My AI Agent Task Organization System

A developer created a file-per-task system for AI coding agents that stores each task as a separate Markdown file in a dedicated /ai/tasks/ directory, using front-matter blocks and checklists to preserve context across sessions. The approach solves context loss problems that arose from monolithic logs, built-in agent memory limits, and per-task shell spawning. The developer reports that writing a clean context dump before closing a session saves 10x the time on the next start and makes task handoffs trivial.

My AI Agent Task Organization System Here's what I tried and where each approach broke down: Running log in a single .txt file: everything ended up in a monolithic timeline. Context was buried. The agent would still hallucinate task order. Relying on the agent's built-in memory features: tool-specific memory like Claude /en/tags/claude/ Projects or custom instructions helped for global preferences but couldn't handle per-task context with interdependent subtasks. Spawning a separate shell per task: worked for a few tasks, then you lose track of which shell had which state; also easy to accidentally kill the wrong session. The solution came down to a single rule: every task gets its own file in a dedicated project directory. I added a /ai/tasks/ folder at the repo root, with one Markdown file per task. Each file uses a simple front-matter block followed by a checklist and a context section. --- status: active priority: high task: "Decrease inference latency in batch processing module" module: analysis/batch/inference.py last active: 2025-03-20 --- Progress - x Profile current pipeline to identify bottlenecks noted top 3 functions - Implement caching in the embedding step blocked: waiting on DB schema change - Test with production-scale data Context Dump Related models: ModelA, ModelB. Key vector columns are in table embeddings v2 . Branch is latency-fix , base commit abc1234 . The last error was a RuntimeError about tensor shape mismatch in the attention layer — discussed with team, identified as an index-off-by-one. Fix needs to wrap around to batch boundaries. Every session starts by loading the relevant task file into the agent's context window. I use a simple shell helper that prepends the markdown content as a system message. This gives the agent a clear status snapshot so it never has to guess where we left off. The biggest improvement isn't technical — it's discipline. The agent works best when the human structures the input. Writing a clean context dump before closing a session saves 10x that time on the next start. This approach also makes it trivial to hand a task off to another team member or to an agent running on a CI machine . Just point them at the .md file and the branch name. If you're fighting context loss with coding agents, this file-per-task model will probably save you a lot of repeated work. The Next OpenAI’s new throttling hit my agent – here’s how I traced the → /en/threads/4437/