← All Guides · Practitioner's Guide
The Practitioner's Guide to AI Agents
From First Principles to Production Systems
Reading order
Overview · 4 min read
Series Introduction
A twelve-part series that takes you from 'what is an agent?' to building self-improving systems. Pick your starting point based on where you are today.
01
AI Products & Strategy · 11 min read
What Is an AI Agent (and What Isn't)?
An AI agent is a system that uses an LLM to decide which actions to take in a loop until a goal is met. This article breaks down the four components every agent shares, the spectrum from chatbot to autonomous agent, what tool calling actually looks like in code, and the design principles that separate good tool definitions from bad ones.
02
AI Products & Strategy · 10 min read
When NOT to Build an Agent
Not every problem needs an AI agent. This article gives you a decision framework for when agents are the wrong choice, with a comparison table, anti-patterns, and the Klarna case study that proves the cost of over-engineering.
03
AI Products & Strategy · 8 min read
Pike's Five Rules of Agent Development
Rob Pike wrote five rules of programming in 1989 at Bell Labs. Thirty-seven years later, they map onto AI agent development with striking precision: measure before tuning, start simple, and get the data right. Nobody has made this connection explicitly. Here is the mapping, the evidence, and the framework it gives you.
04
AI Products & Strategy · 18 min read
Build a Real Agent This Weekend
The series has defined agents, established design principles, and mapped failure modes. This article builds one. A complete research assistant agent with three tools, structured error handling with error categories and retry logic, context management, and a basic eval, all in one runnable Python file using the Anthropic SDK.
05
AI Products & Strategy · 14 min read
Prompt Engineering for Production Agents
Production agents need prompts that produce consistent, structured output under adversarial conditions. This article covers the five patterns that separate production prompt engineering from tutorial-grade prompting: explicit criteria, few-shot examples, nullable fields, enum-with-fallback, and output format contracts.
06
AI Governance & Safety · 16 min read
Context Is the Program
Pike's Rule 5 says data dominates. In AI agents, the context window IS the data structure. This article traces why context quality determines agent behavior more than model capability, maps the five criteria that define good context, and shows what happens when stale data enters the reasoning loop unchecked.
07
AI Governance & Safety · 13 min read
Evals: How to Know If Your Agent Works
Most agent teams ship without evals and rely on 'looks right' testing. Pike's first two rules apply directly: you cannot tell where an agent fails, and you cannot fix what you have not measured. Here is how to build an eval strategy that catches what demos miss.
08
AI Governance & Safety · 15 min read
Guardrails and Safety: The Boundaries Every Agent Needs
Pike's Rule 4 says fancy algorithms are buggier. In agent systems, complexity multiplies failure surfaces. This article maps the three guardrail layers every agent needs, identifies the gap most frameworks miss, covers escalation patterns and workflow gates, and explains why simpler architectures are safer.
09
AI Products & Strategy · 12 min read
Observability: Seeing What Your Agent Actually Does
Your monitoring says 200 OK. The agent returned the wrong answer. Traditional APM was designed for deterministic software. Agents reason, branch, and call tools in sequences they decide at runtime. This article covers the five dimensions of agent observability, the tooling landscape, and a practical instrumentation plan.
10
AI Products & Strategy · 8 min read
Multi-Agent Systems: When One Agent Isn't Enough
Nine articles in this series used a single agent. This one explains when that stops being sufficient and what to do about it. Four signals tell you it is time. Three patterns handle 90% of cases. The hardest part is not building the system; it is debugging it when something goes wrong.
11
AI Products & Strategy · 15 min read
The Self-Improving Agent: From Static Prompts to Learning Systems
Most AI agents run the same prompt every time. The best ones evolve. This article maps the spectrum from static to self-improving agents, introduces the inner loop / outer loop architecture, and walks through a real system that learns from feedback weekly. Pike's Rules 3-4 set the boundary: start simple, add complexity only when measurement demands it.
12
AI Products & Strategy · 17 min read
From Problem to Agent: An Implementation Reference Guide
The series taught ten concepts across ten articles. This capstone walks through all of them applied to one problem: building a Data Quality monitoring agent. Seven steps, from problem definition through production deployment, showing the decision-making process that separates agent projects that ship from agent projects that stall.
PDF download coming soon.