Claude Basics & Applied Practice

8 min

Basic Chat Workflow

1. 1State the context
   What is this task, and who is it for
2. 2Give a clear instruction
   What exactly you want done
3. 3Provide reference material
   Paste in documents, data, or examples
4. 4Review and follow up
   If it's not right, add conditions instead of starting over

Key takeaway: Chat is an iterative conversation you refine with follow-ups, not a one-shot request.

8 min

A Prompt Is a Work Instruction

Think of a prompt as handing a task to a colleague: the less context they have, the more clearly you need to explain it. A vague instruction produces a vague result.

Key takeaway: Prompt quality directly determines output quality.

10 min

The T-C-R-F Framework

1. 1Task
   What you want AI to do, concrete enough to check against
2. 2Context
   Why this matters, who it is for, any constraints
3. 3Reference
   The material, examples, or style you provide
4. 4Format
   The structure, length, and tone you expect

Key takeaway: All four T-C-R-F elements give AI enough to produce a usable result.

10 min

Prompt Practice: Rewrite a Vague Instruction

Key takeaway: Rewriting a vague topic into T-C-R-F is the most basic, most effective prompt exercise.

6 min

Document Analysis: Starting from a Meeting Note

Document analysis is one of the most common work scenarios: meeting notes, reports, and customer feedback all need to be read, organized, and questioned. Here's a reusable six-step process.

Key takeaway: Document analysis needs a repeatable process, not ad hoc effort each time.

10 min

Six Steps: Understand, Organize, Analyze, Question, Produce, Verify

1. 1Understand
   What this document is about and its purpose
2. 2Organize
   Break it into issues, owners, and a timeline
3. 3Analyze
   Find patterns, risks, and relationships
4. 4Question
   Identify gaps and things worth following up on
5. 5Produce
   Turn it into a summary, report, or recommendation
6. 6Verify
   Trace key facts and numbers back to the source

Key takeaway: The six steps give document analysis a consistent rhythm so nothing important gets skipped.

8 min

Fact / Analysis / Unknown

Key takeaway: Splitting output into fact, analysis, and unknown is the most basic review tool.

8 min

Evidence Verification

• Can every conclusion be traced back to a specific passage in the source?
• Do the numbers match the source, rather than being rounded or mistyped?
• Are there contradicting passages that AI may have missed?

Key takeaway: A conclusion that cannot be traced back to the source should be flagged as unverified.

6 min

Projects in Practice: Building a Workspace

Put frequently used templates, style guides, and background material into a Project so every future task continues from the same context.

Key takeaway: Put reusable material into a Project to stop re-pasting it every time.

6 min

Artifacts in Practice: Producing an Editable Deliverable

When a task needs repeated edits before final delivery (a report, a table), Artifacts let you keep editing without regenerating the whole thing.

Key takeaway: Artifacts suit final deliverables that need repeated edits.

8 min

Cowork Practice: Delegating a Complete Task

Using the four practice files (Meeting_A, Meeting_B, Sales_Report, Customer_Feedback), practice delegating a fairly complete task to Claude and producing: three main issues, evidence, open items, recommendations, a one-page executive summary, and a Fact / Analysis / Unknown breakdown.

Key takeaway: Cowork practice is about complete delegation and structured output, not turn-by-turn chat.

8 min

Plan Before You Execute

• Clarify scope and delivery format before execution starts
• Have AI outline its plan first, and confirm before it continues
• Break complex tasks into checkable stages instead of one long run

Key takeaway: Confirming the plan before delegating avoids most rework later.

8 min

Reviewing Cowork Output

After the output is produced, review it using Human–AI Review principles: can facts be traced back, is the analysis reasonable, were open items missed — only then deliver the executive summary.

Key takeaway: Cowork output still needs the same human-review discipline.

8 min

Code / Automation Concepts

Using Sales_Report.csv, practice finding: missing values, duplicates, completion rate, months that missed target, longest response time, lowest satisfaction score, and possible relationships — without claiming causation, only describing observed correlation.

Key takeaway: Automated tasks still need a human to judge correlation versus causation.

6 min

Tool Selection Review

Revisit Module 1's decision flow: single-turn tasks use Chat, multi-step multi-source tasks use Cowork, recurring well-defined tasks use Code. Which mode does each of today's four exercises map to?

Key takeaway: The same decision flow applies to any new task you encounter.

10 min

Your Personal Use Case Canvas

Pick a task that actually recurs in your own work and fill out the Use Case Canvas: current process, frequency, time spent, pain points, the AI help you want, the suggested mode, and the consequence and human-review method if it goes wrong.

Key takeaway: The Use Case Canvas is the key step that connects the course back to your real work.

6 min

Exit Ticket

Before the course ends, fill out the Exit Ticket: the work you most want AI help with, its frequency and time cost, an initial tool category, and what you want the follow-up department interview to cover.

Key takeaway: Exit Ticket data feeds the follow-up department interviews and use-case inventory.