Is firmly.ai agent ready?
firmly.ai is not yet agent ready: it scores 40/100 (grade D) on the w2agent rubric. Weakest areas: Agent Protocols (8), Structured Data (22), Agent Auth (33), Bot Accessibility (43), Agent Discovery (47).
Changed since last check
+2 points since the previous check (2026-09-16)
Fixed: llms.txt follows spec, Developer portal
Regressed: Reachable as Google-Agent, Reachable as Perplexity-User
Changed: Response time (partial → fail), Agent/bot auth documentation (fail → partial)
Category scores
Technical
75
Agent Auth
33
Agent Discovery
47
Agent Protocols
8
Content Quality
65
Structured Data
22
Bot Accessibility
43
Agent protocol panel
- A2A agent cardNot found
- OAuth discoveryNot measured
- MCP discoveryNot found
- llms.txt validityPresent
Check results
Bot Accessibility
- ✓No error status codespass
- ✗Response timefail
- ✗XML sitemap existsfail
- ✓AI agent accesspass
- ?Edge treatment of agent user-agentstracked, not scorederror
- ✗robots.txt existsfail
- ✗Content negotiation (Markdown)fail
- —Declared AI usage preferencestracked, not scoredskip
Structured Data
- ✓OpenGraph meta tagspass
- ✓Semantic HTML elementspass
- ✗Appropriate Schema.org typefail
- —JSON-LD validskip
- ✗Heading hierarchyfail
- ✗Schema.org JSON-LD presentfail
- ✗Schema.org completenessfail
Content Quality
- ✗FAQ contentfail
- ✓Answer-first contentpass
- ✓Content lengthpass
- ✓Token efficiency (HTML-to-text ratio)pass
- ✗Freshness signalsfail
- ✗Author attributionfail
- ✓Citation readinesspass
- ✓Lists and tables for structured infopass
Agent Discovery
- ✓llms.txt follows specpass
- ✓llms.txt existspass
- —MCP server cardtracked, not scoredskip
- ✗Markdown alternate linksfail
- ✗/.well-known/agent-card.jsonfail
- ✓llms.txt links resolvepass
Agent Protocols
- ✗Discoverable API endpointsfail
- ✗MCP endpointfail
- ✗Action schemasfail
- —/.well-known/ucpskip
- ✗Structured formsfail
- —WebMCP imperative APItracked, not scoredskip
- —WebMCP declarative APItracked, not scoredskip
- ✗Reachable as Google-Agentfail
- ✓Reachable as ChatGPT-Userpass
- ✗Reachable as Perplexity-Userfail
Agent Auth
- —MCP authorization (401 challenge → protected resource metadata)skip
- ✗PKCE S256 supportfail
- ✗Public API surfacefail
- —Client ID Metadata Documents (bonus)skip
- —OpenAPI specificationskip
- ~Agent/bot auth documentationpartial
- —OAuth discovery chain (RFC 9728 → RFC 8414)skip
- ✓Developer portalpass
- ✗Scoped API permissionsfail
- —API catalog (RFC 9727)skip
- —Agent operator signing directorytracked, not scoredskip
Technical
- ✓HTTPSpass
- ✓UTF-8 charsetpass
- ✗Canonical URLsfail
- ✓Mobile viewportpass
- ✓Content accessible without JSpass
- ~Security headerspartial
Score history
- 40/100 · rubric v3.0
- 38/100 · rubric v3.0
- 38/100 · rubric v3.0
- 43/100 · rubric v2.0
- 43/100 · rubric v2.0
- 43/100 · rubric v2.0
- 43/100 · rubric v2.0
- 43/100 · rubric v2.0
- 43/100 · rubric v2.0