Harnessing AI Decisions with BDD, ADR, PRD

In the complex world of AI development, maintaining clarity and consistency in decision-making is paramount. Michal Cichra from Safe Intelligence, in his presentation titled “BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike,” delves into the critical importance of documenting and enforcing decisions, not just for human teams but also for AI agents themselves.

Cichra begins by outlining several key acronyms that are central to structured product and engineering processes: WTF, ADR, PRD, and BDD. WTF serves as a foundational question, “Why does any of this matter?” ADR (Architecture Decision Record) is used to record architectural decisions, focusing on what decision was made, why it was made, and how it is enforced. PRD (Product Requirements Document) captures the product goals, defining why a feature exists, what problem it solves, and what outcome is expected. BDD (Behavior-Driven Development) emphasizes running specifications that are both readable and executable.

To illustrate the challenge of maintaining consistent behavior, Cichra uses the well-known “five monkeys” story, drawing a parallel to AI and Large Language Models (LLMs), suggesting they also suffer from a “limited context.” This analogy highlights the need for clear and measurable standards in AI development. Cichra stresses the principle: “If you can’t measure it, you can’t enforce it.” To ensure that AI agents and development teams adhere to defined specifications, a robust enforcement mechanism, or “harness,” is essential. This involves tools like linters, type checkers, and architectural checks to uphold these standards.

The session concludes by emphasizing that while the underlying loop of AI development might be generic, the specific “skills” or rules applied provide focus. These may include frameworks like $ADR, $PRD, $UI-LOOP, $TEST, and Goal Execution, which help structure the development process and improve the overall decision-making landscape for AI applications.