{"slug": "my-ai-agent-task-organization-system", "title": "My AI Agent Task Organization System", "summary": "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.", "body_md": "# My AI Agent Task Organization System\n\nHere's what I tried and where each approach broke down:\n\n**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.\n\nThe solution came down to a single rule:\n\n**every task gets its own file in a dedicated project directory.** I added a\n\n`/ai/tasks/`\n\nfolder 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.\n\n```\n---\nstatus: active\npriority: high\ntask: \"Decrease inference latency in batch processing module\"\nmodule: analysis/batch/inference.py\nlast_active: 2025-03-20\n---\n\n## Progress\n- [x] Profile current pipeline to identify bottlenecks (noted top 3 functions)\n- [ ] Implement caching in the embedding step (blocked: waiting on DB schema change)\n- [ ] Test with production-scale data\n\n## Context Dump\nRelated models: ModelA, ModelB. Key vector columns are in table `embeddings_v2`.\nBranch 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.\n```\n\nEvery 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.\n\nThe 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.\n\nThis 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`\n\nfile and the branch name.\n\nIf you're fighting context loss with coding agents, this file-per-task model will probably save you a lot of repeated work. The\n\n[Next OpenAI’s new throttling hit my agent – here’s how I traced the →](/en/threads/4437/)", "url": "https://wpnews.pro/news/my-ai-agent-task-organization-system", "canonical_source": "https://promptcube3.com/en/threads/4441/", "published_at": "2026-07-30 18:48:49+00:00", "updated_at": "2026-07-30 19:07:45.879533+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "artificial-intelligence"], "entities": ["Claude"], "alternates": {"html": "https://wpnews.pro/news/my-ai-agent-task-organization-system", "markdown": "https://wpnews.pro/news/my-ai-agent-task-organization-system.md", "text": "https://wpnews.pro/news/my-ai-agent-task-organization-system.txt", "jsonld": "https://wpnews.pro/news/my-ai-agent-task-organization-system.jsonld"}}