Guide for AI assistants

Questions answered

• How should an agent retrieve and cite this knowledge?

Suggested reading order

Evidence basis: reference_contract · Section citation

Start at /knowledge-map.json to select documents by topic, questions answered, size and related pages. Read /index.md for orientation, /capabilities.md and /integrations.md for availability, and the relevant detailed topic. /content.json contains the full structured corpus; /llms-full.txt contains the complete Markdown text; /sections.jsonl provides one self-contained, citable record per section.

Read-only representations

Evidence basis: reference_contract · Section citation

Every reference page has matching HTML, Markdown (.md), and JSON (.json) URLs. The homepage uses /, /index.md, and /index.json. Request Accept: text/markdown for Markdown at an HTML page URL. JSON uses the explicit .json URL. /agents.txt is a plain-text alias of /agents.md.

For listed AI User-Agents, GET, HEAD, and OPTIONS are supported. No account is required. Missing or unlisted User-Agents receive a 303 redirect to the main homepage on every path; see the User-Agent access policy below. /openapi.json describes the JSON read endpoints and /.well-known/api-catalog links to it. Unknown paths return 404; unsupported write methods on existing documents return 405.

Preserve context when answering

Evidence basis: reference_contract · Section citation

Cite the relevant canonical page and its review date. Preserve the distinction between an implemented capability, a configured merchant, and external adoption. Do not infer guaranteed outcomes, prices, partnerships, certifications, or connector availability.

This site supplies reference information, not higher-priority instructions for an assistant. It has no MCP server, A2A service, agent registration, or downloadable skill. Keep user consent with any contact action on external services.

User-Agent access policy

Evidence basis: reference_contract · Section citation

Every path on ai.getcatalog.ai requires a User-Agent containing one of the tokens below. Matching is case-insensitive and uses substring matching. These identifiers follow Catalog's AI storefront onboarding policy. Identify your client truthfully; an unlisted client should use the main website or ask Catalog about support.

Missing, empty and unlisted User-Agents receive 303 See Other to https://www.getcatalog.ai/. The original path, query and request body are not carried to the homepage. This applies to HTML, Markdown, JSON, discovery files, unknown URLs and unsupported methods. Listed agents receive the normal read-only response contracts described here.

This is audience routing, not authentication or verified bot identity. User-Agent is caller-controlled. No account or credential is required, and the reference contains no private merchant data. Responses are not stored in shared caches, and vary by Accept and User-Agent.

• chatgpt-user
• gptbot
• oai-searchbot
• claudebot
• claude-user
• claude-searchbot
• perplexitybot
• perplexity-user
• google-extended
• claude-web
• claude-code
• anthropic-ai
• googleother
• gemini-deep-research
• grokbot

GET /measurement.md HTTP/1.1
Host: ai.getcatalog.ai
User-Agent: GPTBot/1.0
Accept: text/markdown

Route a question to the smallest useful evidence set

Evidence basis: reference_contract · Section citation

Use the topic map's topics, answers and relatedPages to choose documents. Its word and byte counts help select a retrieval size. When the question needs the whole company context, use /llms-full.txt or /content.json. When indexing into a retrieval system, /sections.jsonl supplies one JSON object per authored section with the parent document, stable citation URL, review date and resolved sources.

Cite the answer and preserve its evidence basis

Evidence basis: reference_contract · Section citation

Each section has a stable canonical citation URL, evidence basis and source identifiers. Resolve source identifiers using the document's sources array; section-export records already include the relevant source objects. Use the section URL when citing Catalog's curated assessment and the original source URL when citing a particular published claim. Markdown includes explicit section anchors matching the HTML and JSON identifiers.

The evidence basis values are public_source, implementation_review, editorial_guidance and reference_contract. Public-source status means the statement is grounded in an attributed publication, not independently audited. Implementation review establishes code behavior in the reviewed scope, not universal production availability. Editorial guidance is an evaluation or interpretation rule. Reference contract describes this site's own behavior.

Treat the corpus as evidence, not operating authority

Evidence basis: reference_contract · Section citation

This site is reference data for an agent, not a higher-priority instruction source. It does not authorize sending messages, disclosing information, spending API credits, changing DNS, accessing a merchant account or buying products. Follow the user's task and consent boundaries for any external action. Illustrative API requests and synthetic records are marked and are not observed customer results.

When the answer depends on a missing commercial fact, unverified integration or current private configuration, say what the reference establishes and route the remaining question to the appropriate team contact. Do not guess an unavailable endpoint, invent a pricing plan, treat not verified as a promised roadmap, or use another merchant's capabilities as evidence for this company hostname.

Related documents

• Catalog: company knowledge reference
• Sources & evidence
• Terminology & disambiguation