A Practical Course for Everyone

Enjoy the Sun with AI

Use Claude Cowork to automate indoor computer grunt work so you can spend more time outside.

Reconciliation. Triage. Reporting. Briefs. Evidence assembly. Compliance prep. Pipeline reviews. Morning dashboards.

5workshops
7.5hours
120prompts
Zerocode
Illustration of a person working with AI to automate desk tasks

What You Will Learn

  • Set up a CLAUDE.md identity that makes Cowork understand your department, tools, and terminology
  • Automate a 30-minute reconciliation task in under 5 minutes using department-specific data
  • Connect Cowork to Jira, Confluence, and Glean via MCP and build cross-system briefings
  • Handle your department's worst-day backlog: triage 30-50 items, produce a prioritized action plan
  • Build your own custom skill using /skill-creator and schedule it to run automatically
  • Wire skills into automation chains: skill to verify to publish, running before you arrive
  • Recognize the 5 failure modes (miscalculation, misclassification, hallucinated references, overconfidence, missing context)
  • Build a morning dashboard that pulls overnight updates and summarizes what needs your attention
  • Honestly audit your automations: keep what saves time, kill what doesn't

This course does not teach AI theory, prompt engineering tricks, or how to "10x your productivity." It teaches you how to use a specific set of tools for a specific kind of work: structured, repetitive desk tasks where the input is messy and the output needs to be organized, verified, and delivered.

This course is for you if...

  • You spend hours on structured, repetitive tasks: reconciliation, triage, formatting, reporting
  • You work in operations, support, sales, compliance, finance, chargebacks, or admin
  • You are not a developer and do not want to write code
  • You want to understand what AI automation can and cannot do before committing

This is probably not for you if...

  • You need guaranteed accuracy without human review
  • You work with raw PCI data or unredacted PII
  • You want fully autonomous automation with no oversight
  • You expect polished output that does not need checking

What to Expect

Honest limitations

Cowork is a research preview. These are current realities, not edge cases.

Math

LLMs predict what numbers look right. Every formula needs independent verification.

Outbound communication

Can draft but should never send without human review.

Compliance and audit decisions

Not captured in audit logs. First-draft prep only.

Sensitive data

Never feed raw PCI data, unredacted PII, passwords, or credentials.

Running offline

Requires laptop awake and Claude Desktop running. No laptop, no automation.

Start with Workshop 1

90 minutes. By the end, you will have a working CLAUDE.md identity, completed a reconciliation with your department's data, learned the CTOC framework, and made a Monday Promise to automate one specific task.

No prerequisites. No code. Just a Claude Pro or Max subscription, SSO access, and an empty folder on your computer.

Start Workshop 1 →

Not ready to commit? Browse the prompt library — 29 tested prompts organized by department and workshop.

Browse the Prompt Library →

Frequently Asked Questions

Do I need to know how to code?

No. The entire course uses Cowork's desktop interface. You write plain-English prompts and work with files (CSV, Excel, Word, PowerPoint). No terminal, no scripts, no developer tools.

How much does Cowork cost?

Claude Pro is approximately 18 GBP/month. Max is 80-160 GBP/month. Cowork consumes significantly more tokens than regular chat. Heavy users on Pro report hitting limits within days. Max is more practical for daily use.

Is my data safe?

Cowork runs in a sandboxed environment and only accesses the folder you grant. However, prompt injection via uploaded documents is a demonstrated attack. Every workshop includes verification exercises and security best practices.

How much time will I actually save?

It depends on the task. Settlement reconciliation drops from 30-60 minutes to 2-3 min plus 5-10 min review. Some workflows save 20+ minutes per run. Others save nothing once you account for prompt iteration and error checking. The course teaches you to measure before you claim.

Will this work on Windows?

Yes, with caveats. Windows support launched February 2026 and is less stable than Mac. The course works on both platforms.

See all FAQs →