AI Agents
Embeddings as Database Indexes: Tool-Call Permissions in AI Agents
How tool-call permissions and approval boundaries shape reliable AI agent systems using embeddings as the new database index
Blog
Thoughts on AI engineering, backend, frontend, and building modern software.
Prompt Engineering
Prompt Contracts as API Contracts: Structuring AI Outputs for Production Reliability
How structured prompt contracts prevent ambiguity in AI systems, ensuring reliable and predictable outputs in production environments
MLOps
The Hidden Cost of Quiet Prompt Changes: How Small Adjustments Trigger Big LLM Spend
A senior engineer's guide to tracking subtle prompt tweaks that inflate cloud costs and break production systems without raising alarms
AI Engineering
From Prototype to Production: Building Reliable AI Systems
Turn your AI prototype into a production-ready system with concrete strategies for contracts, fallbacks, and evaluation
MLOps
Cost Spikes from Quiet Prompt Changes: Monitoring LLM Features in Production
After deploying an LLM feature, monitoring for cost spikes from subtle prompt changes is critical. Learn how to detect and mitigate these risks in production systems.
LLMs
Structured Outputs as an API Contract: Building Predictable AI Systems
Structured outputs ensure reliable AI behavior in production. Learn how schemas, validation, and retries create predictable model behavior without relying on clever prompts.
Software Architecture
Mastering Software Architecture: Real-World Tradeoffs and Design Decisions for AI Systems
Learn real-world software architecture lessons from a senior engineer building AI systems. Explore tradeoffs, failure modes, and design decisions that shape production-ready tech stacks.
MLOps
Practical MLOps Lessons for Real-World AI Systems
Master MLOps challenges with real-world strategies and engineering judgment. Learn from my experiences building production AI systems.
LLMs
Practical Lessons in LLMs: Real-World Tradeoffs and Implementation Pitfalls
Building production systems with large language models requires balancing speed, cost, and reliability. Learn concrete strategies for deployment, optimization, and avoiding common pitfalls.
RAG & Retrieval
Practical Lessons in RAG & Retrieval: Building Reliable AI Systems in Production
Real-world challenges and design decisions in implementing Retrieval-Augmented Generation for production AI systems