BDR, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike

Name: BDR, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike
Channel: Michal Cichra
Description: In this talk, Michal explores how practices like BDD, ADRs, and PRDs can help teams capture engineering intent more explicitly: what the system should do, why decisions were made, what constraints matter, and how future changes should be judged.

Jovanca Garnadi
Jun 5
1 min read

At AI Engineer Europe 2026, Spec27 Principal Engineer, Michal Cichra, gave a talk titled “BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike.”

Agentic coding gives developers superpowers.

It also gives them a very fast way to create a serious mess.

If agents are going to build, modify, and reason about software systems, we need better ways to instruct them, constrain them, and preserve the decisions they are supposed to respect.

That means taking specifications seriously: not as documentation theatre, but as working context for both humans and AI agents.

In this talk, Michal explores how practices like BDD, ADRs, and PRDs can help teams capture engineering intent more explicitly: what the system should do, why decisions were made, what constraints matter, and how future changes should be judged.

Watch the talk: https://www.youtube.com/watch?app=desktop&v=504PvfXou5Y

Since you’re here, you can also check out the Spec27 early access programme: validation and monitoring for AI agents.