14 min ·
Agents vs Workflows: One Question Decides Which You Need
Agents vs workflows comes down to one question: who decides the next step, your code or the model? Learn the rule, then read Chapter 1 free.
Agent fundamentals
14 min ·
What Is an Agent Harness? The Part You Actually Build
What is an agent harness? The loop, tools, history, stop rules and recovery around the model, what breaks without each, and when to adopt a framework.
12 min ·
What Is an Agent Loop? The Cycle Every Agent Runs
What is an agent loop? The four beats every agent repeats, how ReAct fits, and the three exits ranked by trust, with a worked trace. Read the walkthrough.
12 min ·
Compounding Errors in AI Agents: Why Small Mistakes Snowball
Compounding errors in AI agents are worse than pⁿ: self-conditioning, snowballing and correlated errors. See the evidence and the redesign that fixes it.
Tools, skills and protocols
14 min ·
Idempotent Tools for AI Agents and the Retries They Make Safe
Idempotent tools for AI agents turn a retry or crash-resume into a no-op, not a second charge. Learn keys, receipts and retry rules with a worked example.
Context engineering and memory
11 min ·
What Is Context Rot? Symptoms and the Four Fixes
What is context rot? Why an AI agent degrades as its context window fills, the five failure modes behind it, and four fixes. Learn to diagnose a run.
Patterns and multi-agent systems
16 min ·
Single Agent vs Multi Agent: Start With One, Then Ask This
Single agent vs multi agent: start with one, split only when branches run blind and merge cheaply. Use the decision table, then read Chapter 11.
Evaluating and observing agents
15 min ·
How Many Eval Examples Do I Need? Sample Sizes and Intervals
How many eval examples do I need? Twenty to fifty at first, hundreds to compare versions. The arithmetic, paired tests, and a worked example to copy.
15 min ·
Is LLM as a Judge Reliable? A Calibration Method That Tells You
Is LLM as a judge reliable? Only as far as you have measured it. A calibration method with Cohen's kappa, a worked example and the four biases to test.
Security, reliability and cost
15 min ·
AI Agent Failure Modes: A Field Taxonomy
AI agent failure modes sorted for diagnosis: symptom, cause, trace signature and fix for each, cross-checked against MAST. Keep it open beside your traces.
16 min ·
The Lethal Trifecta: Three Safe Capabilities, One Unsafe Agent
The lethal trifecta AI agents carry: private data, untrusted content, an outbound channel. Run the audit, cut one leg, cap the blast radius. Start here.
Teaching AI agents
13 min ·
How to Teach AI Agents: Sequencing and Assessing the Course
An AI agents course syllabus for instructors: why the loop comes first, how to grade verification over demos, and how peer courses compare. Get the kit.