prompt-engineering
39 talks
How to Actually Tokenmaxx and Save Millions
Stop Fine-Tuning to Fix Retrieval Problems
Beating RL With Reflection: GEPA and Optimize Anything
How long can your skills be before your agent forgets what you told it?
The Missing Layer: Design Taste in AI Agents
The Unreasonable Effectiveness of Separating the Task from the Model
Building Great Agent Skills: The Missing Manual
Stop Writing Tone Instructions. Layer Them.
Let's Go Bananas with GenMedia
Agent Optimization with Pydantic AI: GEPA, Evals, Feedback Loops
Shipping complex AI applications
Judge the Judge: Building LLM Evaluators That Actually Work with GEPA
DSPy: The End of Prompt Engineering
Build a Prompt Learning Loop
The Unreasonable Effectiveness of Prompt Learning
No More Slop
From Arc to Dia: Lessons Learned Building AI Browsers
The Future of Evals
On Engineering AI Systems that Endure the Bitter Lesson
Your Coding Agent Just Got Cloned And Your Brain Isn't Ready
Prompt Engineering and AI Red Teaming
The New Code
From Mixture of Experts to Mixture of Agents with Super Fast Inference
Prompt Engineering is Dead
Buy Now, Maybe Pay Later: Dealing with Prompt-Tax While Staying at the Frontier
The Coherence Trap: Why LLMs Feel Smart (But Aren't Thinking)
The Model Isn't Wrong—You're Just Bad at Prompting
Your LLM Ran Out of Knowledge: Now What?
Personality Driven Development: Exploring the Frontier of Agents with Attitude
Optimizing LLMs in Insurance with DSPy
AI Music Generation, From Prompt to Production
GitHub Copilot: The World's Most Widely Adopted AI Developer Tool
Prompt Engineering Tactics
Judging LLMs
10x Development: LLMs for the Working Programmer
Building with Anthropic Claude: Prompt Workshop
Decoding the Decoder LLM without de code
How to Become an AI Engineer from a Fullstack Background
Principles for Prompt Engineering