Writing
Notes from the build
Practical, no-fluff writing on shipping AI systems in production.
From Impressive Demo to Production Agent
The gap between an agent that wows in a demo and one that survives real users is where most projects quietly stall.
The Economics of Running Agents: Cost and Latency
A multi-step agent can quietly cost ten times a single call. If you are not measuring it, you are not in control of it.
May 7, 2026Designing Human-in-the-Loop Agents
The best agents know when to ask. Designing the handoff between machine and human is where trust is won or lost.
Apr 23, 2026How to Actually Evaluate an Agent
'It worked when I tried it' is not evaluation. Here is how to measure an agent that takes a different path every time.
Apr 9, 2026Guardrails: Keeping Agents Safe in Production
An autonomous system that can act needs limits on what it can do. Guardrails are not optional once real consequences are involved.
Mar 26, 2026Multi-Agent Systems, and When You Don't Need One
Splitting a problem across several agents is powerful, and often premature. Here is when it earns its keep.
Mar 12, 2026Memory for Agents: Context, State, and Recall
Agents need to remember the right things at the right time. That is a design problem, not a database problem.
Feb 25, 2026Tool Use: How Agents Take Action
Tools are what turn a clever talker into something that gets things done. Designing them well is most of the work.
Feb 11, 2026Anatomy of an Agent Loop
Every agent, however sophisticated, runs the same core loop. Understand the loop and you understand the system.
Jan 28, 2026What Actually Makes an AI 'Agentic'
The word 'agent' gets attached to everything. Here is a precise, practical definition, and why the distinction changes how you build and test.
Jan 14, 2026Getting Started with LangChain for Production Apps
A practical guide to building production-ready LLM applications with LangChain, including best practices for error handling and scaling.
Dec 15, 2024MLOps Best Practices for Startups
How to set up ML infrastructure without enterprise budgets. Learn the essential tools and workflows.
Dec 10, 2024RAG vs Fine-tuning: When to Use What
A decision framework for choosing the right approach for your LLM use case based on cost, accuracy, and maintenance.
Dec 5, 2024Building Real-time Data Pipelines with Kafka
Step-by-step guide to streaming architecture for high-throughput, low-latency data processing.
Nov 28, 2024AI for E-commerce: 5 High-Impact Use Cases
Practical AI applications that drive revenue for online retailers, from recommendations to dynamic pricing.
Nov 20, 2024The Startup Guide to AI Budgeting
How to plan and allocate resources for AI initiatives when you have limited runway.
Nov 15, 2024