Claude for Work: From Assistant to Agent
Projects, Cowork, skills, plugins, connectors and reliable delegation.
Turn scattered working notes into a reviewed weekly research or status brief; understand when to use chat, Cowork and more advanced agent features.
2–3 hours suggested practice · Free, written and self-paced · No certificate or video promised
Your learning outcomes
- Choose the right Claude mode
- Create reusable project instructions
- Evaluate skills, connectors and plugins
- Delegate a multi-step deliverable
- Test quality and approval boundaries
0 of 5 activities checked
Completion checkmarks are stored only in this browser. Your answers are not uploaded.
Choose chat, project or Cowork
The task, not the feature list, should determine your starting mode.
Follow along
- Open Claude on an account that supports your intended feature; verify availability in your own interface.
- For a single question use chat; for reusable context consider a Project; for a multi-step deliverable explore Cowork.
- Choose the weekly briefing example and make a three-column list of available sources, required output and approvals.
- Create an empty sandbox/project workspace or use fictional notes, not real client files.
A mode decision and safe practice workspace.
Copy and adapt this prompt
I need a recurring Friday review of three fictional project updates. Recommend whether to use Claude chat, a Project, or Cowork, based on required file handling, recurring context, review, permissions, and complexity. Provide the simplest working setup.You can explain why the chosen mode fits the task; unsupported options are marked optional.
Remember: Cowork, connectors and local file access vary by account, device and administrator settings.
Write project instructions that actually help
Reliable results start with a stable brief and clear boundaries.
Follow along
- Define the audience, scope, voice, source hierarchy, report format and success standard.
- Ask Claude to first produce a plan and list what it cannot verify.
- Use project instructions or a reusable note; keep date-specific material out of permanent rules.
- Test the same brief against two different fictional updates.
Versioned instructions, a short sample brief and gap log.
Copy and adapt this prompt
You are my weekly project briefing assistant. Audience: a busy project sponsor. Use only the provided fictional notes. Sections: summary, completed work, blocked work, owner questions, next-week risks. Cite each note used. If a date, owner or outcome is missing, say UNCONFIRMED. Never send anything or modify source files. Ask for my approval before any external action.The report distinguishes evidence from suggestion and passes a second sample.
Remember: Do not hide missing context or silently infer ownership.
Add skills, plugins and connectors deliberately
A packaged workflow is useful only when tools and permissions match a real need.
Follow along
- List data the workflow truly needs and which approved source owns it.
- Inspect supported Skills/plugins and connector permissions in your Claude account; features vary.
- Draft one reusable 'project update analyst' skill with input schema, output format and checks.
- Run it first without external write access; compare before and after for improvement.
Skill specification and least-privilege access checklist.
Copy and adapt this prompt
Draft a reusable project-update skill specification. Inputs: weekly notes and a project glossary. Outputs: status summary, risk list, source list, missing-information questions. Include minimum access scope, approval rules, three evaluation cases, and a version/date line. Make no claims that reading a prompt enforces security.The skill can be run manually without installing additional software.
Remember: Plugins may bundle subagents and connectors; install only trusted components you understand.
Delegate a complete reviewed report
A complete outcome is more valuable than an impressive-looking prompt.
Follow along
- Supply the approved fictional source pack and your reusable brief.
- Ask Claude to plan the report, draft a one-page narrative and a structured action table.
- Inspect the document or exported result; compare numbers, owners and dates with sources.
- Request fixes and save the revised file under a clear version name.
One checked brief, action tracker and a list of corrections.
Copy and adapt this prompt
Using the provided fictional sources, prepare a one-page executive report plus a table of action items. In the report distinguish confirmed facts, interpretation, and open questions. Before finalizing, run a second pass specifically looking for unsupported claims, mismatched dates, or duplicate tasks. Never send the report.No unverified fact is presented as a confirmed result.
Remember: AI-created documents and tables still require actual human review.
Make the next run reliable
Repeatability requires an error plan, not just saved instructions.
Follow along
- Test a complete update, one missing status and a contradictory due date.
- Log output quality and review time for each case.
- Add a stop rule, approval step and escalation message.
- Only after testing, explore scheduled tasks or supported automated handoffs.
A repeatable, human-reviewed runbook.
Copy and adapt this prompt
Create an operating runbook for this weekly reporting workflow. Include purpose, trigger, permitted sources, step-by-step execution, quality rubric, approval owner, failure messages, duplicate prevention, log fields, cost considerations, and a 7-day improvement plan.The workflow remains safe if a source is unavailable or a connector fails.
Remember: A scheduled instruction is not a guarantee that a service action ran successfully.
Keep your work. Use it again.
Test the workflow on a second example before connecting accounts or automating. If you need feedback on a real project, bring your sanitized brief to a private working session.
All five activities checked. Revisit the quality gates on a fresh example to validate your work.
Product documentation and next steps
Tools and plan entitlements can change. Check your provider and workspace access before following interface instructions.
Existing AI Teachers resources: Agent to Outcome · All free written courses
Updated 2026-10-25. Paid group cohorts, certification, and live dates are not represented as currently available.