# Reports

Every report of the AI Agent Readiness Test: scorecards, verdicts, and verified receipts for each product tested.

The scorecards

One report per product. A fixed five-task battery, a fixed three-model panel, and a verified receipt behind every quote.

[

ProductGrade

AssemblyAI A- 92.5%

Recover from a 429 landed PARTIAL: A complete 429 remedy exists only for LLM Gateway; on the transcription side the error table lists 429 with no fix while the rate-limits page states the HTTP ceiling returns 403, so a 429 on /v2/transcript has no documented cause or correction.

Voice & speech

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/assemblyai-docs-ai-agent-readiness/)[

ProductGrade

Clerk B- 81.2%

Find the exact limits landed PARTIAL: Rate limits are exact, but the Organizations guide scopes 50 MROs to development while pricing states 100 per application.

Identity & auth

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/clerk-docs-ai-agent-readiness/)[

ProductGrade

ClickHouse A+ 97.5%

Find the exact limits landed PARTIAL: Service, warehouse, organization, and API rate limits are all stated with exact numbers, but a knowledge-base page gives 100000 parts per service where the usage-limits and cloud-compatibility pages both give 10k.

Databases & analytics

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/clickhouse-docs-ai-agent-readiness/)[

ProductGrade

Deepgram B- 81.2%

Find the exact limits landed PARTIAL: The plan tables give per-region caps, but they state 50 pre-recorded requests where the pre-recorded guide states 100.

Voice & speech

Fern · published 2026-09-22

](https://docsforagents.com/reports/deepgram-docs-ai-agent-readiness/)[

ProductGrade

Doppler B 83.8%

Recover from a 429 landed PARTIAL: The headers provide a limit number and retry timing, but they do not identify the triggering scope or request bucket.

Security & compliance

ReadMe · published 2026-09-22

](https://docsforagents.com/reports/doppler-docs-ai-agent-readiness/)[

ProductGrade

fal.ai A 95.0%

Find the exact limits landed SPLIT: The docs omit purchase thresholds and exact per-endpoint quotas, while the FAQ says excess requests queue but the concurrency guide documents raw-HTTP 429s.

AI models & inference

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/fal-ai-docs-ai-agent-readiness/)[

ProductGrade

Linear D+ 68.8%

Recover from a RATELIMITED error landed PARTIAL: The page shows separate limit headers, but it does not map a generic error to one limiter or state a complete retry procedure.

Productivity & collaboration

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/linear-docs-ai-agent-readiness/)[

ProductGrade

LiveKit A+ 97.5%

Find the exact limits landed PASS: All quotas and rate limits documented on a single page with consistent values across concurrency, API, LLM, STT, TTS, and observability categories.

Voice & speech

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/livekit-docs-ai-agent-readiness/)[

ProductGrade

LlamaIndex C- 71.2%

Use the Python SDK landed PARTIAL: The generated reference states the two input options but leaves the upload step to a separate page.

Agent frameworks & memory

Astro Starlight · published 2026-09-22

](https://docsforagents.com/reports/llamaindex-docs-ai-agent-readiness/)[

ProductGrade

Mastra B- 80.0%

Find the exact limits landed FAIL: The platform API says rate limits are unpublished, while the environments page says the environment allowance depends on the plan without stating a number.

Agent frameworks & memory

Docusaurus · published 2026-09-22

](https://docsforagents.com/reports/mastra-docs-ai-agent-readiness/)[

ProductGrade

Middesk C- 71.2%

Find the exact limits landed PARTIAL: One exact global number is stated in a single sentence on a page titled for status codes, but no plan quotas, per-endpoint limits, or dedicated rate-limit page exist, and the OpenAPI spec and the API reference pages never mention the limit at all.

Identity & auth

Fern · published 2026-09-22

](https://docsforagents.com/reports/middesk-docs-ai-agent-readiness/)[

ProductGrade

Mux C 76.2%

Find the exact limits landed PARTIAL: API and pricing values agree, but the organization-wide cap and Data burst sizes remain unquantified.

