Code Factory 0.44.1: current UI, First Proof, and a transparent 60-day use case

I built Code Factory for myself. Now I’m sharing it with the world.

AI made code generation dramatically faster, but generating code was never the whole job. I still needed to understand what changed, catch incomplete work, preserve evidence, and know what was actually safe to accept.

Code Factory 0.44.1 updates the public product surfaces and brings the current workflow into focus. First Proof runs a sealed positive control and an intentionally hollow negative control. If the broken path still passes, Code Factory reports HOLLOW_E2E_TEST instead of calling the run proven.

Expected outcomes:

• Vibe coders: less time reconstructing context and fewer false “done” states.

• Engineers: reviewable diffs, tests, receipts, and explicit next-proof steps.

• Teams: repeatable handoffs with less review and rework friction.

• Enterprises: local-first evidence, bounded workflows, and human-controlled promotion.

One transparent 60-day personal-use case observed 25 related tasks, 133 completed turns, 2,710 command runs, 785 MCP or app calls, and 555 file-change events. A separate counterfactual model estimates 30–110 gross manual-equivalent hours over 60 days after a 50% overlap haircut—about 15–55 hours per month. At an illustrative loaded rate of $75–$150/hour, modeled gross capacity value is $2,250–$16,500.

This is one user’s case, not a benchmark, guaranteed ROI, or verified cash saving. Net savings must subtract tool cost and human oversight. I’m publishing the assumptions and the visual so other builders can inspect, challenge, or replace the model.

GitHub: https://github.com/zrk222/code-factory

JetBrains: https://plugins.jetbrains.com/plugin/33009-factoryline-ai-proof