Elite AI Assisted Coding
Subscribe
Sign in
Home
Course
FAQ
Tips
Talks
Guides
Tool Reviews
Archive
Tip
Latest
Top
Discussions
Sandboxing for AI Coding with GitHub Codespaces
Running AI coding agents locally on your machine offers great power but introduces significant security risks.
Oct 20
•
Eleanor Berger
1
Guide AI Agents Through Test-Driven Development
Test-Driven Development (TDD) pairs exceptionally well with AI agents, harnessing their iterative capabilities for self-correction while ensuring tests…
Oct 19
•
Eleanor Berger
2
Maintain a "Living Documentation" File
Core Principle: Transform your AGENTS.md file from a static instruction set into a dynamic, self-updating knowledge base that grows with your project.
Oct 15
•
Eleanor Berger
6
1
Empowering Agents with Environment Management
A significant step toward a fluid development partnership with an AI assistant is to grant it autonomy over its own environment.
Oct 13
•
Eleanor Berger
Use Git for Automated Checkpointing
Commit frequently to create a detailed history of your agent’s work.
Oct 11
•
Eleanor Berger
Build Checkpoints for Your Agent with Neon Snapshots
If you build apps with an AI agent, you probably want a way to go back in time to prior agent turns.
Oct 2
•
Isaac Flath
Attribute Git Commits to AI Agents
Instruct your agent to commit to git with `--author`
Sep 28
•
Eleanor Berger
Break Down Complex AI-Generated Code into Atomic Functions
When working with AI coding assistants, you may encounter situations where the generated code is lengthy, monolithic, or difficult to understand at…
Sep 21
•
Eleanor Berger
2
Enable universal file access for your AI coding agent with MarkItDown-MCP
While some LLMs can read certain file formats like PDFs directly, all LLMs excel at processing Markdown. This makes Markdown the ideal format for…
Sep 7
•
Eleanor Berger
1
1
Make Your Library AI-Friendly
Modern libraries should be designed with both human developers and AI assistants in mind.
Aug 31
•
Eleanor Berger
3
Optimize AI Model Usage by Phase
Use frontier models for analysis and planning, smaller models for execution
Aug 24
•
Eleanor Berger
4
1
Refine your initial prompt instead of course-correcting
When working with AI coding agents, you'll often find that your first attempt doesn't produce exactly what you need.
Aug 16
•
Eleanor Berger
2
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts