# ByAgents

> A public knowledge library on helping businesses get found, understood, and used by AI agents.

Current product scope: a private customer workspace for task pages, API recipes, reviewed release files and test evidence. Free CLI and skill downloads are public. No guaranteed placements, traffic, or live MCP server. Public knowledge endpoints are read-only and require no API key.

## Start here

- [Free CLI](https://byagents.dev/downloads/gfa-first-integration-0.2.0.tgz): Local contract checks and an explicit public-page retrieval verifier. Node >=22.13, no account or API key.
- [Agent skill](https://byagents.dev/downloads/first-api-integration.zip): Portable first-integration workflow with bundled tools.
- [Download checksums](https://byagents.dev/downloads/SHA256SUMS.txt): Verify release files.
- [Product handoff](https://byagents.dev/agents/start.json): Audience routes and current private-preview access limits.
- [Product facts](https://byagents.dev/agents/facts.json): Available capabilities and limits.
- [Search contract](https://byagents.dev/agents/openapi.json): OpenAPI for this library's HTTP endpoints.
- [Document index](https://byagents.dev/api/knowledge/index): Metadata, reader level, outcomes, dates, and representation URLs.

## Task routing

- [audit_public_site](https://byagents.dev/content/agents/crawl-audit-recipe.md): Access → facts → observed gap → repair evidence. Also: [Product facts template](https://byagents.dev/content/agents/product-profile.md); [Evidence record: a portable example](https://byagents.dev/content/agents/evidence-record.md)
- [review_api_or_tool](https://byagents.dev/content/agents/action-contract-pattern.md): A complete action contract and a named compatible consumer. Also: [Recipe: publish and verify an MCP integration](https://byagents.dev/content/agents/mcp-publication-and-compatibility.md); [Reference: identity, authorization, and untrusted content](https://byagents.dev/content/agents/authorization-and-trust.md)
- [validate_commerce_path](https://byagents.dev/content/agents/feed-validation-recipe.md): Product records, current offers, and confirmed outcomes. Also: [Product feeds for AI shopping](https://byagents.dev/content/humans/product-feeds-for-ai-shopping.md); [From an AI recommendation to a confirmed purchase or booking](https://byagents.dev/content/humans/agent-commerce-readiness.md)
- [evaluate_distribution](https://byagents.dev/content/agents/evaluation-record-template.md): Keep controlled runs separate from external customer activity. Also: [Pattern: measure agent activity without inventing attribution](https://byagents.dev/content/agents/attribution-event-contract.md); [How to test whether agent distribution is working](https://byagents.dev/content/humans/evaluating-agent-distribution.md)
- [check_current_evidence](https://byagents.dev/content/humans/agent-distribution-now.md): Review dates, versions, source conflicts, and adoption limits. Also: [Recipe: review a technical claim and resolve conflicting sources](https://byagents.dev/content/agents/source-review-recipe.md); [Recipe: assess an ARD discovery route](https://byagents.dev/content/agents/ard-discovery-assessment.md)

