Delivery Brain

Augusta Labs

An agentic teammate for an engineering org.

A client system built with three teammates in about two weeks. It watches Azure DevOps boards and pull requests, raises evidence-backed delivery risks, lets an LLM triage them, and hands approved work to AI coding agents.

I owned the deterministic side — the risk detectors and the Inngest workflows that queue their signals for triage, plus the review queue and screens — and the graph context the agents plan with: a Neo4j graph of the org and a Qdrant-indexed graph of the code, refreshed every 30 minutes and exposed as read-only Mastra tools.

deterministic delivery-risk detectors
12
repositories in the code graph
7
graph refresh cycle
30 min

How it works

Detect & triage
  1. Azure DevOpswork items · PRs
  2. risk detectors12, deterministic
  3. Inngestdurable workflows
  4. LLM triagecreate · merge · ask
  5. human review
Ground the agents
    • org graphNeo4j
    • code graphQdrant · 7 repos
  2. graph context API
  3. agent toolsMastra, read-only
  4. coding agentplan → PR