fullclaimed8/10

   Bolna is explicitly open source (GitHub repo) and documentation provides dedicated on-premise instructions for self-hosting via Docker or Kubernetes for enterprise deployments, directly satisfying the self-host story. Missing for 10: independent/hands-on confirmation of a successful self-hosted deployment and more detail on feature parity between self-hosted and cloud versions.

   • [github] “Bolna is the end-to-end open source production ready framework for quickly building LLM based voice driven conversational applications.”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram Voice Agent is a cloud API/SaaS product; all evidence points to hosted WebSocket endpoints, EU regional endpoints, and cloud-based configuration — there is no mention of a self-hostable or on-premises deployment package for the core voice agent model/inference stack. missing for 10: any self-hosting/on-prem deployment option, downloadable model weights or container, docs on running the core service outside Deepgram's cloud.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

   proof ↗⚑ flag

Pricing

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

   weight 2 · round to Bolna
   Bolna~partialclaimed4/10

   There is a dedicated call-pricing doc page and mentions that BYOK/connected providers aren't charged (bolna-docs-19, bolna-docs-10), indicating some usage-based pricing structure exists, but no evidence pack item actually quotes a per-minute rate, tiered pricing table, or a cost calculator a founder could use to estimate cost per call. Missing for 10: explicit per-minute/usage rate figures, a pricing calculator or worked cost example, and independent confirmation that published rates are accurate.

   • [claimed-docs] “When you bring your own keys (BYOK), Bolna does not charge for those components.”
   • [claimed-docs] “We don't charge for any usage for providers that you have connected to Bolna.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence pack item mentions pricing, per-minute rates, usage-based cost, or any pricing page/calculator for the Voice Agent product; all citations focus on architecture, features, and developer tools.

   ⚑ flag

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

   weight 2 · round drawn
   Bolna~partialclaimed6/10

   Docs explicitly mention Indian data residency as an available option, and self-hosting via Docker/Kubernetes lets enterprises control where data lives entirely. However, there's no broader multi-region selection (e.g., EU, US) documented beyond India, and no detail on how residency is configured or enforced. Missing for 10: documented multi-region choice beyond India, configuration/UI for selecting region, and independent confirmation of residency enforcement.

   • [claimed-docs] “Indian data residency is available for deployments where data must remain in India.”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Deepgram documents an EU-specific endpoint (api.eu.deepgram.com) for customers requiring EU data processing, and a per-request opt-out for model improvement data retention, showing some regional/data-handling control. However, this is limited to EU vs. default (US) with no evidence of broader region selection (e.g., APAC, other jurisdictions) or a general residency configuration option across the platform. Missing for 10: documented list of all available regions, self-serve region selection in dashboard/API config, and independent confirmation of residency guarantees beyond docs.

   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”

   proof ↗⚑ flag

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

   weight 3 · round to Deepgram Voice Agent
   Bolna—none0/10

   No evidence pack item addresses a training-data opt-out or policy on AI model training use; security docs cover data residency and IP whitelisting only, not training-data usage controls. missing for 10: any explicit statement on AI training data usage/opt-out policy, data processing agreement terms, or contractual guarantee against training use.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Deepgram documents a per-request opt-out (mip_opt_out=true) from its Model Improvement Program, with opted-out requests not retained, directly addressing training-data use. However, the evidence only shows a per-request flag rather than an account-wide default-off setting, and there's no independent verification that opt-out requests are truly excluded from training. Missing for 10: account/org-level opt-out default, third-party audit or independent confirmation of non-training use, and clarity on default behavior when the flag is omitted.

   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   No evidence of data retention controls, deletion APIs, or user-facing privacy/data-lifecycle settings; only tangential mentions of security (IP whitelisting, India data residency) which do not address retention/deletion. Self-hosting option exists but that's deployment control, not a retention/deletion feature.

