

Episode 59: Patterns and Anti-Patterns For Building with AI
25 snips Sep 23, 2025
In this engaging discussion, John Berryman, Founder of Arcturus Labs and an early engineer on GitHub Copilot, dives into the real-world challenges of building AI applications. He highlights the 'seven deadly sins' of LLM development, offering practical solutions to keep projects moving. John explains why aspiring for perfect accuracy may hinder progress and shares insights on context management and retrieval debugging. Treating an LLM like a forgetful intern, he emphasizes starting simply and avoiding unnecessary complexity for successful deployment.
AI Snips
Chapters
Books
Transcript
Episode notes
Don't Demand 100% Accuracy
- Reframe requirements that demand 100% accuracy and compare them to human expectations.
- Make outputs transparent and let users review and sign off so the system saves time without promising perfection.
Keep Users In The Loop With Agents
- Avoid giving agents large closed tasks to run unattended; keep the user in the loop during the process.
- Ask clarifying follow-ups and present intermediate checks so the agent narrows ambiguous requirements.
Use Context Responsibly
- Longer context windows don't guarantee better results and can degrade accuracy, cost, and latency.
- Tier potential context by relevance and trim to fit your token budget for better model performance.