Content & web platforms

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/mux-docs-ai-agent-readiness/)[

ProductGrade

Netlify C+ 77.5%

Find the exact limits landed PARTIAL: Numeric API ceilings are clear, but scope is undefined and plan quotas differ between credit-based and legacy accounts.

Cloud & developer platforms

Astro Starlight · published 2026-09-22

](https://docsforagents.com/reports/netlify-docs-ai-agent-readiness/)[

ProductGrade

Notion A 95.0%

Find the exact limits landed PARTIAL: The page gives exact per-connection and listed size limits, but omits numeric shared-workspace and child-depth limits.

Productivity & collaboration

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/notion-docs-ai-agent-readiness/)[

ProductGrade

Perplexity A- 92.5%

Find the exact limits landed PARTIAL: The page omits numeric Router limits, and the FAQ contradicts its API-specific tier and limiter rules.

Search & retrieval

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/perplexity-docs-ai-agent-readiness/)[

ProductGrade

Persona B- 81.2%

Find the exact limits landed PARTIAL: The guide names all six headers and directs readers to environment-specific values, but its 300 default conflicts with the API reference’s 3003 example.

Identity & auth

Fern · published 2026-09-22

](https://docsforagents.com/reports/persona-docs-ai-agent-readiness/)[

ProductGrade

Plaid A 93.8%

Find the exact limits landed PARTIAL: Plaid lists Sandbox and Production defaults by Item and client, and Billing states a 10-Item Trial quota, but the table disclaims completeness and customer uniformity.

Payments & business data

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/plaid-docs-ai-agent-readiness/)[

ProductGrade

PostHog D- 60.0%

Find the exact limits landed PARTIAL: The numeric rate and pricing tables agree, but the linked monthly query allowance has no amount or matching section on the query page.

Observability & analytics

Gatsby · published 2026-09-22

](https://docsforagents.com/reports/posthog-docs-ai-agent-readiness/)[

ProductGrade

Postman C 75.0%

Find the exact limits landed PARTIAL: The values require overview, pricing, and endpoint pages, and the per-user scope conflicts with support's public-IP explanation.

Cloud & developer platforms

Fern · published 2026-09-22

](https://docsforagents.com/reports/postman-docs-ai-agent-readiness/)[

ProductGrade

Sentry C 76.2%

Find the exact limits landed FAIL: The API page gives headers but no numeric endpoint limits; pricing gives paid baselines but omits the Developer plan quota.

Observability & analytics

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/sentry-docs-ai-agent-readiness/)[

ProductGrade

Supabase A 96.2%

Verify a webhook landed PARTIAL: Creation and the INSERT payload shape are documented, but no page states how a delivery is authenticated: there is no signing secret, signature header, or verification procedure, and the Dashboard steps stop at selecting events without reaching the URL or headers fields.

Databases & analytics

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/supabase-docs-ai-agent-readiness/)[

ProductGrade

Together AI A 93.8%

Find the exact limits landed PARTIAL: The docs retire plan tiers and describe dynamic factors, but one page promises limit headers on every request while another says successful responses omit them.

AI models & inference

Mintlify · published 2026-09-22

](https://docsforagents.com/reports/together-ai-docs-ai-agent-readiness/)[

ProductGrade

Vercel B+ 88.8%

Find the exact limits landed PARTIAL: The rate-limit table gives plan values and scopes, but the general table says Enterprise deployments per day are Custom rather than 24000.

Cloud & developer platforms

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/vercel-docs-ai-agent-readiness/)[

ProductGrade

WorkOS A- 92.5%

Find the exact limits landed PARTIAL: General (6,000 requests per 60 seconds per API key) and AuthKit (1,000 reads and 500 writes per 10 seconds per environment) are exact and scoped, but the default email provider's sending limits are stated only qualitatively, with no number an agent can plan against.

