The real bottleneck was not prompting
A lot of the discussion around agents still focuses on prompts. Better prompts, longer prompts, more careful prompts. What made the biggest difference in my workflow was none of that. It was structure.
I had a backlog of refactors and ideas in my head, but that’s not a real system. Too much repetition, too much context rebuilding, too many tasks started in the wrong order.
My first attempt: a small tool of my own
Before I found Beads, I built a small JavaScript tool that parsed markdown files inside the repo. The goal was simple: make work explicit enough that agents could help without me restating everything every session.
I laid out tasks directly near the code, with priorities like P1, P2, and P3, and with blocking relationships between them. That alone changed a lot. Refactoring became more organized. The backlog stopped feeling like one giant blur. Agents had clearer instructions because requirements were written down, prioritized, and tied to actual project movement.
The real improvement was resumability. I could come back later and say “let’s pick up where we left off,” and there was already enough structure for the session to continue without rebuilding everything from memory.
Where the homemade system hit its limits
That first version worked, but it had real constraints.
Because it lived inside the same repository as the code, it was awkward to use in parallel workflows. It also consumed too much context. Agents didn’t have a built-in way to discover how the system worked, so part of every session still went to teaching the tool back to them.
The key lesson: autonomy isn’t just about having tasks. It’s about having tasks in a form agents can reliably discover, understand, and operate on.
Then I found Beads
Beads solved the problems I was hitting. Instead of a homemade layer over markdown, it gave agents a proper system for ready work, claiming tasks, tracking blockers, taking notes, updating statuses, and resuming across sessions.
Features like bd prime stood out — it teaches the workflow back to the agent in a form it can use immediately. It also includes things I wouldn’t have designed myself at first but that make obvious sense once you work with agents seriously: worktrees, notes, status tracking, and a stronger model for task graphs and session continuity.
What changed
Once I adopted this style of working, agents became noticeably more autonomous and organized. My requirements were documented. Priorities were visible. Dependencies were explicit. The backlog became something agents could actually help clear instead of something I kept describing over and over.
Closing thought
Agent productivity doesn’t come mainly from clever prompting. It comes from durable, structured work.
Prompts guide execution. Structure makes execution resumable, parallelizable, and trustworthy.
If you want agents to be more useful, give them better work structure before you give them better prompts.