   • [claimed-docs] “Indian data residency is available for deployments where data must remain in India.”
   • [claimed-docs] “Whitelist all three IPs on your server or firewall”
   • [claimed-docs] “Learn how to self-host Bolna Voice AI on your own servers using Docker or Kubernetes for secure, private, and scalable enterprise deployment…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed5/10

   Deepgram documents a per-request opt-out (mip_opt_out=true) that prevents retention, and references data-privacy compliance including an EU-specific endpoint, giving users some retention control. However, there is no documented self-service deletion mechanism for already-retained data, no stated retention periods, and no dashboard/API for managing or purging stored voice data. Missing for 10: explicit data deletion API/console, documented retention duration policy, and confirmation of deletion for non-opted-out data.

   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
   • [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

   proof ↗⚑ flag

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

   weight 2 · round to Deepgram Voice Agent
   Bolna—none0/10

   No evidence pack item addresses telemetry, analytics opt-out, or usage-tracking controls for the platform itself; existing security/data-residency docs don't cover this. Missing for 10: any documentation of telemetry collection or an opt-out/disable mechanism, privacy policy statement on usage tracking, self-host confirmation of no phone-home behavior.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed4/10

   Deepgram documents an opt-out mechanism (mip_opt_out=true) for model improvement/data retention on a per-request basis, which is a form of telemetry/usage-data opt-out, but this is narrowly scoped to training data retention rather than general telemetry/usage tracking (e.g., analytics, product usage metrics). Missing for 10: documentation of a broader telemetry/usage-tracking opt-out setting, confirmation this covers all usage data beyond model-improvement retention, and independent verification that opting out has no side effects.

   • [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”

   proof ↗⚑ flag

Call control

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

   weight 2 · round drawn
   Bolna—none0/10

   No evidence in the pack describes call transfer functionality (warm or blind) to a human agent, or context handoff during a live call; the closest items relate to model switching, summaries, and telephony/SIP trunking but not transfer escalation.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence covers telephony connectivity, function calling, multi-agent handoff between AI agents, and mid-call message injection, but nothing documents a warm/blind transfer to a human agent (e.g., SIP REFER, call transfer function, or context handoff to a live operator).

   ⚑ flag

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

   weight 1 · round drawn
   Bolna—none0/10

   No evidence in the pack mentions DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving; only unrelated telephony features like SIP trunking, call summaries, and workflows are documented.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence covers telephony connectivity, function calling, barge-in, and multi-agent orchestration, but nothing documents DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving capabilities.

   ⚑ flag

Campaigns

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

   weight 2 · round to Bolna
   Bolna~partialprobed5/10

   The CLI explicitly manages 'batches' of calls alongside agents/phone numbers, and marketing copy claims support for 'thousands of inbound and outbound calls every minute,' plus a workflows API for multi-step outreach with waits/retries — together implying batch campaign and throughput capability. However, there's no explicit documentation of scheduling controls (e.g., time windows, campaign start/stop) or throughput/rate-limiting configuration for outbound campaigns specifically. Missing for 10: explicit scheduling/calendar controls for campaigns, documented throughput/rate-limit configuration knobs, and any hands-on/independent evidence of batch campaign execution.

   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”
   • [claimed-docs] “Build multi-step outreach sequences that combine voice agent calls, WhatsApp messages, API calls, waits and retries, driven entirely through…”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram's docs confirm outbound telephony connectivity (docs-5, docs-18) and per-call features like barge-in and prompting, but there is no mention of campaign-level batch dialing, call scheduling, or throughput/rate controls for outbound campaigns — this is a real-time conversation API, not a dialer/campaign manager.

   • [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”

   proof ↗⚑ flag

Numbers

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

   weight 3 · round drawn
   Bolna~partialprobed6/10

   Bolna's API/CLI clearly support placing outbound calls and receiving inbound calls (quickstart shows placing a call and fetching transcript via API, CLI manages calls and phone numbers, marketing claims thousands of inbound/outbound calls per minute), and BYOT lets you attach SIP trunks/numbers. However there's no explicit documented endpoint for provisioning/purchasing new phone numbers through the API itself — only CLI mention of managing 'phone numbers' and bringing your own trunk. Missing for 10: explicit phone-number provisioning API endpoint/documentation, independent confirmation of end-to-end inbound+outbound flow.