Identity & auth

Custom Next.js · published 2026-09-22

](https://docsforagents.com/reports/workos-docs-ai-agent-readiness/)[

ProductGrade

Ably C- 70.0%

Recover from error 42910 landed PARTIAL: The page gives complete recovery guidance; an older FAQ contradicts its scope, and a legacy markdown URL returned 404.

Email & messaging

Gatsby 5.16.1 · published 2026-09-21

](https://docsforagents.com/reports/ably-docs-ai-agent-readiness/)[

ProductGrade

Amp D+ 68.8%

Find the exact limits landed PARTIAL: The pages define every requested rule, but possible extra subscription usage has no formula or exact ceiling.

Coding agents

Custom SvelteKit · published 2026-09-21

](https://docsforagents.com/reports/amp-docs-ai-agent-readiness/)[

ProductGrade

Baseten A 95.0%

Use the Python SDK landed PARTIAL: The SDK lacks runnable Python deployment code, and two Qwen deployment guides require different builder GPU counts.

AI models & inference

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/baseten-docs-ai-agent-readiness/)[

ProductGrade

Blacksmith B+ 87.5%

Find the exact limits landed PARTIAL: Resource, cache, concurrency, and platform limits are exact, but the runner and pricing pages disagree on per-minute savings.

Cloud & developer platforms

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/blacksmith-docs-ai-agent-readiness/)[

ProductGrade

Cline B- 80.0%

Find the exact limits landed PARTIAL: The $9.99/month price and the per-1M-token reference rates are exact, but the three ClinePass quota windows are defined circularly with no magnitude, and no page in the API reference states a numeric Cline API rate limit.

Coding agents

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/cline-docs-ai-agent-readiness/)[

ProductGrade

CodeRabbit A 96.2%

Find the exact limits landed PARTIAL: The plans page gives 10 trial reviews per hour for Pro+, while the FAQ gives 3 for the default Pro+ trial.

Coding agents

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/coderabbit-docs-ai-agent-readiness/)[

ProductGrade

CopilotKit C 76.2%

Find the exact limits landed FAIL: The page names all five limit categories but omits a complete per-plan matrix, and the linked dashboard returned only an app shell.

Agent frameworks & memory

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/copilotkit-docs-ai-agent-readiness/)[

ProductGrade

DeepInfra A- 91.2%

Verify an inference webhook landed PARTIAL: The page documents submission and success or failure payloads, but it gives no callback-authenticity verification method.

AI models & inference

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/deepinfra-docs-ai-agent-readiness/)[

ProductGrade

Deno D+ 67.5%

Find the exact limits landed PARTIAL: The limits page says 512MB, while the builds reference says 768MB by default and 4GB on Pro.

Cloud & developer platforms

Custom Deno Deploy site · published 2026-09-21

](https://docsforagents.com/reports/deno-docs-ai-agent-readiness/)[

ProductGrade

ElevenLabs D 66.2%

Find the exact limits landed PARTIAL: The 429 page gives unscoped plan concurrency values, while Models adds doubled Flash limits; two alternative concurrency URLs failed.

Voice & speech

Fern · published 2026-09-21

](https://docsforagents.com/reports/elevenlabs-docs-ai-agent-readiness/)[

ProductGrade

Exa A- 91.2%

Find the exact limits landed PARTIAL: The docs give credits, prices, and Enterprise differences, but rate-limits says 10 QPS while Starter pricing says 5 QPS.

Search & retrieval

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/exa-docs-ai-agent-readiness/)[

ProductGrade

Expo B- 82.5%

Find the exact limits landed PARTIAL: No page under docs.expo.dev states per-plan MAU, bandwidth, storage, or concurrency counts; the numbers exist only on the marketing site at expo.dev/pricing and its pricing.md mirror.

Cloud & developer platforms

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/expo-docs-ai-agent-readiness/)[

ProductGrade

FastMCP A 95.0%

Recover from a tool error landed PARTIAL: The page documents ToolError and is\_error handling, but it gives no corrective retry rule or example.

Agent frameworks & memory

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/fastmcp-docs-ai-agent-readiness/)[

ProductGrade

Fused F 52.5%

Find the exact limits landed PARTIAL: Realtime timeout (120s) and parallel ceilings (max\_workers default 32, max 1000; worker\_concurrency default 1; max\_retry default 2) are stated precisely, but the realtime RAM ceiling is given as ~10GB on the realtime and fused-run pages and as ~4GB twice on the scaling-out page, and no plan or account quota carries a number anywhere in the docs.

Geospatial & maps

Docusaurus 3.9.2 · published 2026-09-21

](https://docsforagents.com/reports/fused-docs-ai-agent-readiness/)[

ProductGrade

Hermes Agent F 53.8%

Find the exact limits landed PARTIAL: Hermes-owned limits are stated exactly but only on the page that owns each subsystem, API server max\_concurrent\_runs default 10, webhook 30 requests per minute per route, webhook body 1 MB, delegation max\_concurrent\_children default 3, max\_concurrent\_sessions null, while no page gives a single numeric model-provider plan quota, so the provider half of the question is answered only by "upgrade your provider plan".

Coding agents

Docusaurus 3.10.2 · published 2026-09-21

](https://docsforagents.com/reports/hermes-agent-docs-ai-agent-readiness/)[

ProductGrade

Inkeep C+ 78.8%

Verify an agent webhook trigger landed PARTIAL: Definition, pushing, verification, and tracking are documented, but signature formatting is missing and invocation endpoints conflict.

Agent frameworks & memory

Fumadocs · published 2026-09-21

](https://docsforagents.com/reports/inkeep-docs-ai-agent-readiness/)[

ProductGrade

Letta C- 70.0%

Find the exact limits landed PARTIAL: Agent caps and API-plan charges are exact (Free "limited to 3 stateful agents", Pro "Up to 20 stateful agents", API Plan "$20 /month", "$0.10 / active agent / mo", "$0.00015 / sec tool execution"), but no page anywhere states a numeric Letta Auto quota, the FAQ restates the free cap as an unquantified "limited number of total agents", and spending limits are only referenced as an email notification with no documented place to set one.

Agent frameworks & memory

Astro Starlight · published 2026-09-21

](https://docsforagents.com/reports/letta-docs-ai-agent-readiness/)[

ProductGrade

Mapbox B- 80.0%

Configure an access token landed PARTIAL: The guides cover least-privilege scopes, URL rules, 401, and 403, but troubleshooting also recommends all public scopes.

Geospatial & maps

Docusaurus 3.6.3 · published 2026-09-21

](https://docsforagents.com/reports/mapbox-docs-ai-agent-readiness/)[

ProductGrade

Massive.com C- 71.2%

Find the exact limits landed PARTIAL: No request limit appears anywhere under /docs/; the four values are only reachable in one knowledge-base article that also states "While we do not have a specific rate limit" alongside the 5-per-minute free-tier cap and the 100-requests-per-second ceiling, while plan-specific data access lives separately on each endpoint page as "Included in all Stocks plans".

Payments & business data

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/massive-docs-ai-agent-readiness/)[

ProductGrade

Mem0 C 73.8%

Find the exact limits landed FAIL: No page gives all requested limits by plan; the attempted pricing and rate-limit pages returned no content.

Agent frameworks & memory

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/mem0-docs-ai-agent-readiness/)[

ProductGrade

Merge C 76.2%

Find the exact limits landed PARTIAL: The three tier values match across HRIS and ATS, but the overview neither lists nor links the 1-request-per-10-seconds async polling exception.

Payments & business data

Fern · published 2026-09-21

](https://docsforagents.com/reports/merge-docs-ai-agent-readiness/)[

ProductGrade

MiniMax C 76.2%

Find the exact rate limits landed PARTIAL: The table gives modality values, but Token Plan throttling is dynamic and most modality tables omit TPM or concurrency.

