Bland vs Bolna

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 drawn
   Bland✓fullprobed8/10

   Bland's docs show all three provisioning steps available programmatically: pathway/agent creation via API (bland-docs-1, bland-docs-18), phone number acquisition/porting/Twilio and SIP attachment (bland-docs-3, bland-docs-16, bland-docs-17), and call placement via API or batch calls (bland-docs-6, bland-docs-23). Both the CLI ('make calls, build and test pathways, configure phone numbers' — bland-docs-12) and the MCP server ('place and inspect calls, build and validate pathways, manage agents' — bland-docs-11/20/27) explicitly cover the full create-agent/attach-number/place-call lifecycle without the dashboard, and runtime probes confirm both the CLI and hosted MCP endpoint are live and functional (bland-probe-rt-1, bland-probe-rt-2). Missing for 10: a single consolidated end-to-end tutorial/example walking through create→attach→call in one flow, and independent (non-vendor) confirmation of the full pipeline working end-to-end.

   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”
   • [claimed-docs] “Users can connect their own Twilio account to Bland, easily bring over your existing phone numbers to use within the platform.”
   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [claimed-docs] “Number porting to bring existing numbers to Bland”
   • [claimed-docs] “Bland supports inbound and outbound SIP. Point calls from your carrier or PBX at Bland to be answered by an agent, or have Bland place calls…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”

   proof ↗⚑ flag

   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

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

   weight 1 · round to Bland
   Bland~partialclaimed4/10

   Bland's MCP server lets external AI coding agents 'build and validate pathways ... through natural language' (bland-docs-11/20/27), and the testbed/evals tools support iterating on and grading prompts, which loosely supports AI-assisted authoring. However there is no evidence of a built-in, first-party generative feature where Bland's own platform AI drafts a full pathway/flow/test-cases from a plain-language description inside the product itself — the closest capability requires an external AI agent connecting via MCP. Missing for 10: a native 'describe your agent, we generate the pathway/prompts/tests' feature, in-product prompt-improvement AI, and independent/hands-on confirmation of AI-generated flows.

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”

   proof ↗⚑ flag

   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

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 drawn
   Bland✓fullprobed8/10

   Docs cover the whole first-call workflow: creating a pathway/prompt (bland-docs-18, bland-docs-26, bland-docs-30), voice cloning/selection (bland-docs-10), phone number setup via own Twilio or new inbound numbers (bland-docs-3, bland-docs-24), and dispatching outbound calls (bland-docs-23), plus a CLI and MCP server confirmed live at runtime (bland-probe-rt-1, bland-probe-rt-2) that let a developer configure and place calls quickly. Missing for 10: no independent hands-on account of a developer actually completing a first call within an hour, and one community comment notes cost concerns rather than time-to-first-call, so onboarding speed is only documented, not externally verified.

   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”
   • [claimed-docs] “A clone needs one clean sample of about ten seconds. Quality of the sample sets the ceiling on quality of the voice”
   • [claimed-docs] “Users can connect their own Twilio account to Bland, easily bring over your existing phone numbers to use within the platform.”
   • [claimed-docs] “Create inbound phone numbers for customer support, etc.”
   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”
   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bolna
   Bland—none0/10

   The evidence pack contains no mention of multi-language support, language detection, or mid-call language switching anywhere in Bland's docs; only pathways, TTS voice cloning, and infrastructure features are documented. Missing for 10: any documentation of multilingual conversation support, automatic language detection, or dynamic language switching mid-call.

   ⚑ flag

   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

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

   weight 2 · round to Bland
   Bland✓fullclaimed7/10

   Bland's 'Conversational Pathways' feature is explicitly a node-based flow builder where founders give instructions at specific conversation points, test individual node interactions in a pathway editor/testbed, and publish drafts separately from production—matching branching/states/handoffs without code (bland-docs-18, 26, 30, 28, 19). Missing for 10: explicit confirmation of a drag-and-drop visual canvas UI (docs describe 'nodes' and 'pathway editor' but no screenshot/UI walkthrough) and independent hands-on corroboration beyond vendor docs.

   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”
   • [claimed-docs] “When you edit a pathway, you are working on a draft. Live calls are not affected. They keep using the published production version.”
   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”

   proof ↗⚑ flag

   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

Personalization

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

   weight 2 · round to Bland
   Bland~partialclaimed5/10

   Evidence shows personalization mechanisms exist—Memory for per-caller context (bland-docs-9), batch calls that likely carry per-recipient data (bland-docs-6), and pathway webhooks/API integrations that could fetch live data (bland-docs-4, bland-docs-30)—but there is no explicit documentation of a 'dynamic variables' injection API or call-time variable substitution mechanism. missing for 10: explicit dynamic-variable/request_data injection documentation, examples of per-call variable interpolation into prompts, independent confirmation of personalization working in practice.

   • [claimed-docs] “Memory lets Bland agents remember people across conversations, including calls, SMS, and other channels, so each interaction feels continuou…”
   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”

   proof ↗⚑ flag

   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

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
   Bland—none0/10

   Bland is a voice AI/phone agent platform; evidence covers pathways, memory, tools, MCP, CLI, etc., but nowhere mentions a document knowledge base or RAG capability for grounding agent responses in uploaded content. Since a voice/conversational agent platform could plausibly ship this (many competitors do), absence of evidence makes this 'none' rather than 'na'.

   ⚑ flag

   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

Agent access

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

   weight 2 · round to Bolna
   Bland✓fullprobed8/10

   Bland has a confirmed live llms.txt at docs.bland.ai/llms.txt (HTTP 200) providing agent-oriented documentation, plus an official MCP server and CLI explicitly designed for AI coding agents to interact with the platform via natural language. missing for 10: independent third-party confirmation that agents actually consume llms.txt successfully in practice, and broader agent-oriented docs beyond the single llms.txt file.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.bland.ai/llms.txt # Bland Documentation Bland is an enterprise voice AI platform for high-volume, …”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bland
   Bland✓fullprobed8/10

   Bland offers a full programmatic/REST API for pathways, calls, batch calls, webhooks, and evals, plus an official CLI (verified runtime installable keylessly via npx) for terminal-based automation, enabling headless/CI usage. missing for 10: no explicit CI/CD pipeline example (e.g., GitHub Actions) or independent case study confirming CI usage beyond docs and CLI probe.

   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”
   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Bland—none0/10

   Bland's evidence only documents it exposing an outbound MCP server so that external AI coding agents can call Bland's own tools (docs-11, docs-20, docs-27, probe-rt-2) — the reverse direction of this story. There is no evidence that Bland itself can consume/plug in third-party MCP servers as a client; its tool integration story is limited to custom HTTP API endpoints and webhooks (bland-docs-4, bland-docs-25).

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Bland✓fullprobed8/10

   Bland ships an official MCP server (docs and runtime probe confirm it's live and gated by API key) that lets AI coding agents place/inspect calls, build pathways, manage agents, query analytics, run evals, and search docs — directly fulfilling the story. Missing for 10: independent third-party hands-on review of the MCP server beyond vendor docs/probe.

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”

   proof ↗⚑ flag

   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

5. ai-native userUse an official CLI

   weight 2 · round to Bland
   Bland✓fullprobed9/10

   Bland ships an official CLI (bland-cli) documented to manage the entire account from the terminal, and a runtime probe confirms it installs and runs via npx keylessly. missing for 10: independent third-party review/usage reports of the CLI beyond the official docs and one probe run.

   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Bland
   Bland✓fullprobed9/10

   Bland documents a comprehensive public API (pathways, calls, tools, webhooks, evals, batch calls) plus SDKs, CLI, and an official MCP server, and runtime probes confirm the CLI installs and the hosted MCP endpoint is live and gated as documented, showing agentic programmatic control. Missing for 10: a formally published OpenAPI/Swagger spec (probe found 404s at standard OpenAPI paths), so machine-readable spec discoverability is unconfirmed.

   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”
   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Bland—none0/10

   Evidence shows generic API-key auth and JWT-based webhook verification (bland-docs-15), but nothing about issuing scoped or least-privilege credentials specific to an agent's permissions (e.g., role-based API keys, scoped tokens limiting call/pathway/account access). Missing for 10: documentation of scoped API key creation, permission levels, or per-agent credential restriction.

   • [claimed-docs] “JWT signatures eliminate these risks through asymmetric cryptography - you verify requests using our public JWKS endpoint without storing an…”

   proof ↗⚑ flag

   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

8. ai-native userBuild against official SDKs

   weight 2 · round to Bland
   Bland~partialprobed6/10

   Bland documents a Web Agent SDK for embedding voice agents (React/Vanilla JS/Node), a CLI, and a REST API used throughout tutorials, giving AI-native developers concrete building blocks; runtime probes confirm the CLI installs and runs. However, no dedicated 'official SDK' page for server-side languages (Python/Node backend SDK) is evidenced, and openapi/swagger spec endpoints all 404, suggesting the API reference isn't machine-consumable in a standard SDK-generation format. Missing for 10: a clearly documented multi-language backend SDK (Python/Node) beyond the browser widget SDK, and a working OpenAPI spec for auto-generating clients.

   • [claimed-docs] “Embed a Bland voice agent into any web application (React, Vanilla JS, or Node). The SDK handles secure authentication between your server a…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”
   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”

   proof ↗⚑ flag

   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

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to Bland
   Bland~partialclaimed6/10

   Bland documents post-call webhooks (automatic HTTP notifications sent after a call completes) and pathway-level webhook execution at specific conversation points, showing genuine event-driven webhook support tied to call lifecycle. However, evidence only covers call-related events (completion, in-call triggers) — missing for 10: a general-purpose event subscription/webhook management API covering other account events (e.g., evals, batch campaign status, pathway publishes), and any independent confirmation of webhook reliability/configuration options.

   • [claimed-docs] “Post-call webhooks are HTTP notifications that Bland AI automatically sends to your server after a phone call completes.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”

   proof ↗⚑ flag

   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

Agentic features

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

   weight 2 · round to Bolna
   Bland~partialclaimed4/10

   Bland offers LLM-judge Evals to grade call quality and an MCP integration that can 'query analytics' on your account data, which are AI-generated evaluative outputs derived from your call data, but there's no dedicated insights/suggestions dashboard or proactive recommendation feature described. Missing for 10: a native analytics/insights UI, evidence of proactive suggestions surfaced to users, and independent confirmation of these AI-generated insights in practice.

   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “Memory lets Bland agents remember people across conversations, including calls, SMS, and other channels, so each interaction feels continuou…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Bland~partialclaimed6/10

   Bland supports batch calls, webhooks, pathways, and scheduled/triggered call campaigns that run without manual intervention, which constitute a form of autonomous background automation for voice workflows. However, this is scoped to phone-call automation only, not general-purpose background task/agent scheduling. missing for 10: evidence of a generic scheduler/cron-like trigger system, independent hands-on validation of unattended background runs, and confirmation of failure handling/monitoring for long-running autonomous automations.

   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Post-call webhooks are HTTP notifications that Bland AI automatically sends to your server after a phone call completes.”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”
   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Bland
   Bland✓fullclaimed8/10

   Bland's core product is a built-in AI voice agent that users delegate tasks to (placing/answering calls, executing pathways, calling APIs, remembering context) rather than a separate feature bolted on — e.g., 'Dispatch AI phone calls to call customers, leads, and to streamline operations' and pathway/tool/memory docs show rich task delegation to the built-in agent. Missing for 10: independent/hands-on evidence of real-world task delegation outcomes beyond vendor docs.

   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”
   • [claimed-docs] “Memory lets Bland agents remember people across conversations, including calls, SMS, and other channels, so each interaction feels continuou…”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bland
   Bland✓fullprobed8/10

   Bland offers an official MCP server that lets AI agents operate the entire account (calls, pathways, agents, analytics, evals) via natural language, plus an official CLI, both confirmed live via runtime probes. missing for 10: independent/hands-on third-party review of the MCP/CLI natural-language experience beyond vendor docs and probes.

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”

   proof ↗⚑ flag

   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

Api quality

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

   weight 2 · round drawn
   Bland—none0/10

   Docs reference an API reference for pathways but no evidence of an interactive playground with runnable examples; a probe for OpenAPI/Swagger specs at standard paths returned 404s, suggesting no such interactive reference exists.

   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Bland—none0/10

   A direct probe found no OpenAPI/Swagger spec at any expected location (all 404s), and no evidence pack item shows a downloadable machine-readable API spec despite extensive API documentation.

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

   proof ↗⚑ flag

   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

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

   weight 1 · round to Bland
   Bland~partialclaimed6/10

   Bland provides draft/staging pathway editing where live production calls are unaffected, plus a testbed for isolated node testing, canary deployments, and staged version adoption — all functioning as sandbox-like mechanisms distinct from production. However, there's no explicit 'sandbox environment' or dedicated test account/data isolation concept described, and testing still appears to involve real calls/production infrastructure rather than a fully isolated non-production environment. missing for 10: a dedicated sandbox/test-mode account distinct from production billing and phone infrastructure, explicit documentation of synthetic/non-production test data, and independent confirmation that testbed/draft testing never touches real production call data or costs.

   • [claimed-docs] “You can also promote a version to staging to test it before it goes live, or send an individual call against a specific”
   • [claimed-docs] “When you edit a pathway, you are working on a draft. Live calls are not affected. They keep using the published production version.”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [claimed-docs] “This is how you A/B test a new agent release against your live production version, with real calls, before committing to a full rollout.”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bland
   Bland~partialprobed4/10

   Bland documents infrastructure versioning concepts (staged/canary rollouts, choosing when to adopt a new release, draft vs. production pathway versions) but there is no evidence of a documented API versioning scheme (e.g., v1/v2 endpoints) or an explicit deprecation policy for its APIs, and the OpenAPI spec probe returned 404s. missing for 10: documented API version numbering/endpoints, an explicit deprecation/sunset policy for APIs, published OpenAPI spec, and independent confirmation of versioning practices.

   • [claimed-docs] “You choose when to adopt a new release. Your infrastructure stays on the version you've selected until you decide to move forward.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [claimed-docs] “You choose when to adopt a new release... Bland supports canary deployments — a way to run a new release on a separate set of containers alo…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bland
   Bland✓fullprobed7/10

   Batch calls let users upload a CSV of recipients to initiate high-volume call campaigns, directly enabling bulk operations across many items, and the CLI/MCP server extend programmatic/bulk management of pathways, agents, and calls. Missing for 10: independent/hands-on verification of batch call performance at scale, and documentation of bulk operations beyond calls (e.g., bulk pathway or number management).

   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Bland
   Bland✓fullclaimed7/10

   Bland's pathways let users define conditional logic that executes webhooks/API calls at specific conversation nodes, and post-call webhooks automatically fire HTTP notifications when a call-completion event occurs — this is a documented rules-trigger-action-on-event mechanism. missing for 10: independent/hands-on verification of the webhook triggering in production, and evidence of event types beyond call-based ones (e.g., generic account-level event automation).

   • [claimed-docs] “Post-call webhooks are HTTP notifications that Bland AI automatically sends to your server after a phone call completes.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”

   proof ↗⚑ flag

   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

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Bland—none0/10

   Bland's docs cover batch calls, pathways, webhooks, and API integrations, but nothing describes scheduling recurring jobs or workflows (e.g., cron-like triggers for calls or campaigns) — batch calls are one-off CSV uploads, not recurring schedules.

   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”

   proof ↗⚑ flag

   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

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

   weight 1 · round to Bland
   Bland~partialclaimed6/10

   Bland pathways support draft/staging/production versioning, A/B testing new releases against live production, and canary/staged rollout with adoption control (bland-docs-2, bland-docs-14, bland-docs-19, bland-docs-21, bland-docs-29, bland-docs-31), plus a testbed and evals for reviewing behavior before shipping (bland-docs-7, bland-docs-8, bland-docs-22, bland-docs-28). However, there is no explicit documentation of an automated 'rollback' mechanism to revert a live pathway/release to a prior version — only forward-adoption and canary controls are described. Missing for 10: explicit rollback/revert-to-previous-version capability, version history/diff view, and independent confirmation of rollback in practice.

   • [claimed-docs] “You can also promote a version to staging to test it before it goes live, or send an individual call against a specific”
   • [claimed-docs] “You choose when to adopt a new release. Your infrastructure stays on the version you've selected until you decide to move forward.”
   • [claimed-docs] “When you edit a pathway, you are working on a draft. Live calls are not affected. They keep using the published production version.”
   • [claimed-docs] “This is how you A/B test a new agent release against your live production version, with real calls, before committing to a full rollout.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [claimed-docs] “You choose when to adopt a new release... Bland supports canary deployments — a way to run a new release on a separate set of containers alo…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”

   proof ↗⚑ flag

   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

Compliance

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

   weight 2 · round drawn
   Bland—none0/10

   The evidence pack contains no mention of call recording consent/disclosure features, per-call recording toggles, or configurable data retention policies anywhere in Bland's docs; while this is a fair compliance axis for a voice AI platform, nothing in the pack substantiates it.

   ⚑ flag

   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

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

   weight 2 · round to Bolna
   Bland—none0/10

   The evidence pack contains no mention of HIPAA, BAA, SOC 2 certification, or data-residency options anywhere in the docs or probes; only a generic tagline calling Bland an 'enterprise' platform for 'regulated' workflows without specifics. Missing for 10: HIPAA/BAA documentation, SOC 2 report or certification evidence, data-residency/region controls, and any compliance attestations.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.bland.ai/llms.txt # Bland Documentation Bland is an enterprise voice AI platform for high-volume, …”

   proof ↗⚑ flag

   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

Scale

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

   weight 2 · round drawn
   Bland~partialclaimed3/10

   Docs mention batch calling for high-volume campaigns and enterprise infrastructure controls (canary releases, staged rollout), implying some capacity for scale, but there is no documented concurrency limit, rate ceiling, or auto-scaling guarantee, and no evidence that capacity increases don't require contacting sales/support. Missing for 10: explicit concurrent-call limits, auto-scaling documentation, and evidence that scaling doesn't require manual requests to Bland.

   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [claimed-docs] “You choose when to adopt a new release... Bland supports canary deployments — a way to run a new release on a separate set of containers alo…”

   proof ↗⚑ flag

   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

Self host

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

   weight 3 · round to Bolna
   Bland—none0/10

   Bland is presented throughout as a hosted enterprise SaaS platform (managed infrastructure, release adoption controls, canary deployments on Bland's own containers) with no mention of open-source code or a self-hostable runtime; a community post even shows a user asking for an open-source alternative because Bland itself isn't one.

   • [claimed-docs] “You choose when to adopt a new release. Your infrastructure stays on the version you've selected until you decide to move forward.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [community] “I want to experiment with building my own phone agent. Currently experimented with bland.ai but it gets expensive. Any open source alternati…”

   proof ↗⚑ flag

   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

Latency

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

   weight 3 · round drawn
   Bland—none0/10

   No evidence pack items mention latency numbers, benchmarks, or tuning guidance for end-to-end voice response time; documentation covers pathways, SIP, MCP, CLI, and enterprise features but nothing about speed/latency metrics or optimization guidance.

   ⚑ flag

   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

Turn taking

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

   weight 3 · round drawn
   Bland—none0/10

   The evidence pack covers pathways, webhooks, batch calls, evals, MCP/CLI integrations, and infrastructure features, but contains no mention of barge-in, interruption handling, stopping TTS mid-utterance, or turn recovery logic — a core voice-agent capability that would be a fair and expected axis for this product type. missing for 10: any documentation or claim about detecting user interruptions, halting agent speech, updating context after a barge-in, and resuming/recovering the conversational turn.

   ⚑ flag

   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

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

   weight 1 · round drawn
   Bland—none0/10

   No evidence pack item mentions noise suppression, audio filtering, or handling of noisy real-world call environments; documentation covers pathways, integrations, MCP, CLI, SIP, and enterprise release features but nothing about audio quality/noise handling.

   ⚑ flag

   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

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
   Bland—none0/10

   The evidence pack contains no mention of turn-taking, end-of-turn detection, VAD, or interruption handling mechanisms of any kind — nothing addresses how Bland decides when a speaker has finished talking. This is a fair and applicable axis for a voice AI platform, but no capability is documented; missing for 10: any mention of end-of-turn/turn-taking model, VAD configuration, or handling of slow speakers/pauses.

   ⚑ flag

   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

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

   weight 2 · round to Bland
   Bland✓fullprobed7/10

   Bland's docs show extensive programmatic control mirroring UI features: pathway creation/versioning, testbed, evals, batch calls, webhooks, SIP/phone number management, and a CLI/MCP server that explicitly lets users 'manage your entire Bland account from the terminal' and perform the same actions (calls, pathways, agents, analytics) as the UI. This breadth strongly supports API parity, though there's no explicit first-party statement guaranteeing 100% feature parity and no discoverable OpenAPI spec (all candidate URLs 404), so full parity isn't independently confirmed. Missing for 10: an explicit parity guarantee/documentation and a machine-readable OpenAPI spec, plus independent hands-on confirmation that every UI action has an API equivalent.

   • [claimed-docs] “See the Pathways API reference to create and manage pathways programmatically.”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [probe] “official CLI documented at https://docs.bland.ai/sdks/cli”
   • [probe] “PROBE runtime (recorded 2026-09-05): `npx -y bland-cli --version` printed `0.6.2` keylessly — the official npm CLI (bland-cli, with dev term…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Bolna
   Bland—none0/10

   No evidence of a data export feature or open-format export of account data (pathways, call logs, memories, etc.); the docs cover CLI, MCP, and SDK integrations but nothing about exporting user data for portability/exit.

   ⚑ flag

   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

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

   weight 2 · round to Bolna
   Bland—none0/10

   Bland is a closed, commercial SaaS voice AI platform; there is no evidence of any open-source license or public source code repository. A community comment explicitly asks for an open-source alternative, implying Bland itself is not open source. This is an applicable axis (a product could publish open-source components) but no evidence supports it.

