AI agents should not just generate code.
They should produce evidence.
That is the core idea behind Agile V:
→ Requirements before implementation
→ Independent verification
→ Traceability from intent to test
→ Human gates before release
→ Evidence bundles instead of after-the-fact documentation
Explore the projects
agile-v-skills
Agent skills for traceable requirements, independent Red Team verification, human gates, and compliance-ready evidence.
→ github.com/Agile-V/agile_v_skills
agentic-agile-v
A practical scaffold for running AI engineering with structured briefs, evidence bundles, validation gates, and risk-based workflows.
→ github.com/Agile-V/agentic_agile_v
From vibe coding to verified engineering.
Top comments (1)
evidence-not-just-code is the unlock. tangentially related to verified engineering: making the gen layer itself reliable is a different but adjacent problem. been baking that into moonshift - failure classifier (transient/deterministic/permanent), per-phase retry caps, event log per turn. $3 per shipped saas, code lands in ur own gh + vercel. first run completely free if u want to see what a verified-by-default gen pipeline looks like from the outside.