AI models & inference

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/minimax-docs-ai-agent-readiness/)[

ProductGrade

MotherDuck A 96.2%

Use the Python SDK landed PARTIAL: The Python landing page extraction failed, while direct guides supplied the SDK path but disagreed on whether a database name is required.

Databases & analytics

Docusaurus 3.10.2 · published 2026-09-21

](https://docsforagents.com/reports/motherduck-docs-ai-agent-readiness/)[

ProductGrade

n8n A 93.8%

Find the exact limits landed PARTIAL: The values require Docs, Pricing, and Support, and Pro retention conflicts at 30 days versus 14 days.

Workflows & automation

GitBook · published 2026-09-21

](https://docsforagents.com/reports/n8n-docs-ai-agent-readiness/)[

ProductGrade

Neo4j F 57.5%

Find the exact limits landed PARTIAL: Official pages disagree on Free graph and backup limits, omit exact Free RAM and storage, and differ on paid maxima.

Databases & analytics

Antora and Asciidoctor · published 2026-09-21

](https://docsforagents.com/reports/neo4j-docs-ai-agent-readiness/)[

ProductGrade

Neon A 93.8%

Verify an Auth webhook landed PARTIAL: The reference covers configuration, payloads, and verification, but it never defines NEON\_AUTH\_URL; the linked walkthrough uses NEON\_AUTH\_BASE\_URL.

Databases & analytics

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/neon-docs-ai-agent-readiness/)[

ProductGrade

OpenCode F 42.5%

Start the first coding session landed PARTIAL: The introduction documents provider connection and project initialization, but prerequisites and setup span multiple sections.

Coding agents

Astro Starlight · published 2026-09-21

](https://docsforagents.com/reports/opencode-docs-ai-agent-readiness/)[

ProductGrade

Orkes F 51.2%

Find the exact limits landed PARTIAL: Task scope and rate-limit zero behavior are documented, but concurrentExecLimit=0 behavior is not stated.

Workflows & automation

MkDocs Material 9.7.5 · published 2026-09-21

](https://docsforagents.com/reports/orkes-docs-ai-agent-readiness/)[

ProductGrade

Ory D- 62.5%

Find the exact limits landed PARTIAL: New and legacy values differ by declared policy, but exact thresholds, shared counters, and 429 handling span four resources.

Identity & auth

Docusaurus 3.10.0 · published 2026-09-21

](https://docsforagents.com/reports/ory-docs-ai-agent-readiness/)[

ProductGrade

Overture Maps F 58.8%

Find the exact access limits landed PASS: The client page fixes order, formats, and whole-type behavior; the cloud-sources table lists six themes and 15 types.

Geospatial & maps

Docusaurus 3.10.2 · published 2026-09-21

](https://docsforagents.com/reports/overture-maps-docs-ai-agent-readiness/)[

ProductGrade

Radar B 83.8%

Find the exact limits landed PARTIAL: Track's hourly and daily values are unstated; fixed plan quotas are absent, and radar.com/pricing.md returned Not Found.

Geospatial & maps

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/radar-docs-ai-agent-readiness/)[

ProductGrade

Recall.ai B- 80.0%

Find the exact limits landed PARTIAL: Create is 120/min/workspace, list is 60/min/workspace, and scheduled concurrency is unlimited, but ad-hoc concurrency is workspace-specific versus 30.

Voice & speech

ReadMe · published 2026-09-21

](https://docsforagents.com/reports/recall-ai-docs-ai-agent-readiness/)[

ProductGrade

Redis B- 82.5%

Find the exact data limits landed PARTIAL: Key and memory scopes are clear; element pages differ by one, and the list page exceeded the 5MB fetch limit.

Databases & analytics

Hugo 0.143.1 · published 2026-09-21

](https://docsforagents.com/reports/redis-docs-ai-agent-readiness/)[

ProductGrade

Reducto A 95.0%

Recover from throttling landed PARTIAL: The rate-limit page maps each 429 body to a fix, but the agent guide incorrectly describes 429 as concurrent-request throttling.

Data pipelines & documents

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/reducto-docs-ai-agent-readiness/)[

ProductGrade

Roboflow C 76.2%

Find the exact limits landed PARTIAL: Public has 15 credits, 10 projects, and 2 members; Core starts at 30 credits, 20 projects, and 3 members, while Hosted API capacity depends on shared credit use.

AI models & inference

GitBook · published 2026-09-21

](https://docsforagents.com/reports/roboflow-docs-ai-agent-readiness/)[

ProductGrade

Runpod B 83.8%

Find the exact limits landed PARTIAL: The docs give all requested scopes, but sync retention appears as both one minute and up to five minutes.

Cloud & developer platforms

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/runpod-docs-ai-agent-readiness/)[

ProductGrade

Runware B- 81.2%

Find the exact limits landed SPLIT: The page states no hard rate limits and recommends 2-4 requests, but it gives no numeric queue capacity.

AI models & inference

Custom Astro · published 2026-09-21

](https://docsforagents.com/reports/runware-docs-ai-agent-readiness/)[

ProductGrade

Speechmatics D 65.0%

Verify a transcription notification landed PARTIAL: The page covers configuration, authentication, allowlists, 2xx acknowledgement, ordering, and failures, but gives no retry timeout value.

Voice & speech

Docusaurus 3.9.2 · published 2026-09-21

](https://docsforagents.com/reports/speechmatics-docs-ai-agent-readiness/)[

ProductGrade

Stream D+ 68.8%

Find the exact limits landed PARTIAL: Both limit pages agree on Connect 10,000, Send Message 1,000, and 60 user requests per endpoint and platform.

Email & messaging

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/stream-docs-ai-agent-readiness/)[

ProductGrade

Stytch A- 90.0%

Find the exact limits landed PARTIAL: The page supplies both quotas and identifiers, but its second-to-day intervals conflict with its universal “top of the hour” rule.

Identity & auth

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/stytch-docs-ai-agent-readiness/)[

ProductGrade

SurrealDB B- 82.5%

Find the exact limits landed PARTIAL: HTTP limits agree, but Free memory conflicts: 512 MB in instance docs versus 1 GB on pricing.

Databases & analytics

Custom Vike and React · published 2026-09-21

](https://docsforagents.com/reports/surrealdb-docs-ai-agent-readiness/)[

ProductGrade

Tavily A+ 97.5%

Find the exact limits landed PASS: Rate Limits covers every requested scope, while Credits & Pricing covers all plan quotas and endpoint costs without conflicts.

Search & retrieval

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/tavily-docs-ai-agent-readiness/)[

ProductGrade

TileDB F 23.8%

Find the exact limits landed FAIL: It documents $100 for six months but omits storage rates and API quotas; the pricing link shows deployment pricing.

Databases & analytics

Quarto 1.6.42 · published 2026-09-21

](https://docsforagents.com/reports/tiledb-docs-ai-agent-readiness/)[

ProductGrade

Tinybird A 95.0%

Find the exact limits landed PARTIAL: The values are 250 per IP per region and 20, 100, and 200 per workspace, but pricing says all limits are organization-wide.

Databases & analytics

Custom Next.js · published 2026-09-21

](https://docsforagents.com/reports/tinybird-docs-ai-agent-readiness/)[

ProductGrade

Trigger.dev A 95.0%

Find the exact limits landed PARTIAL: The limits page covers every category, but Triggering conflicts on payload and output caps.

Workflows & automation

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/trigger-dev-docs-ai-agent-readiness/)[

ProductGrade

TrueFoundry B+ 87.5%

Find the exact limits landed PARTIAL: The docs define six units, first-match order, and monthly plan quotas, but state no numeric default limit when no custom rule exists.

AI models & inference

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/truefoundry-docs-ai-agent-readiness/)[

ProductGrade

Union.ai B- 82.5%

Verify a workflow webhook landed PARTIAL: The sender is documented, but receiver token checking appears only in a separate webhook app example with different semantics.

