Deep dives into system design, architecture patterns, and building software at scale.
A deep dive into access control models — DAC, MAC, RBAC, ABAC, ReBAC, policy engines like OPA, Cedar, and Casbin, Kubernetes RBAC, API authorization patterns, and the principle of least privilege.
How AI agents use tools — function calling APIs, tool definitions, ReAct reasoning loops, tool selection strategies, error recovery, parallel tool calls, and structured outputs with Claude and GPT.
A practical guide to reducing LLM costs in production — token economics, model routing, response caching, prompt compression, batch processing, self-hosted vs API trade-offs, and cost monitoring strategies.
A comprehensive guide to evaluating LLMs — standard benchmarks like MMLU and HumanEval, building custom evals, LLM-as-judge patterns, A/B testing AI features, and tools like Braintrust, Langsmith, and Promptfoo.
A developer's guide to AI-powered search architecture covering semantic search, hybrid search, reranking, query understanding, faceted semantic search, vector databases, and RAG for search systems.
A developer's guide to AI safety guardrails architecture covering input validation, output filtering, content moderation, PII detection, hallucination detection, rate limiting, human-in-the-loop patterns, and tools like Guardrails AI and NeMo Guardrails.
How to orchestrate AI workflows — LLM chains, DAG-based pipelines, conditional branching, human-in-the-loop, error handling, and tools like LangChain, LangGraph, Temporal, and Prefect.
How to evolve APIs safely — additive changes, field deprecation, default values, Postel's law, schema evolution, consumer-driven contracts, and breaking change detection in CI.
How to design batch API endpoints: request patterns, Google-style JSON batching, bulk operations, partial success handling, idempotency in batches, performance trade-offs, and production implementation guidance.