Guide
AI engineering implementation practice map
A practical guide to AI engineering around BMAD, Speckit, and spec-driven development.
This guide focuses on how AI can enter the real software engineering process, rather than staying at the level of scattered prompt words.
focus
- BMAD workflow
- Speckit specification-driven development
- Task splitting and auditing
- Delivery and verification closed loop
How to use this guide
Read this guide as an implementation map rather than a tool catalog. First identify which part of the delivery process is unstable: requirements, task slicing, implementation drift, review, or acceptance evidence. Then map that instability to the corresponding workflow boundary so the team can add the smallest useful contract, gate, or review artifact.
Related reading
The quantitative trading AI engineering chapter shows how specification-driven delivery is used in a real project. The AI Coding Mentor series explains how task design and feedback loops become evaluation assets. The platform-upgrade path series shows how these practices fit into a broader content and engineering system.
Reading path
Continue in AI engineering practice
Technical Interpretation Index | Curated Translations
Original technical interpretation and selected articles from foreign technology communities to explore best practices in AI engineering
Original interpretation: Discovery and prevention of silent hallucination in RAG system
Based on an in-depth analysis of RAG system failure cases in the production environment, we explore the nature of the silent illusion problem, monitoring blind spots, and architectural-level solutions.
Original interpretation: How AI Agent implements large-scale testing quality access control
Practical analysis of AI testing agent based on Node.js project scaffolding, and explore the implementation ideas of automated quality access control
AI engineering implementation practice map
A practical guide to AI engineering around BMAD, Speckit, and spec-driven development.