Spec-Driven Delivery with AI Coding Agents

Written specs and constitutions guide parallel AI coding agents, with human review required at every merge.

9+ repos
Repositories developed through the spec-first workflow
1,190+ PRs
Merged pull requests during 2026

Role: Workflow originator
Period: Mar 2026 to Present
Project type: Featured
Room in the 3D HQ: L3:agent-orchestrated-delivery

Results

9+ repos
Repositories developed through the spec-first workflow
Based on repository analysis; other engineers have not yet adopted this workflow.
1,190+ PRs
Merged pull requests during 2026
A throughput measure only. AI agents wrote much of the code under my specs and review.

Problem

AI coding agents can produce code faster than it can be reviewed. The workflow needed clear traceability from requirements to implementation and a review gate for every merge.

Contribution

I introduced GitHub Spec Kit with versioned constitutions and numbered specs linking task, acceptance and business-rule IDs.
I wrote enforceable agent instructions and dated memory logs.
I ran agents in parallel worktrees and integrated their changes through merge trains, requiring CI gates and human review for every merge.

Architecture

Tech stack

GitHub Spec Kit
GitHub Copilot
Claude Code
GitHub Actions
Codex

Results

Problem

Contribution

Architecture

Tech stack

More AI Engineering projects

I am open to freelance or part-time work in software and AI engineering.