Claude
Claude, Cowork and Claude Code: from your first session to agent harness engineering. 15 platform modules plus 22 that apply to every platform.
Start here
Three modules, in order: the required trio for the AF Claude Practitioner credential.
- Step 1:Module 01 · Track A
Claude 101
What Claude is, how it differs from ChatGPT, and how to use its three surfaces (browser, desktop, Cowork) for real work.
ClaudeBeginners7 lessons · 90 min - Step 2:Module 02 · Track A
How to Prompt
How current frontier models follow instructions, and the five fixes that turn vague prompts into precise ones.
All platformsBeginnersIntermediate10 lessons · 60 min - Step 3:Module 03 · Track B
Set Up Claude Cowork
How Cowork works and how to set up the folder and context files that make it effective.
ClaudeBeginnersIntermediate5 lessons · 90 min
Credentials
Four levels, earned rather than attended: required modules, a verified skill check, and an artifact for the two upper levels. Every credential carries a public verification URL.
- Level 1
AF Claude Practitioner
3 required modules · skill check
- Level 2
AF Claude Power User
7 required modules · skill check
- Level 3
AF Claude Agentic Engineer
3 required modules · skill check · artifact
- Level 4
AF Claude AI Leader
3 required modules · skill check · artifact
Modules
Showing 38 of 38 modules
How to Prompt
How current frontier models follow instructions, and the five fixes that turn vague prompts into precise ones.
AI at Work 101
What a large language model actually is, what that makes it good and bad at, and how the four assistants most organisations use ({{fact:general_assistants}}) package the same idea in different surfaces.
Choosing Your AI Assistant
How to choose between {{fact:general_assistants}} for an organisation, starting from what you already pay for rather than from benchmark tables.
Claude 101
What Claude is, how it differs from ChatGPT, and how to use its three surfaces (browser, desktop, Cowork) for real work.
Sound Like You
How to capture your writing voice, taste, and hard rules in one compact file any AI can use.
Stop Writing Like AI
The patterns that make text read as machine-written, from negative parallelism to banned vocabulary.
Stop Prompting, Start Briefing
Why maintained context files beat repeated prompting, and how to manage them with Obsidian.
Set Up Claude Cowork
How Cowork works and how to set up the folder and context files that make it effective.
Claude Skills
How skills turn your repeated tasks into reusable, auto-triggering workflows.
Claude Connectors
How to connect Claude to the tools where your work already lives, and the restraint rules that keep it cheap and safe.
Cowork + Projects
How Projects give Cowork persistent memory, standing instructions, and scheduled tasks.
Claude as Your Computer
How Claude operates your computer directly, and how to set that up without giving away the keys.
AI Slides
The research-first pipeline that produces decks worth presenting, plus the brand setup that keeps a whole team on-style.
Claude for Excel
How to get real multi-tab spreadsheets with working formulas out of Cowork, with you controlling the assumptions.
Claude Design
What Claude Design produces (sites, decks, video) and the design-system workflow that keeps output on-brand instead of generic.
Claude Code for Non-Coders
How to ship websites, dashboards, and prototypes with Claude Code without writing or reading code.
AI for Your Team
A five-day rollout playbook that works on any of the four assistants, built around recurring deliverables rather than general enthusiasm.
Claude for Your Team
A 5-day playbook for rolling Claude out to a team so adoption actually sticks.
Stop Hitting Claude Limits
Why usage disappears (every message re-reads the whole conversation) and the habits that stop it.
Claude Certificates
Which Claude certifications are real, which are free, which are scams, and the path through Anthropic's catalogue for your role.
Prompt Engineering Deep Dive
The complete prompting toolkit, from structure and roles to hallucination control and complex industry prompts, plus how to measure prompt quality with evaluations.
Agent Harness Engineering
How agents actually work under the hood: the model supplies intelligence, and everything else is a harness you can build.
Agentic Futures Briefing
Where agentic engineering is heading across three horizons: what's standard practice now, what arrives within a quarter, and what's forming six months out.
Claude Code for Developers
How to run Claude Code as a professional engineering tool: operating manuals, subagents, hooks, skills, MCP, and git/CI workflows.
Working Safely with AI
What may and may not go into an assistant, where personal data and the EU AI Act touch everyday use, how prompt injection reaches you through connectors and browsing, and how to keep a named human accountable for every output that leaves your desk.
AI for Sales and Revenue Teams
The five sales workflows where an assistant pays for itself: pipeline triage, account and meeting prep, proposal and follow-up drafting from a brief, objection practice, and forecast commentary.
AI for HR and People
How to turn a role brief into a job ad and an interview kit, draft and plain-language a policy, build onboarding material, and run a bias check on all of it, without ever pasting a candidate or employee record into the wrong place.
AI for Finance
A verification discipline for finance work with an assistant: assumptions before formulas, formulas before numbers, a reconciliation check before anything leaves your desk, and commentary that points at the cells it came from.
AI for Project Managers
To turn raw updates into a status report people read, keep a decision log that survives staff turnover, write stakeholder communications for the audience rather than the project, maintain a risk register that changes, and schedule the recurring briefings where your platform supports them.
AI for Legal and Compliance Teams
Three contract-review patterns (clause extraction, playbook comparison, plain-language summary), how to build and use a clause library, and the four guardrails that decide whether any of it is safe: confidentiality, privilege, hallucinated citations, and what never leaves the firm.
AI for Content and SEO Teams
Two half-sessions with their own exercises: content (briefs to drafts in the house voice, editing, repurposing across channels, and the anti-AI-writing habit) and SEO (keyword clustering, search-intent mapping, on-page briefs, metadata at scale, and checking what AI answers say about your brand), plus the short list of what not to automate.
AI for Tech Teams
The non-agentic developer workflow: the reading-and-writing work around the code that an assistant in a chat does well today, on any platform, without touching your repository. Documentation and ADRs, code review summaries, ticket triage and refinement, incident notes and post-mortems, runbooks.
AI Strategy Briefing for Executives
What has changed in the assistants over the last eighteen months, what an organisation should do in the next ninety days, and how to frame build versus buy, capability versus tools, risk posture and return on investment so the board can decide rather than defer.
Measuring AI Adoption
What the admin dashboards on all four assistants actually measure, how to take a time-saved baseline that survives a finance review, which quality signals to collect, and what good looks like at three, six and twelve months.
Build Your Own MCP Connector
How the Model Context Protocol works and how to wrap an internal tool or API as a connector any MCP-capable assistant can call.
Building on the Claude API
The Claude API from first call to first agent: messages, system prompts, streaming, tool use, and structured output.
Claude Solution Architecture
How to design a Claude solution end to end: platform choice, architecture pattern, evaluation, cost model, and safety plan: the five decisions every deployment stands or falls on.
Plugins
Bundle skills and connectors into installable plugins for a team.
Tracks
Live bootcamps
The same modules, taught in a room. Cohort dates are on each bootcamp page and on Luma.