Tool Use - AI Conversations AI Coding Agents Can Do So Much More (ft Kiran)
17 snips
Oct 7, 2025 Discover how AI coding agents are changing software development with Kiran's insights on optimizing your development environment. Learn about the importance of feedback loops, clear pipelines, and organized code to enhance AI performance. Kiran dives into Slate’s unique context management strategies that prevent common pitfalls and help agents excel in complex tasks. Explore why traditional software engineering skills are still crucial, and gain practical tips for structuring projects that maximize AI coding capabilities.
AI Snips
Chapters
Transcript
Episode notes
Provide Concrete Dev Rules
- Set up explicit dev rules (build, run, debug) so agents can validate their work automatically.
- Use rules files and commands as quasi-tools to give models feedback on correctness.
Guard Commits With Tests And Hooks
- Build strong testing and commit guardrails so agents can't pass by deleting code or tests.
- Use pre-commit hooks, two-stage commits, and manual review bypasses as checkpoints.
Design Code For Model Readability
- Keep codebases simple: fewer types, minimal abstraction, and modular where it naturally fits.
- Favor shorter files and co-locate code that changes together to reduce implicit decisions for models.