Workflows & automation

Hugo with custom Union theme · published 2026-09-21

](https://docsforagents.com/reports/union-ai-docs-ai-agent-readiness/)[

ProductGrade

Unstructured A 96.2%

Transform a document landed PARTIAL: The quickstart gives a complete flow, but the create-job reference appends /api/v1 to a variable that already ends with /api/v1.

Data pipelines & documents

Mintlify · published 2026-09-21

](https://docsforagents.com/reports/unstructured-docs-ai-agent-readiness/)[

ProductGrade

Vapi B- 81.2%

Verify a server event landed SPLIT: The docs configure HMAC credentials but never define signed bytes, signature encoding, timestamp handling, or receiver verification code.

Voice & speech

Fern · published 2026-09-21

](https://docsforagents.com/reports/vapi-docs-ai-agent-readiness/)[

ProductGrade

Vectara F 50.0%

Find the exact limits landed FAIL: The trial page states one credit allocation but sends paid-plan details to a marketing pricing page; no exact paid quotas appear in the docs.

Search & retrieval

Docusaurus 3.10.1 · published 2026-09-21

](https://docsforagents.com/reports/vectara-docs-ai-agent-readiness/)[

ProductGrade

Warp B+ 88.8%

Find the exact limits landed PARTIAL: Plan values are findable, but two pages disagree on whether auto-reload fires at or below 100 credits.

Coding agents

Astro Starlight · published 2026-09-21

](https://docsforagents.com/reports/warp-docs-ai-agent-readiness/)[

ProductGrade

Zep B- 81.2%

Find the exact limits landed PARTIAL: The account window is one minute; Flex lists 600 RPM and Flex Plus 1,000, while Free, Flex under load, and Enterprise vary.

Agent frameworks & memory

Fern · published 2026-09-21

](https://docsforagents.com/reports/zep-docs-ai-agent-readiness/)[

ProductGrade

Zilliz Cloud D- 60.0%

Find the exact limits landed PARTIAL: The docs give collection, partition, and insert limits but omit Free DDL and conflict on load rates; /docs/limits-and-restrictions did not load.

Search & retrieval

Docusaurus 3.10.1 · published 2026-09-21

](https://docsforagents.com/reports/zilliz-docs-ai-agent-readiness/)[

ProductGrade

Airbyte D+ 67.5%

Find the exact limits landed PARTIAL: The limits page lists all numbers, but /platform/next/ returned 404 and the workspace page excludes Plus.

Data pipelines & documents

Docusaurus 3.10.1 · published 2026-08-20

](https://docsforagents.com/reports/airbyte-docs-ai-agent-readiness/)[

ProductGrade

Arcade.dev F 53.8%

Find the exact limits landed FAIL: The docs mention shared provider limits but give no exact API or plan numbers, and llms-full.txt returned 404.

Agent frameworks & memory

Nextra · published 2026-08-20

](https://docsforagents.com/reports/arcade-dev-docs-ai-agent-readiness/)[

ProductGrade

CARTO B- 82.5%

Find the exact limits landed PARTIAL: The docs give matching per-IP ceilings and annual API weights, but they publish only a 35-300 monthly M2M range and no numeric API Access Token entitlement by plan.

Geospatial & maps

GitBook · published 2026-08-20

](https://docsforagents.com/reports/carto-docs-ai-agent-readiness/)[

ProductGrade

Composio B- 80.0%

Use the Python SDK landed PARTIAL: The Python SDK reference executes composio.tools.execute() without the required version or opt-in flag, while the agent quickstart uses current sessions.

Agent frameworks & memory

Fumadocs on Next.js · published 2026-08-20

](https://docsforagents.com/reports/composio-docs-ai-agent-readiness/)[

ProductGrade

Convex B- 82.5%

Verify a log webhook landed PARTIAL: The page documents setup and events, but its verifier parses the request before reading the bytes that it verifies.

Databases & analytics

Docusaurus 3.10.1 · published 2026-08-20

](https://docsforagents.com/reports/convex-docs-ai-agent-readiness/)[

ProductGrade

Daytona D- 62.5%

Find the exact limits landed PARTIAL: The limits page publishes tier resource pools and three per-minute request columns; the agents reduced the task because resource numbers differ across live pages.

Agent sandboxes & browsers

Astro Starlight · published 2026-08-20

](https://docsforagents.com/reports/daytona-docs-ai-agent-readiness/)[

ProductGrade

DuckDB F 56.2%

Find the exact limits landed PARTIAL: Defaults are 80% RAM, 1000, and 4 GB; temporary storage conflicts as unlimited versus 90% free disk.

Databases & analytics

Jekyll 4.4.1 · published 2026-08-20

](https://docsforagents.com/reports/duckdb-docs-ai-agent-readiness/)[

ProductGrade

E2B B+ 87.5%

Recover from a 429 landed FAIL: The reference names the cause but provides no retry timing, response-header guidance, backoff, or limit-remediation steps.

Agent sandboxes & browsers

Mintlify · published 2026-08-20

](https://docsforagents.com/reports/e2b-docs-ai-agent-readiness/)[

ProductGrade

Felt A 95.0%

Find the exact limits landed SPLIT: The guide states 300 requests per minute per IP, but gives no numeric plan threshold and references 429 inconsistently.

Geospatial & maps

GitBook · published 2026-08-20

](https://docsforagents.com/reports/felt-docs-ai-agent-readiness/)[

ProductGrade

Firecrawl B- 81.2%

Verify a crawl webhook landed PARTIAL: The configuration, payload, and HMAC steps are complete, but Overview omits failed from Crawl while the Crawl page lists crawl.failed.

Search & retrieval

Mintlify · published 2026-08-20

](https://docsforagents.com/reports/firecrawl-docs-ai-agent-readiness/)[

ProductGrade

LangChain B+ 87.5%

Find the exact limits landed PARTIAL: The LangSmith tracing path documents exact endpoint limits, plan-tier event limits, data-ingest limits, and monthly trace quotas with scopes and windows.

Agent frameworks & memory

Mintlify · published 2026-08-20

](https://docsforagents.com/reports/langchain-docs-ai-agent-readiness/)[

ProductGrade

Railway C 73.8%

Find the exact limits landed PARTIAL: Both tables are findable, but the API page defines X-RateLimit-Limit as daily beside hourly limits.

Cloud & developer platforms

Custom Next.js · published 2026-08-20

](https://docsforagents.com/reports/railway-docs-ai-agent-readiness/)[

ProductGrade

Browserbase A- 92.5%

A perfect agent surface and a clean quickstart, but the free plan allows either one or three concurrent sessions depending on the page.

Agent sandboxes & browsers

Mintlify · published 2026-08-19

](https://docsforagents.com/reports/browserbase-docs-ai-agent-readiness/)[

ProductGrade

Mailgun C 76.2%

Strong quickstart, one concrete rate-limit number in 144 pages, and it lives under Metrics.

Email & messaging

Redocly · published 2026-08-06

](https://docsforagents.com/reports/mailgun-docs-ai-agent-readiness/)[

ProductGrade

Resend B+ 88.8%

Ships .md mirrors, llms.txt, and an MCP server, and its two webhook pages name the same parameter two different ways.

Email & messaging

Mintlify · published 2026-08-06

](https://docsforagents.com/reports/resend-docs-ai-agent-readiness/)[

ProductGrade

Stripe C+ 78.8%

The docs give instructions to the reading agent itself, and the classic quickstart path graded PARTIAL partly because of it.

Payments & business data

custom in-house · published 2026-08-06

](https://docsforagents.com/reports/stripe-docs-ai-agent-readiness/)

[Subscribe by RSS (opens in a new tab)](https://docsforagents.com/rss.xml) or [nominate a docs site](https://docsforagents.com/nominate/). [Every score in one table](https://docsforagents.com/grades/).

Canonical URL: https://docsforagents.com/reports/