Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Build a working voice agent with the OpenAI Realtime API + Agents SDK, then bolt on an eval pipeline that catches barge-in failures, hallucinated grounding, and latency regressions.
OpenAI's parallel function calling can cut latency in half — or burn money on dependent calls. The architecture, code, and an eval that proves the win.
Build a production RAG agent with LangChain, then measure faithfulness, answer relevance, and context precision with RAGAS. The four metrics that matter and how to wire them up.
Non-deterministic agents break silently when prompts, models, or tools change. Build a regression pipeline with frozen datasets, semantic diffing, and gate thresholds.
How to build a safety eval pipeline that runs known jailbreak corpora, prompt-injection attacks, and tool-misuse scenarios on every release — and gates merges on it.
How to stream tokens, tool-call deltas, and intermediate steps from an agent — with code for both the OpenAI Agents SDK and LangChain — and the gotchas that bite in production.
A practical guide to running SWE-bench (and it Verified / Lite) on your own coding agent, plus the cheaper internal benchmarks that actually move the needle.
Streaming changes the eval game — final-answer correctness isn't enough when users perceive the answer one token at a time. Here's the metric set that matters.
Your agent picked the wrong tool 12% of the time and the final answer was still right. That's a latent bug. Here's the eval pipeline that surfaces it.
