Wirewalk Instituteof AI
ven-120 Basic AvailableFlagship

Claude for Professionals

For analysts, team leads and IT staff who want to use Anthropic's Claude on real client work: choosing the right setup, writing briefs that hold up, building reusable workspaces, verifying numbers and claims, connecting tools safely and turning a pilot into a defensible rollout.

Level
Basic
Study time
12 hours
Lessons
15 in 6 modules
Exam
20 questions

About this course

This course follows Cardinal Ridge Benefits Partners, a composite 185-person employee benefits firm in Columbus, Ohio, through its first Claude pilot. Shadow AI use is already widespread, 430 client renewals are due by January 1, the COO wants hours per renewal cut by 15% before next season, the compliance officer will not let protected health information near a tool without a business associate agreement, and she wants to know why the firm needs Claude when Microsoft Copilot Chat is already licensed and covered. Module by module you choose a plan and data rules, write briefs that stop Claude from claiming what the firm does not offer, design a renewal workspace that keeps clients' data apart, catch a loss ratio that is wrong by 12.8 points before it reaches the client, connect Microsoft 365 without opening an exfiltration path, and present measured pilot results that fall short of the target.

Every lesson works through a full example on realistic materials, compares tools such as Claude Team and Enterprise against Microsoft Copilot Chat and Microsoft Copilot, Claude Projects against a Copilot Chat agent, the Claude Microsoft 365 connector against Copilot Chat in Outlook, chat code execution and Claude for Excel, connectors and Claude in Chrome, scripts and the API, and gives you a template you can use at work this week. Six Decision Labs and a capstone simulation put you in the role of the analyst, the proposal manager, the IT manager and the pilot lead, with business metrics, cliffhangers and several endings. Your capstone, the final lesson, is a Claude working playbook for your own team or the case firm, opened by a one-page decision memo, with rubric feedback from Ellery (practice, not part of the certificate). Product specifics are stated as of the review date and linked to Anthropic's documentation. Completion and a passing exam score earn a Wirewalk Institute of AI certificate of completion and assessment; it is not an Anthropic certification.

What you will be able to do

  • Choose a Claude plan, seat mix, data-handling rule, model tier and mode for each workflow, weighing data class, contract terms, budget and tools you already license, and record it in a setup decision record
  • Write structured briefs with context, audience, delimited materials, examples, an output specification and claim rules, and show each passes a checklist on at least three inputs
  • Verify facts and figures from long documents, web research and client-ready deliverables with quote-first extraction, not-found reporting, citation checks and a pre-send check
  • Configure a Project, a skill and memory settings for a recurring multi-client workflow so no client's data reaches another client's output, with limited edit rights and a maintenance routine
  • Analyze business data with Claude's code execution by profiling, defining, computing and reconciling to a known figure, diagnose definitional errors, and stress-test the recommendation's assumptions
  • Select the least powerful surface or connector for a task and identify its prompt-injection, permission and data-exposure risks, with a mitigation and owner for each
  • Draft an admin baseline and a pilot scorecard that separates measured results from projections and sets license costs against what they return, and decide which workflows stay in the apps, become scripts or are briefed for the API

Syllabus

6 modules · 15 lessons · about 12 hours

Module 1: Before Client Data Moves: Choosing the Claude Setup

A third of the firm already uses personal AI accounts with client data, and Microsoft Copilot Chat is already licensed: choose the plan, data rules, models and modes for a pilot that compliance can sign.
2 lessons
  1. Personal, Team or Enterprise: Where Client Data May Go
  2. Matching Model and Mode to the Work: Haiku to Fable, Search to Research
  • Decision Lab · 12 minThe Shadow AI SurveyA third of the firm already uses personal AI accounts, some with client data. Choose how to respond, which tool to buy, and what to tell a client whose counsel wants answers in writing.

Module 2: Briefs That Produce Usable Drafts

Turn one-line requests into tested briefs for RFP answers, client letters and long plan documents, without letting Claude claim what you do not offer.
3 lessons
  1. From One-Line Requests to Briefs: Context, Audience and Success Criteria
  2. Structure, Examples and Output Specs That Make Drafts Consistent
  3. Reading a 214-Page Plan Document Without Missing the Amendment
  • Decision Lab · 12 minThe RFP Due FridayDraft a 112-question broker-of-record response with Claude in nine days, survive a late addendum, and decide what you are willing to send under your firm's name.

