Backlog.md Hands On
summary
Backlog.md claims to be 99% by AI agents with humans setting vision and reviewing, and the workshop shows the exact loop: write specs as markdown in-repo, init backlog (CLI or MCP), then have an agent create tasks, produce an implementation plan, and implement one task end‑to‑end. It demonstrates a 3-way review (spec, plan, code), a local terminal kanban plus web UI, git-backed markdown tasks, and reports improving success from ~50% prompting to 95% merge rate with spec-driven tasks.
AI-written summary · about
chapters (11)
- 0:00Introduction and context
- 3:04AI agents and workflows
- 13:25What is Backlog MD
- 20:35Demo of Backlog MD interface
- 24:56Backlog MD development journey
- 29:31Spec-driven AI development
- 40:14Q&A and break
- 44:35Workshop setup
- 51:18Live demo with Codex
- 57:30CLI vs MCP integration
- 1:01:27Closing and thanks
related talks
42mBacklog.md: The simplest project management tool for the AI Era
28mHow To Use Spec-Driven Development for Production Workflows
16mTackling tech debt
36mPlan, Specify, and Implement
18mUsing Spec-Driven Development for Production Workflows
47mSpec-Driven Development with AI Agents From High-Level Requirements to Working SW
37mSpec Driven Development: AI Assisted Coding With Doc at the Core
01h 37mFull Walkthrough: Workflow for AI Coding