   • [community] “I want to experiment with building my own phone agent. Currently experimented with bland.ai but it gets expensive. Any open source alternati…”

   proof ↗⚑ flag

   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

4. ai-native userSelf-host the core product

   weight 3 · round to Bolna
   Bland—none0/10

   Bland is documented as a hosted enterprise voice AI platform (call dispatch, pathways, SIP, MCP, CLI) with no mention of an on-prem/self-hosted deployment option; 'enterprise' release controls (docs-14, docs-29, docs-31) only govern version adoption timing on Bland's own infrastructure, not customer self-hosting. A community post explicitly looks for an open-source self-hostable alternative because Bland itself doesn't offer this.

   • [claimed-docs] “You choose when to adopt a new release. Your infrastructure stays on the version you've selected until you decide to move forward.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”
   • [claimed-docs] “You choose when to adopt a new release... Bland supports canary deployments — a way to run a new release on a separate set of containers alo…”
   • [community] “I want to experiment with building my own phone agent. Currently experimented with bland.ai but it gets expensive. Any open source alternati…”

   proof ↗⚑ flag

   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

Pricing

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

   weight 2 · round to Bolna
   Bland—none0/10

   No evidence pack item shows published per-minute or usage pricing, a pricing page, or any cost calculator; the only pricing-adjacent mention is a community complaint that Bland 'gets expensive' with no figures. Missing for 10: published price list, per-minute rate documentation, cost calculator or estimator tool.

   • [community] “I want to experiment with building my own phone agent. Currently experimented with bland.ai but it gets expensive. Any open source alternati…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bolna
   Bland—none0/10

   No evidence in the pack mentions data residency, regional hosting options, or geographic storage controls for Bland; enterprise/infra docs discuss release versioning and SIP/canary deployments but not region selection. Missing for 10: any mention of data residency options, region-specific hosting, or compliance-driven storage location controls.

   ⚑ flag

   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

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

   weight 3 · round drawn
   Bland—none0/10

   No evidence in the pack addresses data-training opt-out or AI-training privacy policies for Bland; nothing about training-data usage or opt-out controls is mentioned across any of the docs or probes.

   ⚑ flag

   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

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Bland—none0/10

   No evidence pack items address data retention policies, data deletion controls, or privacy/compliance settings for call recordings, transcripts, or memory data. This axis clearly applies to an enterprise voice AI platform handling call data, but nothing in the evidence documents retention periods, deletion APIs, or GDPR/CCPA-style data controls. Missing for 10: retention policy docs, data deletion API/endpoint, compliance certifications, memory/data purge mechanism.

   ⚑ flag

   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

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

   weight 2 · round drawn
   Bland—none0/10

   No evidence pack items mention telemetry, analytics opt-out, or usage-tracking controls for Bland's own platform; this is a fair question for an enterprise SaaS product but is simply unaddressed in the evidence.

   ⚑ flag

   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

Call control

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

   weight 2 · round drawn
   Bland—none0/10

   The evidence pack covers pathways, webhooks, SIP, MCP, CLI, and other Bland features, but contains no mention of call transfer (warm or blind) or handing off a live call to a human agent with context. This is a standard telephony capability that could plausibly be documented, so absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

   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

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

   weight 1 · round drawn
   Bland—none0/10

   The evidence pack covers pathways, SIP, webhooks, evals, and MCP/CLI tooling, but nowhere mentions DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving — capabilities that are plausible for a voice telephony platform but are simply undocumented here.

   ⚑ flag

   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

Campaigns

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

   weight 2 · round to Bland
   Bland✓fullclaimed8/10

   Bland's docs explicitly describe batch calls for uploading CSV recipient lists to run high-volume outbound campaigns, backed by scheduling/throughput-related infrastructure like SIP integration, phone number management, and analytics/evals to monitor campaign performance. Missing for 10: explicit documentation of scheduling controls (e.g., call windows/timing) and rate-limiting/throughput knobs specifically, plus independent hands-on verification of batch campaign behavior at scale.

   • [claimed-docs] “Batch calls let you initiate high-volume call campaigns by uploading a list of recipients via CSV.”
   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”
   • [claimed-docs] “Bland supports inbound and outbound SIP. Point calls from your carrier or PBX at Bland to be answered by an agent, or have Bland place calls…”
   • [claimed-docs] “Number porting to bring existing numbers to Bland”

   proof ↗⚑ flag

   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

Numbers

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

   weight 3 · round to Bland
   Bland✓fullprobed8/10

   Bland's docs explicitly document creating/managing inbound phone numbers, outbound call dispatch via API, bringing your own Twilio numbers, and SIP for both inbound/outbound, all programmatically accessible, plus a CLI/MCP that manage phone numbers and calls end-to-end. Missing for 10: no explicit REST API reference/OpenAPI spec confirmed (probe shows openapi.json 404s) and no independent hands-on developer report of a full provision+call round trip.

