Build in Claude, ChatGPT or Gemini: as a Project, in Cowork, or a local folder for Claude Code
You leave with your first purpose-built agent set up and running, plus the mental model that makes every agent after it easier to build. Most people start with a personal strategy coach that knows their background, their 2026 goals, and the patterns that hold them back.
What you'll build
Your first agent, in the container that fits you: a Project in Claude or ChatGPT, a folder-backed Cowork agent, or a local folder for a coding agent
A role profile that captures your work, your team, and how you think, so the agent stops giving generic advice
Custom system instructions generated through a guided, coaching-style interview
A background knowledge base, built with Deep Research, that your agent draws on every day
What you'll learn
How agents actually work: the brain (the model), the context (memory and files), and the tools it can reach for
The difference between instructions that are always on and context that travels with you, and why that distinction makes or breaks an agent
When to use a Project, when to use Cowork, and when to reach for a coding agent
Why context beats clever prompting, and the document structures that make agents remember what matters
What you won't get anywhere else
I'll share two highly refined mega-prompts I've developed over months of daily use: an Interview Prompt that interrogates your communication style, decision-making, and blind spots to generate deeply personalised instructions, and a Personal OKR Prompt that gets you crystal clear on what you're actually optimising for. People I've delivered these to have described the experience as life-changing. These are not generic templates.
2
Fri · 3 Jul · 2:30–4:30pm
Security
Working with agents safely
Before you wire AI into your CRM, calendar, and files, you need to know the risks. You leave with a clear mental model for what's safe to connect, what isn't, and the vetting checklist you'll use before installing any integration in Week 2.
What you'll learn
Prompt injection in plain English: how hidden instructions get into the content your agent reads, why email is the highest-risk channel, and how to shrink the attack surface
How to vet an MCP server before you trust it: official versus DIY, read-only first, and the safe-first-test pattern
Permission scoping and blast radius: deciding what an agent should and should not be able to see, do, or change
The higher-risk territory (browser control and computer use) and the compliance questions to ask before adopting any AI tool
What you won't get anywhere else
We use real moments of confusion from past cohorts (file-sharing permissions, a live prompt-injection demo) as the teaching examples, so the risks land concretely instead of as abstract warnings.
Week 27 Jul – 10 JulYour tools & reusable skills
3
Tue · 7 Jul · 2:30–5:00pm
Integrations & MCP
MCP servers (Attio, Todoist, Calendar) and native connectors
Your agent goes from smart-but-blind to wired into your actual tools. We use a go-to-market pipeline as the worked example, but the techniques apply to any workflow: connect your CRM, task manager, calendar, or any platform so your agent can read, act, and automate across them.
What you'll build
Live connections between your two or three most-used tools, so your agent works from your real data
A multi-tool workflow, for example: find deals untouched for a week, then create follow-up tasks with full context
A diagram of your main platforms and where data flows between them, ready to share with your team
A ranked list of automation ideas for your business, sorted by impact and effort
What you'll learn
What MCP (the Model Context Protocol) is, why it has become the standard for connecting AI to live platforms, and how local and hosted servers differ
The safe-first-test pattern for any integration: read before you write, verify before you edit
Chaining tools together so platforms that don't talk to each other directly can work through your agent
Permission scoping in practice: controlling what your agent can see, do, and modify across every connected system
What you won't get anywhere else
A couple of years ago this kind of setup would have taken weeks of custom development. Now you build it in a single session. I've run this exact stack daily since late 2025 across consulting, coaching, and sales, and you'll see the real workflows live: a pipeline review that surfaces stale deals, call prep with research pulled in automatically, and post-meeting follow-ups that update the CRM and create tasks in one go.
4
Fri · 10 Jul · 2:30–4:30pm
Skills
Reusable, named workflows
Skills are the unlock that makes everything afterwards easier. You leave having shipped at least one skill, with a clear sense of what separates a genuinely good skill from an OK one, and how to share it with your team.
What you'll learn
The taxonomy that ends the confusion: context file versus system instruction versus skill versus integration, and when to reach for each
What is inside a great skill: the description that makes it trigger at the right moment, the steps, and the examples
The quality moves that separate a reliable skill from a flaky one: source-of-truth rules, context discipline, and a troubleshooting block
How to share skills across a team, from sending a single file to a shared repository with named owners
What you won't get anywhere else
We walk through a real skill I use every day to process coaching transcripts, then build a brand-new skill live using the skill-creator eval loop, which compresses days of trial-and-error into minutes. Advanced builders get the consolidation; newcomers get a working skill they can copy.
Week 314 Jul – 17 JulAgents that work without you
5
Tue · 14 Jul · 2:30–5:00pm
Proactive Agents
Scheduled, always-on agents
The session Cohort 2 asked for most. You leave with at least one proactive agent running on a schedule that genuinely earns its place (not just a daily info dump), and a clear ladder for making it more useful every week.
What you'll build
Your first scheduled agent that runs on its own, reads yesterday's output, and reports back without being asked
An upgrade path that adds your business context so it suggests actions, not just summaries
A stretch build where the agent drafts the work for you, not just flags it
A plan for where it should live, from running on your laptop to cloud-hosted and always on
What you'll learn
The four-level ladder for proactive agents: briefing, then suggestions, then drafted solutions, then an agent that reviews and improves its own past runs
What makes a proactive task worth keeping: it acts on your context, respects your attention, and gets better over time
Real, working examples: a morning briefing, automatic capture of commitments from your meetings, and a daily revenue check
How and when to graduate from your laptop to an always-on, cloud-hosted agent
What you won't get anywhere else
Picture the difference between an intern who emails you a status report and an eager teammate who says 'this could be better, want me to fix it?'. That's the jump this session is about. I'll walk through my own growth agent, built over six weeks of iteration, showing the real output at each level so you can see exactly where yours can go. The skills you built in Week 2 pay off hard here.
6
Fri · 17 Jul · 2:30–4:30pm
Team Agents
Rolling agents and skills out across your team
Weeks 1 to 3 make you more capable. This session makes your whole team more capable. You leave with a rollout map: which tools go where, how to share skills and context, and how to build a culture that keeps people learning.
What you'll learn
How to deploy a shared agent, loaded with your company context, that everyone on the team can use from the tools they already work in
Where company knowledge should live so agents can actually navigate it, and why structure beats dumping everything in one place
Sharing skills across a team at three levels, from a single shared file to a maintained repository with named owners
The realistic adoption picture: you don't need everyone building, you need a focused group building things everyone else benefits from
What you won't get anywhere else
This answers the question a Cohort 1 CEO kept asking: how do I radiate this out to the rest of the organisation? We use real examples from teams in the room, including a public skills repository other companies copy, and the patterns that make a rollout stick instead of fizzle.
Week 421 Jul – 24 JulBuild software & showcase
7
Tue · 21 Jul · 2:30–5:00pm
Coding Agents
Claude Code, Cowork, Codex, or Cursor (your choice)
Write a clear, one-shot brief, hand it to a coding agent, and watch it build. No coding required. You experience directing an agent that already knows how to code, and the power of running several in parallel. Software teams ship a working prototype; everyone else ships a validation page to test demand.
What you'll build
A one-shot PRD: a brief so clear that a developer, an agency, or an AI agent could build from it without follow-up questions
A live, deployed prototype or validation page, built from your brief
First-hand experience managing more than one agent working in parallel
Something you can share with users, your team, or investors the same day
What you'll learn
The mindset shift: you're not learning to code, you're learning to direct an agent that already can
The one-shot brief format that prevents hours of fixes, and why the plan lives in a file the agent ticks through, not in the chat
Which tool fits which job: Claude Code and Cowork for custom builds, Lovable and Replit for quick prototypes
Directing an autonomous agent: when to let it run, when to step in, and how to course-correct without starting over
What you won't get anywhere else
I've logged well over 100 hours with coding agents, building prototypes, internal tools, landing pages, and full applications. You get the distilled version: which tool to use when, the prompting patterns that actually work, the mistakes that waste an afternoon, and the shortcuts that save one. This is not a tutorial you could follow on YouTube; it's guided building with someone who has done enough of it to know where things break.
8
Fri · 24 Jul · 2:30–4:30pm
Showcase
Demo day
The finale. Members of the cohort demo what they built, we celebrate the standout agents from across the four weeks, and we map out what to build next. You leave with a clear picture of what is possible well beyond the programme.
What's included
4 weeks • 8 live sessions • weekly guest speakers & office hours • yours to keep
4× Live Build Workshops
Tuesdays · 2.5 hrs
Each week you build a working agent from scratch, live with the cohort. An hour of teaching, then a guided co-build.
4× Tactics Sessions
Fridays · 2 hrs
Sharper craft on top of the week's build: security, skills, team rollout, and the techniques that make your agents better.
Guest Speaker Lunch & Learns
Thursdays
A weekly session with a specialist guest, going deeper on a topic that complements the week.
Weekly Office Hours
Grouped by department
Drop-in sessions by function to get feedback on your agents and see how others are solving the same problems.
1:1 Coaching with James
Optional add-on
Add a Coaching Package for three 1:1 or small-group strategy sessions on your specific agents and rollout.
Private Community
Four weeks inside a group with James and the cohort. Share wins, swap notes, and get unstuck between sessions.
Full Recordings & Guides
Every session is recorded, with step-by-step build guides, so you can catch up or go deeper any time.
Prompts, Templates & Frameworks
The mega-prompts, system instructions, skills, and agent frameworks you build are yours to keep and adapt.
Partner Perks
Discounts on Granola, Attio, and more.
Works with Claude, ChatGPT, Gemini, and whatever AI tools you already use.
Ready to build?
4 weeks. 8 live sessions. Skills and agents that stay with you.