   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “The Bolna CLI (bolna) is a single Go binary that lets you manage agents, calls, phone numbers, and batches directly from your terminal”
   • [claimed-docs] “Bring Your Own Telephony (BYOT) lets you connect any standards-compliant SIP trunk to the Bolna platform.”
   • [claimed-docs] “Power thousands of inbound and outbound calls every minute with human-like, multilingual intelligence”
   • [probe] “official CLI documented at https://www.bolna.ai/docs/cli/introduction”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Docs confirm Deepgram Voice Agent supports inbound/outbound calls and telephony integration (e.g., via Twilio bridging audio to a single WebSocket), but there is no evidence Deepgram itself provisions or manages phone numbers—developers must bring their own Twilio account/number and build a bridging server. Missing for 10: native phone-number provisioning API, first-party telephony number management, and evidence of outbound call initiation directly through Deepgram's API without a third-party carrier.

   • [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”

   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 Bolna
   Bolna✓fullclaimed8/10

   Bolna explicitly documents 'Bring Your Own Telephony (BYOT)' allowing any standards-compliant SIP trunk to connect to the platform, plus IP whitelisting requirements for the connection, directly addressing carrier/PBX independence from bundled telephony. missing for 10: explicit step-by-step Twilio/Telnyx number import walkthrough and independent/hands-on verification of SIP trunk setup working end-to-end.

   • [claimed-docs] “Bring Your Own Telephony (BYOT) lets you connect any standards-compliant SIP trunk to the Bolna platform.”
   • [claimed-docs] “Whitelist all three IPs on your server or firewall”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence only documents a generic WebSocket bridge pattern for Twilio (docs-18, docs-8) and a general 'Telephony' feature bullet (docs-5), but there is no mention of SIP trunking, PBX connectivity, or Telnyx number import — the specific mechanisms a platform engineer would need to bring their own carrier.

   • [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
   • [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”

   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 Bolna
   Bolna~partialclaimed3/10

   Bolna offers post-call analysis primitives — configurable extraction-categories (bolna-docs-1) and toggleable call summaries (bolna-docs-2) — which could be used to build custom scoring/flagging, but there's no documented automated QA/quality-scoring, failure-flagging, or resolution-analysis feature out of the box. Missing for 10: dedicated call-scoring/QA dashboard, automatic failure detection, resolution-analysis reporting, and independent evidence these extraction fields are used for review purposes.

   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers Deepgram Voice Agent's real-time conversation infrastructure (STT/TTS, function calling, telephony, prompting, A/B testing of voices/prompts) but contains no mention of post-call AI review, automated quality scoring, failure flagging, or resolution analysis of completed calls.

   ⚑ flag

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

   weight 2 · round drawn
   Bolna—none0/10

   Evidence only shows API-level features like call summaries (call_summary_enabled) and extraction categories, but there is no mention of a dashboard UI presenting success rates, durrations, outcomes, or sentiment analytics — missing for 10: any dashboard/UI screenshot or docs describing aggregated call analytics views.

   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Deepgram is a developer API/infrastructure product; evidence shows mentions of A/B testing metrics (conversion, CSAT, containment rate) as data points but no evidence of an actual built-in dashboard for call analytics, success rates, durations, sentiment, or outcomes that founders can view without building their own.

   • [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”

   proof ↗⚑ flag

Monitoring

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

   weight 1 · round drawn
   Bolna—none0/10

   Evidence covers call summaries, extraction categories, transcripts, CLI, MCP, and SIP/telephony features, but nothing describes live-call monitoring dashboards, real-time observability, or alerting on agent misbehavior or error-rate spikes. No mention of metrics, alert thresholds, webhooks for anomaly detection, or a monitoring console for platform engineers. Missing for 10: real-time monitoring dashboard, alerting/notification system for errors or misbehavior, error-rate tracking, on-call/integration with observability tools.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence of live monitoring dashboards, error-rate alerting, or observability/analytics tooling for production calls; docs cover agent architecture, function calling, telephony, and configuration but nothing about monitoring or alerting on agent misbehavior.

