AI Codex
The practitioner's guide to deploying AI.
Forward Deployed Engineers build AI systems inside companies. AI Agent Managers run them. Both roles are exploding — and neither has a good free resource yet. This is it.
Where do you want to start?
Deploying AI for companies?
Two roles are defining enterprise AI right now. AI Agent Managers run AI systems inside their own company. Forward Deployed Engineers build them for clients. Full learning paths for both.
Using Claude at work?
Better prompting, workflows that stick, and the habits that separate people who get consistent value from Claude from those who don't.
Building with Claude?
From your first API call to production deployment. Or from a product idea to real users — two paths depending on whether you're a developer or a founder.
Rolling out to your team?
Whether you're a team lead doing a department rollout or IT handling org-wide deployment — structured paths with the decisions you need to make, in order.
Not sure which one fits you?
Answer 2 questions and we'll point you to the right path.
New role · exploding fast
What is a Forward Deployed Engineer?
Anthropic and OpenAI both launched billion-dollar deployment companies in the same week. Both built around the same type of engineer. Here's what they do, what they earn, and how to become one.
Read the guide →500K–1M new jobs predicted
What is an AI Agent Manager?
Aaron Levie predicts 500,000 to 1 million companies will hire someone to own their AI agents internally. Most already have this person — they're just still arguing over whether to call them an AI Agent Manager, AI Ops Manager, or Agent Operator.
Read the guide →Context
What AI Is Actually Doing to Your Job
Worth reading
Worth reading this week
Claude's June 15 billing change: programmatic usage moves to a separate credit pool
From June 15, 2026, Agent SDK, `claude -p`, Claude Code GitHub Actions, and third-party agent apps stop drawing from your subscription's usage limits and start drawing from a separate monthly dollar credit, metered at API list prices. Interactive Claude Code and web chat are unchanged. Here's exactly what changes, the credit per plan, and what to do before the deadline.
6 min read
Dynamic Workflows in Claude Code: when Claude orchestrates its own agent swarm
Shipped with Opus 4.8 as a research preview, Dynamic Workflows let Claude write a multi-step plan and fan it out across tens to hundreds of subagents running in the background. It's built for work one context window can't hold — codebase-wide migrations, sweeping audits. Here's what it is, how it differs from sub-agents and Agent Teams, and when it's worth the token bill.
7 min read
Claude Opus 4.8: what's new, and why migration is easy this time
Anthropic's new flagship launched May 28, 2026. Pricing is unchanged at $5/$25. Effort now defaults to high, fast mode is 3x cheaper, and a 1M context window ships by default. Unlike the 4.6→4.7 jump, there are no new breaking changes — moving from Opus 4.7 is a model-name swap.
8 min read
Or browse by topic
Full glossary →Weekly brief
For people actually using Claude at work.
Each week: one thing Claude can do in your work that most people haven't figured out yet — plus the failure modes to avoid. No tutorials. No hype.
No spam. Unsubscribe anytime.