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
Learn how to incrementally update fine-tuned models with new data while preserving existing capabilities, using replay buffers, evaluation gates, elastic weight consolidation, and model versioning strategies.
Implement consumer-driven contract testing for AI agent microservices using Pact and JSON Schema validation. Catch breaking API changes before they reach production with automated CI integration.
A practical guide to making your first open-source contribution to the OpenAI Agents SDK, covering dev setup, finding good first issues, writing quality code, and navigating the pull request review process.
Design and implement conversation branching systems that manage complex dialog trees with dynamic paths, state tracking, path merging, and dead-end prevention.
Master the core principles of conversation design for AI agents including turn structure, progressive disclosure, error recovery, and building flows that feel natural to users.
Learn how to define conversation funnels for AI agents, track user journeys through interaction stages, identify drop-off points, and optimize conversion rates with data-driven insights.
Learn the three core strategies for managing conversation history in AI agents — sliding windows, summary-based compression, and compaction — to stay within context window limits while preserving critical information.
Learn how to measure AI agent conversation quality using automated scoring rubrics, LLM-as-judge patterns, and human correlation validation to ensure your agent produces coherent and helpful responses.
Build robust conversation repair strategies for AI agents including error detection, clarification prompts, rephrasing requests, and graceful recovery from misunderstandings.