   • [claimed-docs] “Dispatch AI phone calls to call customers, leads, and to streamline operations.”
   • [claimed-docs] “Create inbound phone numbers for customer support, etc.”
   • [claimed-docs] “Users can connect their own Twilio account to Bland, easily bring over your existing phone numbers to use within the platform.”
   • [claimed-docs] “Number porting to bring existing numbers to Bland”
   • [claimed-docs] “Bland supports inbound and outbound SIP. Point calls from your carrier or PBX at Bland to be answered by an agent, or have Bland place calls…”
   • [claimed-docs] “Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.bland.ai/openapi.json, https://docs.bland.ai/swagger.json, https://docs.bland.ai/api/op…”

   proof ↗⚑ flag

   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

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 drawn
   Bland✓fullclaimed8/10

   Bland's docs explicitly document inbound/outbound SIP trunking to connect a customer's own carrier or PBX, plus number porting, and separately support connecting an existing Twilio account/numbers. Missing for 10: no mention of Telnyx import specifically and no independent/hands-on validation of SIP setup success.

   • [claimed-docs] “Bland supports inbound and outbound SIP. Point calls from your carrier or PBX at Bland to be answered by an agent, or have Bland place calls…”
   • [claimed-docs] “Number porting to bring existing numbers to Bland”
   • [claimed-docs] “Users can connect their own Twilio account to Bland, easily bring over your existing phone numbers to use within the platform.”

   proof ↗⚑ flag

   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

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 Bland
   Bland~partialclaimed7/10

   Bland's Evals feature explicitly lets users define LLM-judge agents that grade calls on custom dimensions (quality, resolution, etc.), and the Testbed lets you replay and analyze specific call nodes to spot failures — directly matching automated call review/scoring. However, this requires the user to configure eval criteria rather than being a fully out-of-the-box automatic analysis, and there's no evidence of a pre-built default 'failure flagging' report. Missing for 10: evidence of fully automatic, no-setup call scoring/dashboard, and independent/hands-on validation of eval accuracy.

   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bland
   Bland~partialprobed4/10

   Evidence confirms Bland has an analytics layer (MCP server can 'query analytics') and quality-grading tools like Evals (LLM judges scoring call dimensions) and a testbed for reviewing call interactions, implying some built-in metrics exist. However, there is no direct evidence of an actual dashboard UI showing success rates, call durations, outcomes, or sentiment trends over time — analytics access shown is via MCP/API query rather than a visual dashboard. Missing for 10: screenshots or docs of a native analytics dashboard, explicit mention of success-rate/duration/sentiment metrics, and independent confirmation the dashboard requires no custom building.

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”

   proof ↗⚑ flag

   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

Monitoring

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

   weight 1 · round to Bland
   Bland~partialclaimed4/10

   Bland provides post-call webhooks, evals with LLM judges, and an MCP integration that can 'query analytics' — giving some after-the-fact quality/analytics visibility — but there is no documented live-call monitoring dashboard, real-time alerting, or error-rate-spike notification system in the evidence pack. Missing for 10: live/real-time call monitoring UI, configurable alert thresholds, error-rate spike detection/paging, independent confirmation these exist in production.

   • [claimed-docs] “Post-call webhooks are HTTP notifications that Bland AI automatically sends to your server after a phone call completes.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”

   proof ↗⚑ flag

   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

Testing

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

   weight 2 · round to Bland
   Bland✓fullclaimed8/10

   Bland provides explicit pre-production testing tools: Evals (LLM-judge grading of call quality), the Testbed (replay/edit/re-run node interactions on historical or test chats), staging promotion and draft-vs-production pathway separation, and canary/A/B rollout testing against real calls before full deployment. Together these let a developer simulate conversations and grade agent behavior before real phone calls go live. missing for 10: no independent/hands-on evidence of eval accuracy or testbed usage from outside vendor docs, and no explicit description of a pure text-based conversation simulator separate from testbed/staging.

