The agent-native software factory
Guides on building, governing, and scaling an agent-native software factory, plus write-ups of the podcasts and talks behind the ideas.
Guides on building, governing, and scaling an agent-native software factory, plus write-ups of the podcasts and talks behind the ideas.
Within AI Coding Agents
AI Coding Agents
Maintenance

Feature flag cleanup requires proof that a flag is stale. Coding agents can remove the obsolete branch and evaluation call while testing the permanent behavior.
Read articleAI Coding Agents
Developer Tools

API client generation should start from a reviewed OpenAPI contract, use a pinned generator, prove the output is reproducible, and compile real consumers before release. Learn the workflow for agent-run regeneration with Factory Droid Exec and review.
Read articleAI Coding Agents
Performance
Performance regression review compares a branch with its merge base under the same workload, budget, and environment. Learn how to set baselines, measure variance, and use Factory code review and Droid Exec to make findings reproducible.
Read articleAI Coding Agents
Security

Container image hardening works best one finding at a time. Learn how to scope an agent task from a scanner result, rebuild and scan the new digest, run the production entrypoint, and review the change with Factory Droid Exec and security review.
Read articleAI Coding Agents
Platform Engineering

Reproducible environments for coding agents make failures diagnosable and results comparable. Pin tools, preserve commands, isolate changes, and capture evidence.
Read articleAI Coding Agents
Guides

Select Kimi K2.5 in Factory while it remains available, check its deprecated status and credit multiplier, and configure reasoning for scoped coding tasks.
Read articleAI Coding Agents
Testing

Test impact analysis helps coding agents select fast checks without missing affected behavior. Learn how to combine dependency data with risk-based validation.
Read articleAI Coding Agents
Observability

Coding agent observability work needs stable signal names, bounded cardinality, and behavioral evidence. Learn how to review instrumentation changes.
Read articleAI Coding Agents
Testing

Test fixture maintenance with coding agents can remove hidden dependencies, reduce setup cost, and preserve the behavior each test proves.
Read articleAI Coding Agents
Reliability

Retry safety means a retried call cannot duplicate side effects or multiply load. Review idempotency, retry ownership, backoff, and deadlines in agent code.
Read articleAI Coding Agents
Reliability

Queue consumer safety depends on idempotent side effects, a correct acknowledgment point, bounded retries, and dead-letter handling. Learn the failure-injection tests to require on agent-written consumers and how Factory Missions validate them.
Read articleAI Coding Agents
Testing
Accessibility testing with coding agents combines deterministic scans, keyboard flows, semantic inspection, and human review. Build useful evidence into every UI change.
Read articleStart building