A practical workshop for executives
AI Leadership Lab
Turn your business data into a report you can trust, then build the routine that produces it.
- Time commitment
- 2 days · 09:00-17:00 · 13 learning hours
- Learning format
- 13 modules, with guided practice
- Experience needed
- No coding background required
Inside the programme
Start with a decision you make regularly. Work through the modules in order, using the included fictional company data.
Before the workshop
The practice pack contains Northstar Services data, templates and worked examples. Complete the prework 48 hours before class.
Download practice pack- Download and unzip
Keep an untouched copy. Open PREWORK.md and complete it 48 hours before class.
- Check your tools
Confirm Claude App, Code Desktop, Skills and local routine access. Install Node.js 22+.
- Choose one decision
Bring a recurring business question. Use fictional data or information approved by your organisation.
What you’ll take away
A report, a reusable method and a plan to test in your organisation.
- Produce a cited CEO/CTO report with reproducible calculations
- Create and test a reusable Skill and read-only evidence agent
- Build, verify and pause a local scheduled reporting MVP
- Create a business initiative plan with options, budget and scenarios
- Measure value and define three accountable 90-day AI pilots
Full agenda, workshop guidance and source references
Build the report. Check the evidence. Make the decision.
A hands-on workshop for CEOs, CTOs, founders and department leaders who want to build a useful reporting MVP themselves. Begin in Claude App, then use Claude Code to create a narrow agent and a local scheduled workflow. No prior coding experience is assumed; you will inspect and run guided commands.
Use a fictional company, Northstar Services, to connect business KPIs, system health and business planning. Approved organisational data is optional. Each block below opens a full tutorial with numbered steps, copyable prompts, saved outputs, verification and troubleshooting. The tutorials are public. Enrolled learners can save progress to their account; visitors save step checks in their browser.
Start here
Download the complete practice pack (ZIP). Unzip it, read PREWORK.md and keep an untouched copy. The pack contains two reporting periods, source definitions, templates, starter/completed Skills and agents, a deterministic calculator, failure exercises and facilitator answers. Inspect the answer key only after your first attempt.
Complete prework 48 hours before the workshop: sign in to Claude App and Code Desktop, confirm Projects/Skills and local routine access, install Node.js 22+ from its official site, and choose a recurring decision. Confirm approved data and any read-only connector with your organisation. Use fictional local files if no connector is approved; record live integration as not completed.
Day 1 - Claude App: from decision to reusable method
| Time | Module | Saved output |
|---|---|---|
| 09:00-09:30 | 1. Choose an executive decision | Task card and baseline |
| 09:30-10:30 | 2. Understand AI and choose an approach | Use-case decision card |
| 10:30-10:45 | Break | |
| 10:45-12:00 | 3. Write precise instructions | Three tested prompts |
| 12:00-13:00 | Lunch | |
| 13:00-14:00 | 4. Build an executive Project | Context and source-refresh checklist |
| 14:00-15:00 | 5. Produce a verified report | Cited brief and calculations |
| 15:00-15:15 | Break | |
| 15:15-16:15 | 6. Create a reusable Skill | Installed Skill and test outputs |
| 16:15-17:00 | 7. Select the automation MVP | Agent canvas and acceptance tests |
Day 2 - Claude Code: from method to tested MVP
| Time | Module | Saved output |
|---|---|---|
| 09:00-09:15 | Recap | One success and one failure |
| 09:15-10:30 | 8. Set up Code and source access | Local run and permissions record |
| 10:30-10:45 | Break | |
| 10:45-12:00 | 9. Build an extraction agent | Read-only agent and six tests |
| 12:00-13:00 | Lunch | |
| 13:00-14:15 | 10. Build and schedule the report | Report, routine history and recovery checks |
| 14:15-15:00 | 11. Build a business initiative plan | Options, budget and scenarios |
| 15:00-15:15 | Break | |
| 15:15-16:15 | 12. Evaluate value and plan adoption | ROI scenarios, policy and three pilots |
| 16:15-17:00 | 13. Demonstrate and hand over | Peer-checked handover and next action |
The agenda describes teaching time, not a booked event. Cohort invitations confirm dates, timezone, venue and facilitators. Short explanations alternate with practice; approximately 80% of the time is hands-on.
What success looks like
You can trace a report claim to its source, reproduce its arithmetic, show a real Skill/agent invocation, demonstrate an unchanged rerun and inspect an actual scheduled execution. You leave with a business initiative plan and three pilots with owners, measurements, cost limits and stop criteria. Reports stay drafts until reviewed by a person.
The required schedule runs locally: Claude Desktop must be open and the computer awake. A saved schedule is not evidence that it ran. Cloud routines are an extension for laptop-independent work and require separate source-access and cost decisions. Claude subscriptions and usage are separate from workshop enrolment; availability depends on plan and admin settings. No automated report delivery, production system changes or payment integration is included in the practice workflow.
Source mapping and further reading
The Udemy source contains 17 lectures: 16 relevant topics and one bonus-links lecture excluded from teaching. These original exercises adapt the strategic themes and the supplied 13-module framework; they do not reproduce course videos or transcripts. View the full lecture mapping, also included in the ZIP.
- AI Leader: Generative AI & Agentic AI for Leaders & Founders - Udemy
- Proposed two-day framework
- Claude Skills, custom agents and local schedules
Source outline and official documentation checked 12 October 2026. Facilitators recheck interfaces and feature access before each cohort. Completion is formative learning and participation, not an accredited qualification or a production-readiness certificate.
Bring your team
Explore every tutorial at your own pace, or request a facilitated cohort. Enrolled learners save progress to their account across devices.
Your starting point
Bring a laptop, approved Claude App and Claude Code Desktop access, Node.js 22+, and the fictional practice pack. Complete prework 48 hours before class. Feature access depends on plan and organisation settings; no coding experience is assumed.
Who you’ll learn with
AI Sentinels Academy · facilitators confirmed with your cohort
Enquire about team training →