Module 3: Workspaces for Recurring Work

Design the Projects, skills and memory settings behind 430 renewal packets, and decide between artifacts and Office add-ins for client-ready deliverables.
2 lessons
  1. Projects, Skills and Memory: Designing the Renewal Workspace
  2. From Analysis to Client-Ready Deliverables: Artifacts or Office Add-ins
  • Decision Lab · 10 minThe Workspace That LeakedSet up sharing, memory and the Project design for 25 people drafting renewal packets, then deal with what the design lets through.

Module 4: Numbers and Claims You Can Defend

Analyze claims experience with code execution, research a regulatory question with checked citations, and stress-test a recommendation the night before the client meeting.
3 lessons
  1. Renewal Analysis with Code Execution: Profile, Define, Compute, Reconcile
  2. Research Memos You Can Defend: Search, Research and Citation Checks
  3. Hard Calls: Stress-Testing a Recommendation with Effort and Reasoning
  • Decision Lab · 15 minThe 84% ProblemThe night before a client strategy meeting, a loss ratio Greg got from Claude disagrees with the carrier's by 12.8 points, a regulated report lands in your inbox, and the client's CFO wants a straight answer on a federal rule.

Module 5: Connecting Claude to Where the Work Lives

Use the Microsoft 365 connector, Office add-ins, Claude Desktop, Claude in Chrome and Claude Code where each fits, and contain prompt injection by design.
2 lessons
  1. Connectors and MCP: Meeting Prep from Outlook, SharePoint and Teams
  2. Choosing the Surface: Desktop, Chrome, Office Add-ins and Claude Code
  • Decision Lab · 12 minThe Carrier Portal ShortcutAccount managers want a browser agent on nine carrier portals and account executives want Claude to send email for them. Decide what to switch on, then face an inbound email written for your AI.

Module 6: From Pilot to Practice

Set the admin baseline, report measured pilot results separately from projections, buy seats against measured use, decide what scales, becomes a script or is briefed for the API, and assemble your capstone playbook.
3 lessons
  1. The Admin Baseline: Identity, Data, Features and Connectors
  2. Measuring the Pilot and Deciding What Moves to Scripts or the API
  3. Capstone: The Claude Working Playbook
  • Decision Lab · 15 minDecember 10Present a pilot that missed its target to a COO setting next year's budget, on the morning an incident lands on your desk.
  • Capstone simulation · 30 minRenewal SeasonRun Cardinal Ridge's Claude pilot from the shadow AI survey in August to the budget decision in December: setup, workspace, verification, connectors, a night-before crisis and the number you put in front of the COO.

Exam and certificate

The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Anthropic. Product and company names are trademarks of their respective owners.

More in AI Models and Vendors

All 22 courses in this track
ven-001 Free intro Available

Your First Hour with ChatGPT, Claude and Gemini

A hands-on hour with ChatGPT, Claude and Gemini, told through one small business racing a deadline. Set up an account with a privacy setting you chose, decide what never goes into a personal account, write prompts that produce usable drafts, use files and web search, catch confident mistakes before they go out, and pick the assistant that fits how you work.

1 h · 7 lessons Free intro
ven-110 Basic Available

ChatGPT and the OpenAI Platform for Professionals

A practical, current tour of ChatGPT as a professional tool: choosing a plan and model, prompting well, analyzing files, researching with citations, using images and voice, organizing work in projects and memory, connecting apps and plugins, delegating multi-step work to ChatGPT Work, and knowing which admin and privacy controls matter. Ends with clear guidance on moving a workflow to the OpenAI API.

8 h · 15 lessons See price at checkout
ven-130 Basic Available

Google Gemini and Workspace AI

A practical tour of Google's AI stack as of October 2026: the Gemini app and Google AI plans, Gemini inside Gmail, Docs, Sheets, Slides, Meet and Drive, Deep Research, Gemini Notebook (formerly NotebookLM), Gems, image and video generation, Workspace admin and data protections, and Google AI Studio as the bridge to the API.

7 h · 15 lessons See price at checkout