# AI-SDLC guides
Source: https://ai-sdlc.io/guides

Every AI-SDLC guide in one place: what an AI SDLC is phase by phase, how to evaluate an autonomous SDLC framework, how model routing bounds cost, and four buyer guides on trust, compliance, autonomy and adoption.

Practical guides for teams evaluating and adopting AI-SDLC. Each guide answers one decision question and links the documentation, specification or white paper behind every claim.

- [What is an AI SDLC? Running the software lifecycle with agents, phase by phase](https://ai-sdlc.io/guides/what-is-ai-sdlc): What an AI SDLC (AI-native or agentic SDLC) is, how each of the eight lifecycle phases changes when agents do the work, and where governance, autonomy levels and audit evidence fit. (last modified 2026-11-17)
- [Why can't teams trust AI-written code yet?](https://ai-sdlc.io/guides/trusting-ai-written-code): Why review cannot keep up with agent output, and how AI-SDLC moves the human decision to the start of the work and proves the review ran. (last modified 2026-11-17)
- [What does compliance by design mean?](https://ai-sdlc.io/guides/compliance-by-design): How AI-SDLC derives gate defaults, attestation and retention from a declared compliance posture, and maps to the EU AI Act, NIST AI RMF and ISO 42001. (last modified 2026-11-17)
- [How much autonomy does an AI-SDLC agent get?](https://ai-sdlc.io/guides/agent-autonomy-levels): The four AI-SDLC autonomy levels, how an agent earns promotion, what demotes it, and how cost and readiness gates bound it at every level. (last modified 2026-11-17)
- [How do you get started with AI-SDLC?](https://ai-sdlc.io/guides/adopting-ai-sdlc): A staged path to adopting AI-SDLC: read the primer, run the getting-started guide on one repository, then decide whether paid help is worth it. (last modified 2026-11-17)
- [How to evaluate an autonomous SDLC framework](https://ai-sdlc.io/guides/evaluate-autonomous-sdlc-framework): Seven questions, each mapped to a public standard (DORA, NIST SSDF, SLSA, OWASP), with a scoring table for comparing autonomous SDLC frameworks. (last modified 2026-10-20)
- [Model routing cost: how AI-SDLC bounds LLM spend](https://ai-sdlc.io/guides/model-routing-cost): How routing cheap models to review probes and strong models to development, plus per-task and monthly budget caps, bounds LLM spend, with a worked end-to-end task cost. (last modified 2026-10-20)
