Using Spec-Driven Development for Production Workflows - Erik Hanchett, AWS
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
spec-driven development — Writing and agreeing the specification first, then having an agent implement against it — the spec, not the code, becomes the artifact you maintain.
Why it matters
spec-driven developmentWriting and agreeing the specification first, then having an agent implement against it — the spec, not the code, becomes the artifact you maintain.Full definition → helps you tackle complex, multi-feature codebases where naive prompting breaks down, by forcing upfront planning into distinct phases before code generation. Useful if you've hit the ceiling of ad-hoc AI coding on larger projects.
Key quotes
“Because if you give them just a little bit of of leeway, they will go off the rails.”
Erik Hanchett
“you are the human in the loop, so to speak. You need to be the code reviewer of all the code that's generated through this process.”
Erik Hanchett
“at the end of the day, if something goes wrong, you are the person that are going to be blamed for it, not the agent”
Erik Hanchett
“Kind of like that Goldilocks zone of information is what you need.”
Erik Hanchett
“I really think MCP is still maturing. There's a lot uh a long road ahead for it, especially with some of the security stuff it's doing.”
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
videoEveryone Gets A Software Company — Benjamin Guo, Zo Computer
articleAgile AI Development Lifecyclevaleriavg_dev
articleBeyond code generation: rethinking engineering productivity in the age of AI agentsIlya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura
videoFrom AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWSAI Engineer