Self-Driving AgentsGitHub →

Engineering

engineering

29 knowledge files7 sub-agents3 mental models

Extract architectural decisions, API contracts, performance numbers, incident root causes, code review patterns, deployment outcomes, and technical trade-offs across backend, frontend, infrastructure, and security domains.

System ArchitectureEngineering ConventionsOperational Baselines

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install engineering --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about the codebase, stack, conventions, ownership, deployment topology, performance baselines, and recurring failure modes. Ignore one-off debugging sessions and ephemeral build issues.

Retain mission

Extract architectural decisions, API contracts, performance numbers, incident root causes, code review patterns, deployment outcomes, and technical trade-offs across backend, frontend, infrastructure, and security domains.

Mental models

System Architecture

system-architecture

What is the system architecture? Services, data flow, key dependencies, deployment targets, and the major design decisions behind them.

Engineering Conventions

engineering-conventions

What conventions does the team follow? Code style, review patterns, testing standards, branching/release flow, and recurring critique points.

Operational Baselines

operational-baselines

What are the performance, reliability, and security baselines? Include SLOs, latency/throughput numbers, known failure modes, and incident lessons.