# inline Docs > An autonomous agent that reviews every pull request, guards the merge, and watches your code, CI, cloud, and compliance — all from one portal. inline is an autonomous software-assurance platform powered by Claude. Its core is a GitHub pull-request review agent: on every PR it runs a cost-optimized pipeline (path filters → incremental diff → a fast model triages → a frontier model reviews substantive changes → a validation gate → a posted GitHub review) and can gate the merge. Around that core it adds a feedback loop that learns from accepted and dismissed findings, a code graph for whole-repo reasoning, sandboxed and verified auto-fix PRs, and a suite of monitors — repository security (Sentinel), CI/CD health (Actions), cloud posture (Cloud), BAA/vendor compliance, and autonomous penetration testing (Pentest). Teams drive it from an admin portal, on the pull request via @inline commands, and — for pre-PR review inside coding agents — over an authenticated MCP server. This file indexes the documentation for LLMs and AI agents; each link points to a clean Markdown version of a page. ## Get started - [Introduction](https://inline.dev/docs/index.md): inline is an autonomous agent that reviews every pull request, guards the merge, and monitors your code, CI, cloud, and compliance — from one portal. - [Quickstart](https://inline.dev/docs/quickstart.md): Connect a repository and get your first automated review — from sign-in to a posted GitHub review in a few minutes. - [Core concepts](https://inline.dev/docs/concepts.md): The vocabulary of inline — organizations, connections, repos, reviews, findings, jobs, and the modules built on top. - [Architecture](https://inline.dev/docs/architecture.md): How inline is shaped — a GitHub App, an admin portal, an always-on background reviewer, an MCP server, and Claude, with your data in your own cloud. ## Code review - [The review pipeline](https://inline.dev/docs/review-pipeline.md): The full path a pull request takes through inline — from a verified webhook to a posted GitHub review — stage by stage. - [Cost & two-tier models](https://inline.dev/docs/review-cost.md): How inline holds the blended cost of a review to a few cents — path filters, incremental diffs, prompt caching, diff compression, and two model tiers. - [Noise control](https://inline.dev/docs/review-noise.md): The validation gate — confidence floor, severity threshold, dedup fingerprints, line anchoring, and the comment cap — that keeps inline quiet and trusted. - [The merge gate](https://inline.dev/docs/merge-gate.md): The inline / review check run that can block a merge while open findings remain — off, report-only, or block by severity — and how a finding clears. - [Repository memory](https://inline.dev/docs/repo-memory.md): The per-repo profile inline distills from its own reviews and re-reads on every review — durable architecture, conventions, fragile areas, and gotchas. - [The feedback loop](https://inline.dev/docs/feedback-loop.md): How inline learns from accepted, dismissed, resolved, and reacted-to findings — harvesting signals on PR close and proposing suppression rules for patterns your team rejects. - [Learnings & skills](https://inline.dev/docs/learnings.md): Two ways to teach inline — short taught rules (learnings) and authored expertise packs (skills), both folded into the review with progressive disclosure. - [Code graph](https://inline.dev/docs/codegraph.md): Commit-anchored code-graph indexes that let the reviewer answer exact structural questions — who calls this, what's the blast radius — plus a 3D graph explorer. - [Conversations](https://inline.dev/docs/conversations.md): Talk to inline from a PR comment — ask questions, force a review, teach a rule, or resolve a thread — with every interaction logged in the portal. - [Configuring reviews](https://inline.dev/docs/review-config.md): Every review setting — workspace defaults and per-repo overrides — for severity, identity, instructions, path filters, budget, and the optional modules. ## Automation - [Auto-fix PRs](https://inline.dev/docs/auto-fix.md): inline can open a stacked fix-PR that patches a review finding and verifies the patch in a sandbox before you ever see it. - [The sandbox](https://inline.dev/docs/sandbox.md): Ephemeral microVMs where inline runs and authors tests, boots your app for browser e2e, and verifies fixes — with video and screenshot evidence. - [Walkthroughs](https://inline.dev/docs/walkthrough.md): A hosted, layered diff viewer built for each PR — ordered change cohorts, Mermaid diagrams, visual recaps, and an "Ask inline" chat, shareable by link. - [MCP: pre-PR review](https://inline.dev/docs/mcp.md): Review your changes before you open a PR — inline exposes an authenticated MCP server so coding agents like Claude Code can request a review of the working tree. ## Security & monitoring - [Sentinel: repo security](https://inline.dev/docs/sentinel.md): Continuous dependency and supply-chain security monitoring — vulnerability range-matching, malicious-package detection, agentic confirmation, and GitHub-native alert ingestion. - [Security auto-fix](https://inline.dev/docs/security-autofix.md): Turn a confirmed Sentinel alert into a verified remediation PR — deterministic dependency bumps or an agentic patch, verified in a sandbox, on a convention-matched branch. - [Pentest: red-teaming](https://inline.dev/docs/pentest.md): Autonomous offensive-security agents attack a repository's own code in an isolated sandbox, prove exploitability with non-destructive PoCs, and surface only validated findings. - [Actions: CI/CD monitoring](https://inline.dev/docs/actions.md): Watch GitHub Actions runs — AI-triaged failures with root cause and suggested fix, flaky-test detection, and duration-regression alerts. - [Cloud monitoring](https://inline.dev/docs/cloud.md): Provider-agnostic cloud posture, health, and spend monitoring for Azure — collectors over ARM REST, AI-triaged findings, and zero stored customer secrets. - [Observability](https://inline.dev/docs/observability.md): Runtime error monitoring — wrap any app in the inline SDK (or post the open envelope from any language), get grouped, symbolicated issues with AI root-cause analysis against the commit that shipped the bug. - [Observability protocol](https://inline.dev/docs/observability-protocol.md): The open JSON envelope inline's error ingest accepts — every field, every default, and what a minimal client has to send. - [Compliance](https://inline.dev/docs/compliance.md): Track BAA and vendor-agreement coverage — detect which third-party providers your code sends data to, and whether a signed agreement covers that exposure. ## Platform - [Connecting GitHub](https://inline.dev/docs/connect-github.md): The two ways inline connects to GitHub — the org-wide GitHub App or per-admin OAuth — and how to choose between them. - [Organizations & teams](https://inline.dev/docs/organizations.md): How inline separates work into organizations (workspaces) — the tenancy boundary for connections, repos, reviews, settings, and billing. - [Roles & permissions](https://inline.dev/docs/permissions.md): How inline governs who can do what — organization roles (Owner, Admin, Member) and the restricted developer role scoped to their own PRs. - [Members & invites](https://inline.dev/docs/members-invites.md): Add teammates to an organization by email invite, assign a role, and link a GitHub account so inline can attribute pull requests. - [Notifications](https://inline.dev/docs/notifications.md): Get inline's alerts where your team already works — Microsoft Teams channels and email — with per-category routing. - [Settings reference](https://inline.dev/docs/settings.md): A map of every settings surface in the inline portal — where each control lives and what it governs. ## Reference - [Security & trust](https://inline.dev/docs/security-trust.md): How inline handles your code and credentials — least-privilege access, sandbox isolation, enforced safety on offensive tooling, and human-in-the-loop control. - [Privacy policy](https://inline.dev/docs/privacy.md): What information inline collects, how it is used and shared, how long it is kept, and how to contact us. - [Glossary](https://inline.dev/docs/glossary.md): The vocabulary of inline, defined in one place. - [For AI agents (llms.txt)](https://inline.dev/docs/ai-native.md): These docs are built to be read by LLMs and coding agents, not just humans — with clean Markdown endpoints and an llms.txt index.