Autonomous incident remediation,
in single-digit minutes.
For production crashes, Remediate Labs diagnoses the root cause, generates a fix, and opens a PR — automatically, in minutes. For everything else, it surfaces errors with root-cause context so your team decides what gets fixed next. Built with the Anthropic SDK on FastAPI + Postgres + pgvector.
Agent pipeline
~6 min
from detected event to fix-PR
Avg MTTR
38 min
detection to merged fix
CI pass rate
100%
sandbox passes on first run
Numbers refresh from scripts/measure_mttr.py against the live demo DB.
See the methodology for how each is computed.
How it works
Architecture deep-dive →01
Detect
CloudWatch alarms fire on production errors and POST to a webhook. Push-based — no polling load on the production server.
02
Triage
Haiku-class classifier filters real incidents from noise and duplicates. Ground truth from a 100-case golden dataset.
03
Diagnose
Diagnosis agent grounds every claim against the actual repo via GitHub Code Search. No fabricated function names.
04
Fix
Fix-generation agent writes a patch, runs it in a Docker sandbox against the real test suite, retries up to 3× on failure.
05
Approve
HIGH/CRITICAL actions queue for human approval before merging. Approvals also feed an RLHF preference dataset.
Recent writing
All posts →We Built a Call Graph Because Our Agent Kept Breaking Callers It Never Knew About
The agent found one caller via GitHub search, patched it, and shipped. Two other callers broke in production. The fix was correct. The picture was incomplete.
Five Data Structures for a Call Graph — Why We Chose Hash Map of Sets
The adjacency matrix sounds clever. It's wrong for sparse graphs. The edge list is right for serialization and wrong for queries. Here's what each actually costs.
Cross-Encoder Re-Ranking — From Top-3 to Rank 1
The vocabulary gap query is at rank 3. Five functions have identical lexical scores — vector can't break the tie. Cross-encoder re-ranking sees query and document together and pushes the correct function to rank 1.