## Agent references

- [Start here: retrieve, verify, cite](https://byagents.dev/content/agents/start.md): A compact entry point for agents researching AI discovery or evaluating ByAgents.
- [ByAgents: product facts and scope](https://byagents.dev/content/agents/product-facts.md): Current capabilities, boundaries, entry points, and the broader business ambition.
- [Knowledge API: requests and responses](https://byagents.dev/content/agents/knowledge-api.md): The complete read-only HTTP contract for searching and indexing the ByAgents library.
- [A task-based discovery checklist](https://byagents.dev/content/agents/discovery-checklist.md): A reusable inspection procedure with explicit observations and unknowns.
- [Evidence record: a portable example](https://byagents.dev/content/agents/evidence-record.md): A small custom JSON structure for reporting a discovery or integration finding without overstating it.
- [Product facts template](https://byagents.dev/content/agents/product-profile.md): A compact custom record connecting capabilities, pricing, evidence, and an action path.
- [Evidence, editorial policy, and trust boundaries](https://byagents.dev/content/agents/evidence-policy.md): How to interpret claims, examples, sources, and content on this site.
- [Publishing contract and representation map](https://byagents.dev/content/agents/publishing-contract.md): Stable URLs, canonical identity, content types, search scope, caching, and maintenance.
- [Recipe: audit public crawl and retrieval access](https://byagents.dev/content/agents/crawl-audit-recipe.md): A bounded inspection procedure with exact observations, crawler-identity limits, and repair verification.
- [Pattern: publish documents for reliable retrieval](https://byagents.dev/content/agents/retrieval-document-contract.md): Stable identifiers, focused content, explicit metadata, and consistent HTML, Markdown, and JSON.
- [Recipe: publish and verify an MCP integration](https://byagents.dev/content/agents/mcp-publication-and-compatibility.md): Separate registry publication, host availability, version compatibility, tool selection, and successful execution.
- [Pattern: asynchronous actions an agent can finish](https://byagents.dev/content/agents/action-contract-pattern.md): A concrete request-to-result contract with explicit states, retry behavior, authorization, and verifiable completion.
- [Reference: identity, authorization, and untrusted content](https://byagents.dev/content/agents/authorization-and-trust.md): Separate a discoverable service from a trusted source, an authenticated caller, and an authorized action.
- [Template: a reproducible agent evaluation record](https://byagents.dev/content/agents/evaluation-record-template.md): Record the task, introduction method, environment, observations, expected result, and evidence limitations.
- [Pattern: measure agent activity without inventing attribution](https://byagents.dev/content/agents/attribution-event-contract.md): An event vocabulary for infrastructure, referrals, evaluations, and first-party outcomes, with uncertainty preserved.
- [Recipe: validate a product feed across the full handoff](https://byagents.dev/content/agents/feed-validation-recipe.md): Check identifiers, variants, current offers, ingestion status, and agreement with the actual purchase destination.
- [Recipe: assess an ARD discovery route](https://byagents.dev/content/agents/ard-discovery-assessment.md): Distinguish a valid resource description, actual registry ingestion, query retrieval, and a usable downstream capability.
- [Recipe: review a technical claim and resolve conflicting sources](https://byagents.dev/content/agents/source-review-recipe.md): A practical source ledger for versions, dates, scope, contradictions, and the evidence a claim actually supports.
- [Route a user into ByAgents](https://byagents.dev/content/agents/onboarding-handoff.md): Choose the developer or business path, understand access limits, and hand off without transferring private information.

