Articles

Notes, tests, and arguments.

A tutorial should do more than run, and an explanation should do more than agree with the first page of search results. These are my arguments about developer content, documentation, and the AI systems I build around them.

Code Documentation: Comments, Generated Reference, and External Guides
Decide what belongs in code comments, generated reference, and written guides so each reader can find the right kind of answer.
5 min read
How to Write Task-Based Documentation Headings
Write documentation headings that tell a reader which task, decision, concept, or recovery path a section covers.
5 min read
Accessibility Testing for Documentation: A Release Checklist
Test developer documentation for release-blocking accessibility failures in structure, code, links, visuals, keyboard use, and rendered output.
6 min read
Internal vs. External Documentation: What Belongs Where
Compare internal and external documentation, decide where each page belongs, and split shared subjects without exposing private operating context.
6 min read
What Is Technical Documentation, and What Should It Include?
Technical documentation helps a developer decide, start, use, and recover from a product. Choose each page by the task it owns.
5 min read
Types of Technical Documentation: 8 Essential Types, Plus Agent Instructions
Understand the main types of technical documentation, study useful examples, and build a documentation system for users, teams, and coding agents.
6 min read
Technical Documentation Best Practices, Tested on Real Developer Docs
Use a tested review card to make documentation tasks, failure states, limits, and ownership clear before readers need support.
4 min read
Technical Documentation Template: Build Product Docs With a Tested Structure
Download a technical documentation template, learn what each page must prove, and turn its placeholders into trustworthy product docs.
6 min read
Technical SEO Checklist for Documentation Sites
Technical SEO for developer documentation: crawling, rendering, indexing, canonicals, internal links, Core Web Vitals, structured data, and search visibility.
13 min read
Organize Documentation Around Reader Routes, Not Your Org Chart
Reorganize a documentation site around reader routes, canonical answers, tested labels, and direct redirects instead of mirroring the org chart.
12 min read
Documentation Review Should Start With the Product, Not the Prose
Review documentation in four passes: product truth, reader route, rendered behavior, and release state, before polishing prose.
12 min read
The Agentic Workflow Playbook: From Prompt to Shipped PR
The repeatable five-stage process I run to take a task from vague intent to a pull request I trust, with an AI agent doing the heavy lifting and me stepping in to frame the work and read the diff before it merges.
9 min read
Fine-Tuning vs RAG for Agent Memory: When Each Approach Makes Sense
Fine-tuning and RAG solve different parts of the agent memory problem. Here is how to decide which one you actually need.
8 min read
Shared Memory vs Isolated Memory in Multi-Agent Workflows
How to choose between shared and isolated memory architectures for multi-agent systems, including their coordination and debugging trade-offs.
6 min read
Why Your Coding Agent Keeps Forgetting Everything: Memory Persistence in AI Coding Assistants
The memory persistence patterns that actually work for AI coding assistants, and why most agents lose context between sessions.
9 min read
LLM Inference Optimization: What Actually Works in Production
A practical breakdown of the inference optimization techniques that move the needle — batching, quantization, caching, and attention kernels — with concrete numbers and the tradeoffs between them.
7 min read
Memory Versioning and Audit Trails for Regulated AI Agents
If your agent overwrites its memory, you cannot pass a compliance audit. How to build append-only memory versioning and trace agent reasoning.
8 min read
Contextual Compression for Agent Memory: What Stays and What Goes
How agents decide what to keep in memory when context space is finite, and the three compression strategies that actually work.
8 min read
Episodic, Semantic, and Working Memory in AI Agents: A Practical Map
AI agents juggle three distinct memory types. Getting them wrong is the source of most agent memory failures I see in production.
7 min read
Memory Serialization: How Agents Persist State Across Sessions
Why agents forget everything on restart, and the serialization patterns that actually solve it
7 min read