   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges.”
   • [claimed-docs] “The testbed lets you take any call ... isolate a specific node interaction, edit the prompt, and run it multiple times to see how the output…”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “The testbed lets you take any call — whether it's a historical call from call logs or a test chat from the pathway editor — isolate a specif…”
   • [claimed-docs] “You can also promote a version to staging to test it before it goes live, or send an individual call against a specific”
   • [claimed-docs] “When you edit a pathway, you are working on a draft. Live calls are not affected. They keep using the published production version.”
   • [claimed-docs] “This is how you A/B test a new agent release against your live production version, with real calls, before committing to a full rollout.”
   • [claimed-docs] “Bland supports canary deployments — a way to run a new release on a separate set of containers alongside your production infrastructure and …”

   proof ↗⚑ flag

   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

Post call

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

   weight 2 · round drawn
   Bland~partialclaimed6/10

   Bland documents post-call webhooks that automatically deliver call data to a developer's server after each call, and evals let you grade/classify calls (dispositions) via LLM judges — both align with the API/webhook delivery and outcome-tagging parts of the story. However, there's no explicit documentation of structured entity extraction (e.g., named fields like names, dates, custom entities) as a distinct capability, nor a described webhook payload schema. Missing for 10: explicit entity-extraction feature docs, sample webhook payload showing structured outcome/entity/disposition fields, and independent confirmation of the data delivered.

   • [claimed-docs] “Post-call webhooks are HTTP notifications that Bland AI automatically sends to your server after a phone call completes.”
   • [claimed-docs] “Evals let you measure the quality of your calls with LLM judges. You define eval agents, each of which grades one dimension of a call”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”

   proof ↗⚑ flag

   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

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
   Bland—none0/10

   Bland ships an MCP *server* so coding agents can control the Bland account (docs-11/20/27, probe-3/probe-rt-2), which is the opposite role from what the story asks — the voice agent itself acting as an MCP *client* that plugs in external MCP servers as tool sources mid-call. Tool/function calling is documented only via custom HTTP API integrations (bland-docs-4, bland-docs-25), with no mention of the agent consuming MCP servers as a toolset source during calls.

   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [claimed-docs] “The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validat…”
   • [probe] “official MCP server documented at https://docs.bland.ai/integrations/mcp/overview”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP endpoint https://api.bland.ai/v1/mcp returned HTTP 4…”
   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Bland
   Bland~partialclaimed6/10

   Bland's pathway/tools docs confirm agents can call external APIs and execute webhooks mid-conversation (bland-docs-4, bland-docs-25, bland-docs-30), which supports live function calling during a call. However, no evidence describes mechanisms for avoiding dead air (e.g., filler speech, streaming partial responses) while waiting on API results. missing for 10: explicit documentation of latency-masking/filler-speech behavior during API calls, and independent/hands-on confirmation of smooth conversational flow.

   • [claimed-docs] “The API integration lets you connect your AI agent to any HTTP endpoint.”
   • [claimed-docs] “Connect external APIs and take live actions during phone calls.”
   • [claimed-docs] “Give your agent instructions on how it should respond at specific points of the conversation. Choose between prompting or fixed sentences. E…”
   • [claimed-docs] “Conversational pathways are our new way of prompting Bland that has led to major breakthroughs in realism. Give your agent instructions on h…”

   proof ↗⚑ flag

   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

Recording

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

   weight 2 · round to Bolna
   Bland—none0/10

   No evidence pack item explicitly documents an API or endpoint for retrieving full call recordings or transcripts programmatically; references to call logs (testbed) and post-call webhooks hint at underlying data but never confirm a recording/transcript retrieval capability.

   ⚑ flag

   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

Transcription

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

   weight 2 · round to Bolna
   Bland—none0/10

   Bland is a phone-call AI platform where transcription accuracy is clearly relevant, but the evidence pack contains no mention of STT provider selection, language model choice for transcription, or key-term/vocabulary boosting features. missing for 10: STT provider selection, transcription accuracy documentation, custom key terms/vocabulary support, language model configuration for transcription.

   ⚑ flag

   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

Voices

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

   weight 2 · round to Bland
   Bland~partialclaimed4/10

   Bland documents voice cloning itself (a ~10-second clean sample sets the quality ceiling) which supports the 'clone a custom brand voice' half of the story, but no evidence describes a documented consent process, verification, or authorization requirement for cloning someone's voice. missing for 10: documented consent/verification workflow for voice cloning, legal/compliance guidance on brand-voice rights, independent confirmation of the cloning feature's fidelity.

   • [claimed-docs] “A clone needs one clean sample of about ten seconds. Quality of the sample sets the ceiling on quality of the voice”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Bolna
   Bland~partialclaimed3/10

   Docs show voice cloning support (a 10-second sample sets voice quality) but there is no evidence of a broad pre-built voice library to choose from, nor any mention of plugging in multiple third-party TTS providers. Missing for 10: documented voice library/catalog, multi-provider TTS integration, and any comparison of voice options.

   • [claimed-docs] “A clone needs one clean sample of about ten seconds. Quality of the sample sets the ceiling on quality of the voice”

   proof ↗⚑ flag

   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