Hands-on Claude Code training for people who have never written a line of code, so they can build the tools their work has been waiting for.
10,000+ people trained across 500+ organisations
Claude Code is usually sold as a tool for engineers. We think the bigger story is everyone else. The analyst rebuilding the same report every Monday, the finance team reconciling three exports by hand, the operations lead with a tracker that lives in someone’s head. Claude Code lets them describe what they need in plain English and get a working tool back.
We know because we did it ourselves. Our own website was built with Claude Code, with no developers and no agency. This half-day, hands-on class takes your team from setup to a small, real build of their own, using their own files and recurring tasks, with the checks and guardrails that keep it safe.
What people say after our classes
97%
said the class will help them get more value from AI at work
97%
enjoyed the class
88%
would recommend it to a colleague
5 hrs
average time each person expects to save every week
Post-class surveys across our classes.
Every session is built from scratch around your work, but every session builds the same foundations.
Getting set up in the Claude desktop app, choosing how much Claude may do without asking, and having it interview you to write a CLAUDE.md file that remembers your work, your files and your rules.
A plain-English mental model of how Claude Code reads files, writes code and runs it, so people know why a tool built from code gives the same answer every time and a chat answer might not.
Having Claude look through your folders, spreadsheets and recurring tasks for jobs worth automating, then debating the options with a simulated panel before committing to one small build.
Letting Claude interview you to write a one-page brief, then using plan mode so it sets out what it will do and waits for your approval before it touches a single file.
Queuing follow-ups, stopping it when it drifts, keeping a clean slate between tasks and choosing the right model, so people stay in charge of the work and the cost.
Checking the output against a sample where you already know the answers, asking a separate reviewer agent to pick holes in it, and testing anything with a screen in the browser.
Turning what works into Skills the team can reuse, and drafting scheduled routines that run on their own with a human review step built in.
Keeping data, passwords and permissions locked down, knowing what should never go near the tool, and making the case to IT with a clear picture of what was built and how.
The capstone
Everyone finishes the session by taking one small build from idea to a working, checked tool on their own machine, so people leave with something that saves them time next week, not just notes.
We can usually map your highest-impact use cases in a single conversation.
Get in TouchThese are the kinds of tools non-developers have built in our workshops, from analysis that runs as checked code to dashboards that rebuild themselves. A coding agent lets people take this further, on their own files and data.
A dashboard built from a deal workbook using written-down column mappings and checks run as code, so missing or non-reconciling data is flagged rather than guessed.
A raw sales extract turned into an interactive market share dashboard, with the layout saved as a Skill so the next market looks the same and can be compared side by side.
A monthly flash report turned into a dashboard showing who is ahead of or behind plan, with cash and debt concerns flagged and a formula workbook behind every number.
Drawn from our anonymised client use case library.
Three signals showing coding agents moving beyond engineering teams. Each links to its source.
2x
growth in the share of Claude Code sessions spent on writing and data analysis, to about 20%
AnthropicThe class moves through six parts. Each one builds on the last, so by the second half of the session people are working on a real task of their own rather than a demo.
01
Install, permission settings and a CLAUDE.md written by interview, plus a quick tour of how Claude Code works and why checking its output matters.
02
Claude scans your own files and recurring work for opportunities with evidence behind them, a simulated panel argues for and against, and everyone picks one small build for the day.
03
A one-page brief written by interview and reviewed sceptically, then a plan that Claude must get approved before it changes anything.
04
Claude builds while people steer: queuing the next step, interrupting when it drifts, handing over with a short note and clearing the slate to keep it sharp.
05
A reviewer agent goes through the work and ranks what to fix, tests run against answers you already know, and anything visual gets tried in the browser.
06
Guardrails for data and access, a Skill or a scheduled routine so the work repeats without you, and a short summary of what was built, what was checked and what is left.
Delivered in person at your offices.
Going further
Once a few people are building, the question becomes how to make it a team habit rather than a handful of clever side projects. Our advanced training is for those people and the leaders backing them.
People who spend hours each month stitching exports together, rebuilding the same report or checking numbers by hand.
The people who keep things moving with trackers, chasers and spreadsheets, and know exactly which tool they would build if they could.
Teams who already use Claude or ChatGPT every day and have hit the limit of what a chat window can do.
Heads of team with a backlog of small internal tools that never get prioritised, who want their people able to build safely themselves.
Other courses teams pair with this one.
Every Claude Code session is led by one of our instructors, with a dedicated tutor in the room so nobody gets left behind.
Founder + Chief AI Officer
AI Instructor
AI Instructor
AI Instructor
AI Instructor
AI Instructor
AI Instructor
AI Instructor
Yes. Our Claude Code training for developers is a separate half-day session for engineering teams, working in their own repositories with plan mode, hooks, sub-agents and testing. Many firms run both.
No. The class is built for people who have never written code. They describe what they need in plain English and Claude Code writes, runs and explains the code. What we teach is how to brief it well, keep it in check and prove that what it built actually works.
Claude is brilliant at reading, writing and analysing in a chat. Claude Code builds things: it creates files, writes code and runs it on your machine. That means it can make a tool that does the same job the same way every time, such as a report that rebuilds itself from this month’s exports, rather than giving you a fresh answer each time you ask.
Small, useful tools built around their own work. A dashboard that refreshes from a spreadsheet export, a script that reconciles two reports and lists the exceptions, a tidy-up of hundreds of files, a weekly monitoring routine or a simple internal web page. Everyone picks one small build so they finish the day with something that works.
We send a short checklist before the day: Claude Code installed on each machine, the right account access, and agreement on which files and systems are in bounds. We cover data and access guardrails in the class itself, and we are happy to talk your IT team through it beforehand.
In person at your offices by default, with an instructor and a dedicated tutor in the room. Having people on hand makes setup and the first real build much smoother. We can run it remotely if that suits your team better.
Attendees keep a curated prompt library and cheat sheets, and we run a follow-up review call to see what people have built, what got stuck and where to take it next.
Yes. We are based in Covent Garden, London, and run most sessions in person at clients’ offices in London and across the UK. We also work with teams worldwide, from Paris and Berlin to New York and Singapore, and can run sessions remotely when that suits better.
From The Distillation, our newsletter on putting AI to work.
We analysed our last 30 client conversations to find the five AI challenges firms raise most, from uneven adoption to proving ROI. Plus field notes from Cowshed and Montagu, The AI Summit London 2026, and funded graduate training places.
Josh Page ·
GPT-6 Astra and Claude Opus 5.5 moved the frontier twice in three weeks. Plus AI training for the industries that make things, field notes from our US rollouts with Access Holdings portfolio companies, and funded graduate places on our next open enrolment sessions.
Josh Page ·
Anthropic just built the most capable AI model ever and decided not to release it. The cyber capabilities are extraordinary, the coding benchmarks are unprecedented, and the implications for every firm using software are serious.
Tom Hewitson ·
Tell us about the reports, trackers and recurring tasks that eat your team’s week, and we will design a day around building the tools that fix them.
Get in Touch