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.
Within AI Coding Agents
AI Coding Agents
Testing
Accessibility testing with coding agents
Accessibility testing with coding agents combines deterministic scans, keyboard flows, semantic inspection, and human review. Build useful evidence into every UI change.
Read articleEnterprise AI
AI Coding Agents
Agent readiness can cut repeated token work
Agent readiness exposes avoidable setup, search, and validation work. Connect repository improvements to token efficiency without inventing a savings benchmark.
Read articleAI Coding Agents
API Development
Protecting API compatibility with coding agents
API compatibility checks help coding agents change services without surprising consumers. Compare contracts, trace callers, and validate old and new behavior.
Read articleAI Coding Agents
Enterprise AI
Model routing has to account for the warm cache
Model routing can lose its price advantage when a switch discards cached context. Factory’s research explains why task state belongs in the decision.
Read articleAI Coding Agents
Governance
Audit trails for coding agent changes
A coding agent audit trail connects identity, intent, tool activity, validation, review, and deployment. Learn what evidence to retain without collecting unnecessary data.
Read articleAI Coding Agents
Enterprise AI
Context compaction must preserve the next step
Context compaction should preserve decisions and file state, not just shrink a transcript. Factory’s published study shows what to test after a long coding session.
Read articleAI Coding Agents
Platform Engineering
Safer database migrations with coding agents
Database migrations with coding agents need staged schema changes, compatibility tests, rollback evidence, and human approval without hiding operational risk.
Read articleAI Coding Agents
Software Supply Chain
Safer dependency updates with coding agents
AI dependency updates need more than a version bump. Scope compatibility work, inspect transitive changes, run focused tests, and keep every update reviewable.
Read articleAI Coding Agents
Maintenance
Removing stale feature flags with coding agents
Feature flag cleanup is a cross-cutting maintenance task. Learn how coding agents can prove a flag is stale, remove both branches, and validate the resulting behavior.
Read articleAI Coding Agents
Observability
Coding agent observability that reviewers can verify
Coding agent observability work needs stable signal names, bounded cardinality, and behavioral evidence. Learn how to review instrumentation changes.
Read articleAI Coding Agents
Engineering Management
Coding agent task specifications that work
A coding agent task specification needs a bounded outcome, repository context, acceptance criteria, and verification steps. Use this practical structure for delegated work.
Read articleAI Coding Agents
Developer Experience
Coding agents in monorepos, with clear boundaries
AI coding agents in monorepos need explicit package boundaries, local instructions, dependency graphs, and affected tests. Make large repositories easier to change safely.
Read article
