davidgasquez.com
📚 Personal bits of knowledge
🧰 Expand agent guidelines with fast tests, interactive testing, and linters/type checkers/formatters
- Add sub-bullet under feedback loops for interactive code testing
- Emphasize speed of tests alongside quality
- Recommend providing linters, type checkers, and auto-formatters for agents
+3
-1
Artificial Intelligence Models.md
+3
-1
Artificial Intelligence Models.md
···
67
67
- Add relevant context to the prompt. Context can be external docs, a small pseudocode code example, etc. Adding lots of context can confuse the model, so be careful!
68
68
- [Teach the agents to use tools](https://www.anthropic.com/engineering/claude-code-best-practices).
69
69
- Be aware of the "cache" (e.g: never edit files manually during a session)
70
-
- [Focus on building a rich environment with good tests, documentation, consistent patterns, and clear feature definitions - this helps both humans and AI work better](https://blog.nilenso.com/blog/2025/05/29/ai-assisted-coding/).
70
+
- [Focus on building a rich environment with good and fasts tests, documentation, consistent patterns, and clear feature definitions - this helps both humans and AI work better](https://blog.nilenso.com/blog/2025/05/29/ai-assisted-coding/).
71
71
- Balancing log verbosity is crucial. Informative yet concise logs optimize token usage and inference speed.
72
72
- [You need quick and clear feedback loops](https://lucumr.pocoo.org/2025/6/12/agentic-coding/) (fast tool responses, clean logs, ...).
73
+
- Give them the ability to interactively test the code they are writing too.
74
+
- Linters, type checkers, auto-formatters - give coding agents helpful tools to run and they'll use them.
73
75
- Prefer functions with clear, descriptive and longer than usual function names over classes. Avoid inheritance and overly clever hacks.
74
76
- Write legible (text based) relevant content and link it with anything else (code, diagrams, ...).
75
77
- Use a checklist. Plan, iterate, and refine.