Agentic-Agile: Why Agent Development Needs Agile (Not Just Prompts)
The article discusses the challenges of prompt-driven development in software engineering and introduces the concept of Agentic-Agile development. This new methodology aims to improve collaboration between human developers and AI agents by emphasizing structured processes and continuous improvement. The author shares insights from their experience at Microsoft and invites feedback on the evolving framework.
- ▪Prompt-driven development often leads to unpredictable results and debugging challenges.
- ▪Spec-Driven Development improves consistency but struggles to scale with larger projects.
- ▪Agentic-Agile development seeks to integrate AI agents into teams while maintaining flexibility and alignment.
Opening excerpt (first ~120 words) tap to expand
“A bad system will beat a good person [or agent] every time” ~Dr. William Edwards Deming (with apologies) I started vibe coding by writing prompts (often dictated into my phone), refining them with an agent in M365 Copilot, and creating handoff files to use with GitHub Copilot CLI. The results were predictably non-deterministic. Prompt-driven development is a typical starting pattern: a developer opens a chat session, writes a prompt, reviews the output, adjusts, re-prompts. Maybe they get something useful. Maybe they spend an afternoon debugging emergent behavior that nobody specified and nobody tested.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Microsoft Dev Blogs.
Discussion
0 commentsMore from Microsoft Dev Blogs
