docs.lightning.engineering agentic web readiness

A+ Manifest validity: 71% (5/7 valid, 3 errors, 6 warnings) · Surface score 60 (coverage 40 + breadth 15 + conformance 5). 9 standards observed across 4 of 9 steps; 7 manifests present, 3 errors, 6 warnings. Checked 2026-10-23 17:33:47 UTC. This grades the agent-facing files published at docs.lightning.engineering, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/docs.lightning.engineering.svg) · JSON · Markdown · Re-check now

Coverage by step

01 DiscoverAI Catalog well-known file, agents.txt 02 Identifynothing observed 03 PermitContent Signals Policy 04 Readllms.txt, AGENTS.md, Markdown for Agents 05 Act 06 Coordinatenothing observed 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	absent HTTP 404
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid	entries[0] has no description; registries index on it no entry has representativeQueries; ARD registries use 2-5 example queries to index entries host block missing (displayName, identifier, documentationUrl help clients name the publisher)
MCP Server Cards (SEP-2127) `/.well-known/mcp/server-card.json`	valid	tools/resources/prompts listed in the card; SEP-2127 excludes primitives (list them live, or under a namespaced _meta key)
Agent2Agent Protocol `/.well-known/agent-card.json`	absent HTTP 404
llms.txt `/llms.txt`	valid	no blockquote summary under the title
AGENTS.md `/AGENTS.md`	valid
Agent Skills `/.well-known/agent-skills/index.json`	absent HTTP 404
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	absent HTTP 404
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	valid	no Agentmap: line (optional convention pointing agents at /.well-known/ard.json)
security.txt (RFC 9116) `/.well-known/security.txt`	absent HTTP 404
auth.md `/auth.md`	errors	none of the auth.md mechanism names found (identity_assertion, service_auth, anonymous)
Open Knowledge Format `/okf/index.md`	errors	missing YAML frontmatter block (--- ... ---) missing okf_version (0.1 or 0.2) in frontmatter (OKF §8)

What an agent can call

MCP endpoint https://docs.lightning.engineering/~gitbook/mcp (streamable-http), tools: searchDocumentation, getPage, askQuestion, sendFeedback — from /.well-known/mcp/server-card.json
MCP endpoint https://docs.lightning.engineering/~gitbook/mcp (streamable-http), tools: searchDocumentation, getPage, askQuestion, sendFeedback — from /~gitbook/mcp/server-card
llms.txt: Builder's Guide, 164 links, llms-full.txt present
OKF bundle (/okf/index.md): Page Not Found, 5 concept links
robots.txt AI policy: unlisted crawlers allowed

Standards observed

llms.txt https://docs.lightning.engineering/llms.txt
AGENTS.md https://docs.lightning.engineering/AGENTS.md
Content Signals Policy https://docs.lightning.engineering/robots.txt
AI Catalog well-known file https://docs.lightning.engineering/.well-known/ai-catalog.json
agents.txt https://docs.lightning.engineering/agents.txt
Markdown for Agents https://docs.lightning.engineering/
MCP Server Cards (SEP-2127)
Model Context Protocol
AI Crawler User-Agent Tokens in robots.txt

Cheapest next steps

Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description
security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback llms_txt). Call the MCP endpoint at https://docs.lightning.engineering/~gitbook/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://docs.lightning.engineering/~gitbook/mcp POST a JSON-RPC tools/list, or server/discover on the 2026-07-28 revision, before reading HTML.

Practical readability: exa_parsable yes, markdown negotiation yes, render markdown_native, HTML quality high, first content at byte 0.

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

Readiness subscores: reach 20/20, readability 30/30, capabilities 21/35, conformance 5/15, total 76/100, grade A.

How the grade is made

+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. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules