# finch.com: agentic web grade B

Score 33 (coverage 20 + breadth 3 + conformance 10); 3 standards observed across 2 of 9 steps; checked 2026-10-26T00:37:15Z. This grades the agent-facing files published at finch.com, not the organisation's products.

## Manifests

| Manifest | Path | Result | Errors | Warnings |
| --- | --- | --- | --- | --- |
| Agentic Resource Discovery | /.well-known/ard.json | redirected → / |  | redirected to /, not /.well-known/ard.json |
| AI Catalog well-known file | /.well-known/ai-catalog.json | redirected → / |  | redirected to /, not /.well-known/ai-catalog.json |
| MCP Server Cards (SEP-2127) | /mcp/server-card | redirected → / |  | redirected to /, not /mcp/server-card |
| Agent2Agent Protocol | /.well-known/agent-card.json | redirected → / |  | redirected to /, not /.well-known/agent-card.json |
| llms.txt | /llms.txt | valid |  | the H1 is not the first line; no blockquote summary under the title |
| AGENTS.md | /AGENTS.md | redirected → / |  | redirected to /, not /AGENTS.md |
| Agent Skills | /.well-known/agent-skills/index.json | redirected → / |  | redirected to /, not /.well-known/agent-skills/index.json |
| api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs | /.well-known/api-catalog | redirected → / |  | redirected to /, not /.well-known/api-catalog |
| AI Crawler User-Agent Tokens in robots.txt | /robots.txt | no AI tokens |  | no AI crawler token named (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, ...); the policy for them is whatever User-agent: * says (partial); no Agentmap: line (optional convention pointing agents at /.well-known/ard.json); no Content-Signal: line (optional; states ai-train / search / ai-input preferences) |
| security.txt (RFC 9116) | /.well-known/security.txt | absent HTTP 404 |  |  |
| auth.md | /auth.md | redirected → / |  | redirected to /, not /auth.md |
| Open Knowledge Format | /okf/index.md | redirected → / |  | redirected to /, not /okf/index.md |

## Standards observed

- llms.txt: https://finch.com/llms.txt (https://agenticweb.wiki/protocols/llms-txt/)
- OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization): https://finch.com/.well-known/oauth-protected-resource (https://agenticweb.wiki/protocols/oauth-metadata-for-agents/)
- OAuth Client ID Metadata Document: https://finch.com/.well-known/oauth-authorization-server (https://agenticweb.wiki/protocols/oauth-cimd/)

## Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch (https://agenticweb.wiki/protocols/ard/)
2. AGENTS.md: instructions for coding agents working on or with the site (https://agenticweb.wiki/protocols/agents-md/)
3. api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description (https://agenticweb.wiki/protocols/api-catalog-rfc9727/)

Published a manifest or spotted a path we missed? Submit at https://agenticweb.wiki/submit/ or email mailto:info@belgravialabs.com?subject=Manifest%20or%20correction%20for%20finch.com.

## Agent pre-flight & practical readiness

Preferred mode: `llms_txt`. GET /llms.txt and follow the links it names. That index is the page list an agent should read.

Fetch: `GET https://finch.com/llms.txt` GET /llms.txt and follow its links.

Practical readability: exa_parsable yes, markdown negotiation no, render `ssr_rich`, HTML quality `high`, first content at byte 56521, HTML-to-llms.txt token ratio 8.278×, JSON-LD Organization, ImageObject, WebSite, SearchAction, WebPage, Service, Offer.

AI crawler posture: `open_to_all` · Assistant access: OpenAI `allowed`, Anthropic `allowed`, Google `allowed`, Perplexity `allowed`, Exa `allowed`.

Readiness subscores: reach 20/20, readability 22/30, capabilities 6/35, conformance 10/15, total 58/100, grade B.

## Rubric

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15.

JSON: https://agenticweb.wiki/check/finch.com/index.json · badge: https://agenticweb.wiki/badge/finch.com.svg