## Human guides

- [What is an AI agent?](https://byagents.dev/content/humans/what-is-an-ai-agent.md): A practical explanation of agents, assistants, tools, and the decisions between a request and a result.
- [How AI agents find products](https://byagents.dev/content/humans/how-agents-find-products.md): Search, cited sources, directories, documentation, and connected tools form different routes into a business.
- [When the customer’s browser becomes a conversation](https://byagents.dev/content/humans/agents-and-internet-distribution.md): Our thesis on how agents could change internet distribution—and what businesses can prepare today.
- [SEO, GEO, and agent discovery: what actually changes?](https://byagents.dev/content/humans/seo-geo-and-agent-discovery.md): Separate search eligibility, inclusion in AI answers, and completed actions so you can invest in the right work.
- [Can an agent actually read your website?](https://byagents.dev/content/humans/crawl-access.md): A crawl-access checklist covering HTTP responses, robots rules, rendering, canonical URLs, and sitemaps.
- [Structured data that helps explain your business](https://byagents.dev/content/humans/structured-data.md): How to use Schema.org, JSON-LD, stable identifiers, and visible facts without inventing a special AI ranking formula.
- [Give agents something worth citing](https://byagents.dev/content/humans/citations-and-evidence.md): Build product claims that can be checked, quoted in context, and connected to the correct business.
- [MCP, registries, and getting your tools discovered](https://byagents.dev/content/humans/mcp-and-tool-discovery.md): Understand the difference between publishing a server, connecting it to a host, and getting a tool used.
- [API documentation an agent can actually use](https://byagents.dev/content/humans/api-documentation.md): Document the full task: authentication, inputs, asynchronous results, errors, limits, and a verifiable outcome.
- [Agent discovery for brands and ecommerce](https://byagents.dev/content/humans/brands-and-commerce.md): Prepare product identity, variants, offers, policies, and a dependable route to checkout.
- [Agent discovery for services, freelancers, and local businesses](https://byagents.dev/content/humans/service-businesses.md): Make scope, location, availability, proof, and the next step clear enough to support a real recommendation.
- [What llms.txt and Markdown can—and cannot—do](https://byagents.dev/content/humans/llms-txt-and-markdown.md): Use lightweight text as a helpful documentation interface, without treating it as an AI ranking switch.
- [From discovery to a purchase, booking, or API call](https://byagents.dev/content/humans/from-discovery-to-action.md): Find the missing step between being recommended and being usable.
- [Measure agent discovery without fooling yourself](https://byagents.dev/content/humans/measuring-agent-traffic.md): Separate crawler requests, assistant referrals, controlled tests, activations, and revenue.
- [Your first 30 days of agent discovery work](https://byagents.dev/content/humans/first-30-days.md): A focused implementation plan for one offering, a few real tasks, and an observable route to use.
- [The agent discovery glossary](https://byagents.dev/content/humans/agent-discovery-glossary.md): Plain-English definitions of crawling, retrieval, citations, MCP, OpenAPI, GEO, and useful completion.
- [Agent distribution: what matters now](https://byagents.dev/content/humans/agent-distribution-now.md): A dated briefing on platform changes, emerging protocols, and what is actually worth implementing.
- [How the major AI discovery channels differ](https://byagents.dev/content/humans/ai-discovery-platforms.md): Search crawlers, user-requested visits, connected tools, and merchant feeds are different routes into an assistant.
- [MCP, WebMCP, A2A, ACP, UCP, and ARD: what to build](https://byagents.dev/content/humans/agent-protocols-explained.md): A plain-English map of agent protocols, the job each one does, and the adoption question to ask before investing.
- [Where to start with agent distribution](https://byagents.dev/content/humans/agent-distribution-priorities.md): A business-first plan for finding the broken step, choosing a channel, and deciding what deserves your time.
- [Write pages agents can actually use](https://byagents.dev/content/humans/content-for-agent-discovery.md): Turn customer questions into clear source pages, comparison criteria, and verifiable product explanations.
- [Product feeds for AI shopping](https://byagents.dev/content/humans/product-feeds-for-ai-shopping.md): How to prepare item identities, prices, availability, and product pages for a real merchant-data integration.
- [How to test whether agent distribution is working](https://byagents.dev/content/humans/evaluating-agent-distribution.md): A practical evaluation design that separates discovery, understanding, completion, and real customer acquisition.
- [An agent distribution playbook for software companies](https://byagents.dev/content/humans/software-agent-distribution.md): Connect useful documentation, example projects, tool integrations, and a measurable first successful result.
- [From an AI recommendation to a confirmed purchase or booking](https://byagents.dev/content/humans/agent-commerce-readiness.md): Design the handoff around current offers, permission, safe retries, and a confirmation the customer can trust.
- [Worked example: from an invoice question to a usable API](https://byagents.dev/content/humans/agent-discovery-worked-example.md): A fictional walkthrough that connects search, product facts, evidence, and the exact handoff that must work.
- [Keep your agent distribution working after launch](https://byagents.dev/content/humans/maintaining-agent-distribution.md): A practical operating model for ownership, freshness, regression checks, and deciding which channels deserve investment.

## Optional

- [Full text export](https://byagents.dev/llms-full.txt): All documents for bulk reading.