AI/LLM Training
Get your team building with AI instead of just talking about it.
- Prompt engineering and LLM integration patterns
- Agentic design patterns and multi-step workflows
- Evaluation, testing, and reliability strategies for AI systems
- Tool-assisted coding workflows with AI pair programming
What this is
Most AI training is either too theoretical or too superficial. I teach engineers how to actually build with LLMs. Not just how to write a prompt, but how to design systems around models that are probabilistic, expensive, and occasionally wrong.
The material covers the full stack of practical AI engineering: choosing the right model for the job, structuring prompts that work reliably, building agent workflows that recover from failures, and setting up evaluation frameworks that catch regressions before users do.
Everything is hands-on. People build real components during the training, not toy examples. They leave with working code and patterns they can apply immediately.
How it works
Before I run a session, I learn the team. I want to know the stack, where current AI experiments have stalled, and what the team is actually trying to build. The curriculum gets built around those gaps, not a generic skills inventory.
Sessions run in half-day or full-day blocks, combining instruction with hands-on exercises against the team's actual codebase and tools where possible. I don't use toy examples when the real problem is available.
Between sessions, the team builds with what they've learned. The goal is making sure the training lands in production, not just in notes.