Back to system map
PROJECT / 11

SENTINEL - Autonomous Site Reliability Engineer

An agentic-SRE system that investigates production alerts on its own with real tool calls, proposes exact remediations grounded in runbook RAG, and executes only after a human approves.

SYSTEM BUILD

What went into it

  1. 01

    Runs a bounded agent loop with JSON-schema tools — fetch logs, pull metrics, search runbooks — that must converge on a schema-validated proposal or the incident is honestly marked failed.

  2. 02

    Passes every remediation through a static safety analyzer with 12 hard-block rules before it reaches the human approval gate; execution is simulate-by-default with an audited strict mode.

  3. 03

    Retrieves from a heading-weighted BM25 + tf-idf knowledge base of runbooks and post-mortems, citing documents on every proposal with a confidence score and rollback plan.

  4. 04

    Pairs the agent with a simulated fleet of 8 services and 8 fault scenarios with ground truth, so the entire investigate → approve → execute loop demos safely offline.

MEASURED OUTPUT

What changed

Kept a human unconditionally in the loop — the agent's only write is a proposal, and safety-blocked scripts never reach the approval queue.

Backed by 38 Vitest/Supertest tests and 6 Playwright E2E specs across the API and console.

Next systemSIMULACRA - Synthetic Data Generation Pipeline