   ⚑ flag

Testing

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

   weight 2 · round drawn
   Bolna—none0/10

   No evidence of any simulated conversation testing, evals, or pre-production testing framework for agents; the evidence pack only covers deployment, telephony, providers, pricing, and SDKs. Missing for 10: any mention of test/eval tooling, simulated call testing, or conversation quality scoring before live calls.

   ⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence covers live-call features (function calling, prompting, telephony, A/B testing of live configs) but nothing describes a simulated-conversation or eval framework for pre-production testing of agents before real phone calls. Missing for 10: any documentation of a test/sandbox mode, conversation simulation tool, or eval harness for agents.

   • [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
   • [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”

   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 Bolna
   Bolna~partialclaimed6/10

   Bolna provides extraction-categories API to attach custom entity/data extraction to agents and a call_summary_enabled toggle for summaries, plus transcript fetch via API — covering entities, summaries, and outcomes. However, there's no explicit documentation of a unified structured 'disposition' field, no clear webhook delivery mechanism for post-call structured payloads (only API fetch is shown), and no example of the combined extraction+summary+disposition JSON schema. missing for 10: webhook-based delivery of extraction results, documented disposition/outcome field, end-to-end example combining all three data types in one payload.

   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”
   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers live function calling during a call and various agent configuration/telephony features, but there is no mention of post-call structured data extraction (summaries, entities, dispositions) or webhook delivery of such analytics after a call ends.

   ⚑ 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
   Bolna—none0/10

   Evidence only shows Bolna exposing its OWN MCP server so external clients (Claude, Cursor, Windsurf) can manage a Bolna account (bolna-docs-17, bolna-probe-3) — the reverse direction of the story, which asks whether a Bolna voice agent can consume external MCP servers as tool sources mid-call. No documentation shows Bolna agents acting as an MCP client or importing toolsets from third-party MCP servers during a call. missing for 10: any evidence of Bolna voice agents connecting to external MCP servers as tool sources, mid-call toolset loading via MCP.

   • [claimed-docs] “Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.”
   • [probe] “official MCP server documented at https://www.bolna.ai/docs/build-with-ai/mcp”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence confirms mid-call function calling exists for the Voice Agent (deepgram-docs-2) but only documents an MCP *server* built into the CLI that lets coding tools access Deepgram APIs (deepgram-docs-13, deepgram-probe-4) — this is the reverse direction, not the Voice Agent acting as an MCP client to pull in external toolsets mid-call. No evidence shows the Voice Agent itself can connect to MCP servers as a tool source.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
   • [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

   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 Deepgram Voice Agent
   Bolna—none0/10

   The evidence pack covers extraction categories, call summaries, workflows, and custom LLM providers, but nothing describes an agent invoking external APIs or custom functions mid-call and voicing the result seamlessly. Missing for 10: documentation of a function-calling/tool-use API, examples of mid-call API invocation, and any mention of latency-masking/filler techniques to avoid dead air.

   ⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Docs confirm function calling is a supported feature for performing tasks mid-conversation (deepgram-docs-2), and the agent architecture is a single low-latency WebSocket for audio in/out (deepgram-docs-1) with barge-in and inject-message features (deepgram-docs-8, deepgram-docs-11) suggesting attention to latency/dead-air. However there's no explicit documentation or example describing how function-call latency is masked (e.g., filler speech, streaming partial results) while awaiting an API response. Missing for 10: concrete guidance/examples on avoiding dead air during function execution, sample code showing async function calls with the agent speaking a holding phrase, and independent/hands-on verification of smooth latency handling.

   • [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
   • [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”

   proof ↗⚑ flag

Recording

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

   weight 2 · round to Bolna
   Bolna~partialclaimed5/10

   Docs confirm fetching call transcripts via API (quickstart mentions 'fetch the transcript') and call summaries can be toggled, but there is no explicit documentation of a dedicated recordings-retrieval endpoint or bulk/programmatic export for all calls. missing for 10: explicit call-recording download/API endpoint, confirmation that recordings are retained and accessible for every call, and independent verification of transcript completeness/format.

   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”
   • [claimed-docs] “Call summaries are an agent-level toggle: call_summary_enabled (boolean, off by default) on the agent create and update APIs”
   • [claimed-docs] “POST /agent/{agent_id}/extraction-categories — create a category (name + model) and attach it to an agent”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   The evidence pack covers Voice Agent architecture, function calling, telephony bridging, LLM providers, and data privacy opt-outs, but nowhere describes an API or mechanism to retrieve full call recordings or persisted transcripts after a call ends. No endpoint, storage feature, or retrieval workflow is documented for this specific capability.

   ⚑ flag

Transcription

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

   weight 2 · round to Deepgram Voice Agent
   Bolna~partialclaimed5/10

   Docs confirm STT provider choice (Deepgram, Azure, ElevenLabs) and full LLM control including custom OpenAI-compatible endpoints, plus transcript retrieval via API, giving developers real provider/model flexibility. However there is no evidence of key-term/vocabulary boosting or accuracy tuning controls, nor any real-time transcription accuracy benchmarks. Missing for 10: key-term/keyword-boost configuration, accuracy/latency benchmarks for real-time transcription, and independent validation of transcription quality.

   • [claimed-docs] “Bolna supports Deepgram, Azure, ElevenLabs, and more.”
   • [claimed-docs] “For custom llm simply keep provider in the llm_agent key as custom and add a openai compatible base_url”
   • [claimed-docs] “Make your first Voice AI call with the Bolna API — verify your key, get an agent, place a call, and fetch the transcript in about five minut…”

   proof ↗⚑ flag

   Deepgram Voice Agent~partialclaimed6/10

   Docs confirm real-time transcription via the unified WebSocket API, selectable LLM providers (docs-9), and multilingual STT/TTS model choices (docs-10), giving developers meaningful control over STT and LLM models. However, there is no evidence of 'key terms' or keyword-boosting controls specific to the Voice Agent's transcription pipeline. Missing for 10: explicit key-term/keyword-boost configuration support, independent benchmarking of transcription accuracy.

   • [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
   • [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”
   • [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”

   proof ↗⚑ flag

Voices

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

   weight 2 · round drawn
   Bolna—none0/10

   Evidence shows Bolna lets founders choose among third-party voices/accents/styles (bolna-docs-8) and integrates providers like ElevenLabs (bolna-docs-6), but there is no mention of a voice-cloning feature for a custom brand voice, nor any documented consent process for cloning. Missing for 10: voice cloning capability, consent/verification workflow documentation, any policy on brand voice usage.

   • [claimed-docs] “You can choose different voices, accents, and speaking styles to match your brand.”
   • [claimed-docs] “Bolna supports Deepgram, Azure, ElevenLabs, and more.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   No evidence of a voice cloning feature or consent process; docs cover STT/TTS model selection, multilingual voices, and agent configuration but never mention custom voice cloning or consent workflows.

   ⚑ flag

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

   weight 2 · round to Bolna
   Bolna~partialclaimed6/10

   Docs confirm multiple TTS providers (Deepgram, Azure, ElevenLabs, and more) plus voice/accent/style customization, satisfying the 'plug in providers' part of the story. However, there's no evidence of a broad pre-built voice library or catalog to browse/select from, only provider integration. Missing for 10: evidence of a large built-in voice library/catalog, provider-count breadth beyond three named examples, independent/hands-on confirmation of voice quality or selection UX.

   • [claimed-docs] “Bolna supports Deepgram, Azure, ElevenLabs, and more.”
   • [claimed-docs] “You can choose different voices, accents, and speaking styles to match your brand.”

   proof ↗⚑ flag

   Deepgram Voice Agent—none0/10

   Evidence confirms TTS model selection exists (docs-10 references choosing a TTS model) but there is no documentation of a broad voice library or of plugging in multiple third-party TTS providers analogous to the multi-LLM-provider list (docs-9). Missing for 10: evidence of voice catalog/library breadth, evidence of multiple supported TTS providers/vendors, and any provider-switching mechanism for voice output.

   • [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”

   proof ↗⚑ flag