Quant/Dev in Trade. Formerly Software Engineer with a focus in computer vision and machine learning.
Trained as a Physicist.
We are still in early days and I'm sure this isn't the best way to approach this but here is what I do.
1. Agent context with platform/system idiosyncrasies, how to access tools, this is actually kept pretty minimal - and a line directing it to the plan document.
2. A plan document on how to make changes to the repo and work that needs to be done. This is a living document pruned by the orchestrating agent. Included in this document is a directive written by you to use, update the document after ever run. Here also is a guide on benchmarking, regression, unit tests that need to be performed every time.
2a. When an agent has a code change it is then analyzed by a council of subagents, each focused on a different area, some examples, security, maintainability, system architect, business domain expert. I encourage these to be adversarial "red team". We sit in the core loop until the code changes pass through the council.
2b. Additional subagents to create documentation, build architecture diagrams etc.
2c. A suggested workflow is created on how to independently invoke testing, and subagent, etc.
This project is an enhanced reader for Ycombinator Hacker News: https://news.ycombinator.com/.
The interface also allow to comment, post and interact with the original HN platform. Credentials are stored locally and are never sent to any server, you can check the source code here: https://github.com/GabrielePicco/hacker-news-rich.
For suggestions and features requests you can write me here: gabrielepicco.github.io