Agents & AI Engineering11 min read
CLAUDE.md and AGENTS.md: What Coding Agents Read
How Claude Code and Codex load project instruction files, what belongs in them, and a worked AGENTS.md for a small Next.js repo.
Published · Updated
Blog
Every post, newest first. If you're new, start with one of these instead.
Where to start
Get an AI job
Compare the AI career pathsSee what each job involves day to day, then open its guides, posted pay and practice interview questions.
The whole pathBuild with agents
AI APIs for Beginners: Make a Request and Handle the ResponseLesson one of the free 17-lesson agent course: send a request to a model, read the answer, and test what happens when it fails.
The whole pathKeep up with AI
Best AI Accounts to Follow on X (Twitter) in 2026Researchers, engineers and lab accounts, with examples of what each one posts.
The whole path
Agents & AI Engineering12 min read
Datalab in Practice: Marker, Surya, Chandra and the API
Install Marker, convert a PDF, read the output, then do the same through the Datalab API. Every command comes from the official READMEs and docs.
Published · Updated
Agents & AI Engineering12 min read
Designing the Document Review Queue
Which documents a person should check, how many to spot-check, how many reviewer hours you need, and how corrections make the system better.
Published · Updated
Agents & AI Engineering10 min read
Document AI Cost at Scale: Pages Are the Small Part
Per-page prices for Datalab, Extend, Azure, Google and LLM APIs as of September 2026, and a worked example showing why human review is most of the bill.
Published · Updated
Agents & AI Engineering10 min read
Document AI Now: From OCR to Vision-Language Models
What changed when document parsing moved from OCR to AI models that read the whole page, with dated examples from Datalab, Extend, Azure and Google.
Published · Updated
Agents & AI Engineering10 min read
Document AI Glossary: 30 Terms, Defined Plainly
Thirty document AI terms, from OCR and parsing to precision, review thresholds and per-page pricing, each linked to the post where it matters.
Published · Updated
Agents & AI Engineering12 min read
Extend in Practice: Schemas, Evals and Workflows
How Extend's extraction schemas, test sets and workflows fit together, from its docs, with a worked schema for one made-up invoice.
Published · Updated
Agents & AI Engineering11 min read
Extend vs Datalab vs Other Document Parsers
Extend, Datalab, Google, Azure and Mistral compared on one disclosed invoice task, using only documented features and published prices.
Published · Updated
Agents & AI Engineering11 min read
Git Workflows with Claude Code and Codex
Branches, commits, worktrees and pull requests with a coding agent, plus the git actions an agent should never take without you.
Published · Updated
Agents & AI Engineering10 min read
Headless and CI Use of Coding Agents
Run Claude Code and Codex non-interactively and in GitHub Actions: flags, the GitHub app, Codex cloud, secrets, and a worked workflow.
Published · Updated
Agents & AI Engineering11 min read
Hooks for Coding Agents: Rules the Model Can't Skip
How Claude Code and Codex hooks work, the settings.json shape, and a worked hook that runs your checks before the agent commits.
Published · Updated
Agents & AI Engineering10 min read
Install Claude Code and Codex, Then Run a First Task
Install Claude Code and Codex, sign in, give each the same broken test to fix in a practice project, and check what it changed before you keep it.
Published · Updated