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 Enterprise AI
Modernization
Enterprise AI

Java modernization with OpenRewrite works as a loop. Recipes make the mechanical changes, Droids repair what the recipes leave and write new ones, and the compiler, tests, and a clean dry run verify every step. How to set it up with Factory.
Read articleModernization
Enterprise AI

.NET modernization with Roslyn pairs analyzers, code fixes, and dotnet format with Droids that handle what no code fix covers. How to move .NET Framework and older .NET code to .NET 10 with deterministic checks on every step, using Factory.
Read articleModernization
Enterprise AI

A Ruby and Rails upgrade goes one minor version at a time. RuboCop, bin/rails app:update, dual boot, and Synvert handle the mechanical changes, deprecation warnings become the work list, and Factory Droids fix the residue under the same deterministic checks.
Read articleModernization
Enterprise AI

PHP modernization works best when Rector performs the mechanical upgrade, PHPStan and the test suite gate every step, and Factory Droids handle the residue and write new Rector rules. A practical setup with hooks, skills, and Droid Exec.
Read articleAI Coding Agents
Enterprise AI

Evaluate fast inference for coding agents across providers and gateways. Compare response latency, model compatibility, cost, and time to a validated result.
Read articleModernization
Enterprise AI

COBOL modernization works when every step is checked by something deterministic. Compile with GnuCOBOL, inventory with a real parser, capture golden files from batch inputs, and let Droids handle the residue that translation tools leave behind.
Read articleFactory Private
Enterprise AI
Self-hosted AI agents put the control plane, session data, models, and updates under your team. Compare those responsibilities with a managed deployment first.
Read articleFactory Private
Data Governance

AI agent telemetry should answer an operational question without collecting unnecessary code. Choose metrics, identity detail, and content export deliberately.
Read articleAI Coding Agents
Enterprise AI
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 articleComparisons
Enterprise AI

Factory vs Devin compared. See how Droid vs Devin differ on delegated work, CI, model choice, data flows, retention, and private or airgapped deployment.
Read articleEnterprise AI
Guides

Use agent readiness to find the repositories blocking an AI rollout, prioritize fixes, and measure progress with Factory’s reports and dashboard.
Read articleFactory Private
Enterprise AI

On-prem AI development needs more than a local agent. Place the control plane, model endpoint, build tools, and telemetry inside the approved boundary.
Read articleStart building