Skip to content

Repository files navigation

Agent Integration Playbook

A free, vendor-neutral reference on giving AI agents access to real systems — Gmail, Slack, GitHub, Google Drive, Notion, PostgreSQL, MCP servers — without leaking credentials or granting more than the job needs. Eighteen guides, no gate, no signup.

Read it at agenticfabriq.github.io.

It is written for engineers shipping agents into production at companies that have to answer who did what, on whose behalf, and with what permission. Each guide is one path start to finish: what breaks without the control, runnable code, a decision table of the options genuinely on the table, a checklist you can paste into a pull request, and the failure modes with the symptom first. External claims link the vendor's own page, an RFC, or a standards document rather than a secondary source that restates them.

The library splits three ways, by when you need the answer rather than by topic. Connect is before the grant exists. Govern is the policy layer that stops you re-deciding the same thing per provider. Fail is after it is live and something is wrong. Each pillar has a cornerstone guide carrying the whole argument; the topic guides underneath it are reference.

Prose is CC BY 4.0. Code is Apache-2.0. Maintained by Agentic Fabriq.

Connect

Giving an agent real access to the systems your team already uses: which permission it needs against this provider, how it gets one, and what the provider hands over that you did not ask for.

Govern

Identity, permissions, credentials, and audit — the decisions you make once and apply everywhere, rather than re-arguing them per provider.

Fail

What breaks in production, read backwards from the symptom: how to see it coming, how to tell which failure you are looking at, and what contains it.

Runnable examples

Every non-trivial code path has a runnable file under examples/, referenced from its guide by path. They are checked on every commit: they compile, their imports resolve, and anything touching the Agentic Fabriq SDK is validated against the published surface, so a sample cannot drift into calling something that does not exist.

Contributing

Corrections are the most useful contribution. If a scope name changed, a quota moved, or a guide states more than its cited page states, open an issue or a pull request. Read CONTRIBUTING.md for the content standards every guide is held to.

The three guide lists above sit between BEGIN GENERATED and END GENERATED markers and are produced from the frontmatter in src/content/guides/. Do not edit them by hand: change the guide, run npm run readme, and commit the result. npm run verify fails if they disagree, so a retitled guide cannot leave a stale index behind. The social cards under public/og/ work the same way — npm run og redraws them, and npm run verify fails when they no longer match the titles they picture.

Local development

npm install
npm run dev      # local server
npm run og       # redraw the social cards in public/og/ from the frontmatter
npm run readme   # regenerate the guide index in this file from the frontmatter
npm run verify   # build, tests, lint, link check, og and readme checks, sample check

About

Open playbook for connecting AI agents to real systems: tool integrations, OAuth and agent identity, least-privilege scopes, credential vaulting, audit trails, and production failure modes.

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages