Context Engineering: What Goes in the Context Window
Prompt engineering asks how to phrase a request. Context engineering asks what the agent needs to know. Here's the budget I run across 30+ production agents
Aug 1, 2026
Best AI Agents for Small Business: What I'd Buy in 2026
A practitioner's buyer's guide to AI agents for small business — the three real tiers (off-the-shelf, DIY, custom), a 5-point rubric for evaluating any tool
Jul 30, 2026
Context Engineering: How I Use It to Build AI Agents
Context engineering is the discipline that replaced prompt engineering for serious agent work. Here's how I structure context windows across 30+ production…
Jul 28, 2026
Human-in-the-Loop AI Agents: When to Add an Approval Gate
Updated for 2026. The decision framework I use to decide when a production AI agent needs a human approval step — and when adding one silently kills adoption.
Jul 23, 2026
Prompt Caching With the Claude API: Cut Input Costs
How to use cache_control to cut Claude API input costs by up to 90% on agents with large stable prompts — the prefix-match invariant, what to cache
Jun 18, 2026
AI Agent ROI: Is an Automation Worth Building?
The framework I use to decide whether an AI automation is actually worth building — quantified manual cost, build cost, run cost, maintenance tax
Jul 9, 2026
How to Automate Your Small Business With AI Agents
The exact playbook I use to automate a real small business with AI agents — from the $5/month Cloudflare stack to the tasks that actually pay off.
Jul 4, 2026
AI Agent Cost Math: When Haiku Beats Sonnet
Updated for 2026. The cost math I use to pick Claude Haiku vs Sonnet per task — token economics, the routing rule, and where cheap models quietly cost more.
Jun 8, 2026
How to Debug an AI Agent in Production (A Field Guide)
Updated for 2026. The exact playbook I use to debug AI agents running live — trace every step, isolate the failing layer, and reproduce non-determinism fast.
Jun 8, 2026
Multi-Agent Orchestration: Queues, State, Handoffs
Updated for 2026. The orchestration patterns I use to run multi-agent systems — durable queues, externalized state, and clean handoffs that survive retries.
Jun 8, 2026
The Eval Harness I Use to Ship AI Agents Without Fear
Updated for 2026. The eval harness I use to ship AI agents — a graded test set, an LLM judge, and a regression gate so a prompt change can't break prod.
Jun 8, 2026