Core Frameworks

The Good Prompt

SDR Framework
What it is

A 3-part structure for every prompt: Stage (your role + context), Define (the task), Rules (tone, format, examples).

Why it works

Claude performs better when it knows who you are, what you need, and exactly how to deliver it. Less guesswork = better output.

Common mistake

Jumping straight to the task without context. "Write a report" gives Claude nothing. "I'm a marketing lead preparing a Series A deck — write a 5-page market report with citations" is complete.

Memory trick

SDR = film set. Set the scene → Direct the action → Run the rules. Every good film has all three.

The 4D Framework

AI Fluency Model
What it is

Academic framework (Dakan + Feller) defining 4 competencies for effective AI collaboration. Delegation · Description · Discernment · Diligence

Each D explained

Delegation — who does what (human vs AI)
Description — how clearly you communicate
Discernment — evaluating AI output critically
Diligence — using AI ethically, staying accountable

Common mistake

Skipping Discernment — trusting AI output without reviewing it. Claude can be wrong. Always check.

Memory trick

Delegate the task → Describe it clearly → Discern the output → Do it right. Four verbs in order.

Research Mode

vs. Web Search · Extended Thinking · Enterprise Search
What it is

An agentic, multi-step process. Claude plans → searches repeatedly (each search builds on the last) → synthesizes → cites every source. Extended thinking auto-activates.

Use it when

You need a comprehensive report from multiple sources, with citations, that would take hours manually. Market research, competitive analysis, project briefs.

Do NOT use when

Web search → quick single fact
Extended thinking → deep reasoning, no external data needed
Enterprise search → internal org docs, Slack, emails, policies

Memory trick

Research goes OUT (web). Extended thinking stays IN (Claude's head). Enterprise searches YOUR stuff (internal docs).

Key Features

Projects

Persistent Workspace
What it is

Dedicated workspaces that remember your files, instructions, and context across every conversation inside them. Claude never starts from zero.

Use it when

Ongoing work (not one-off questions), reusable reference materials, consistent tone/format requirements, or team collaboration.

3 permission levels

Can view — read + chat, no edits
Can edit — full collaboration, change instructions
Owner — controls everything including access

RAG mode

Auto-activates when knowledge base fills up. Expands capacity up to 10×. Claude retrieves only what's relevant — experience feels the same.

Common mistake

Uploading files with vague names like "document1.pdf". Claude uses filenames to understand content — name them descriptively.

Skills

Expertise Packages
What it is

Folders of instructions, scripts, and resources that Claude loads dynamically to perform specialized, repeatable tasks — like expertise packages.

Two types

Anthropic Skills — built-in, auto-invoked. Examples: Excel, Word, PowerPoint, PDF creation.

Custom Skills — you or your org uploads them. Example: brand voice review, quarterly analysis workflow.

To enable

Settings → Capabilities → toggle on Code execution and file creation first, then Skills. (Required dependency — Skills won't work without it.)

Common mistake

Thinking Skills = Plugins. They're different. Skills = repeatable workflows. Plugins = external data connectors.

Artifacts

Interactive Outputs
What it is

Interactive, reusable outputs Claude builds — calculators, trackers, charts, dashboards — not just paragraphs. Functional tools you can actually use.

Why it matters

Unlike text responses, Artifacts persist. A content tracker with columns for topic, status, hook, publish date is something you reference repeatedly, not read once.

Common mistake

Thinking Claude only outputs text. When you need a working tool — ask for one. "Build me a tracker" not "write me a list."

Best for

Dashboards, planners, comparison tables, calculators, anything you'll reuse or interact with.

Cowork — Desktop App Features

Cowork

Desktop App Only — NOT Claude Code
Folder Access

Claude reads and writes to folders you share. Only those folders — nothing else on your machine.

Scheduled Tasks

Recurring work on a timer — daily briefings, weekly roundups, inbox triage. Catches up if your computer was off.

Subagents

Background workers Claude spins up for complex tasks. It breaks work into subtasks, runs them in parallel, gives you one result.

Dispatch

Continue Cowork conversations from your phone. Hands tasks to your desktop — files, apps, connectors — while you're mobile.

Browser Use

Claude navigates Chrome pages, interacts with sites, pulls data directly into tasks. Great for scraping competitor pricing across 10 sites.

Computer Use

Claude clicks, types, opens apps — like you would. Research preview, Mac only. Permission prompt required per app. Priority order: connectors → Chrome → screen.

Exam Memory Tricks
SDR (Stage · Define · Rules)  ·  4D (Delegate · Describe · Discern · Diligence)  ·  RAG = 10× capacity  ·  Research goes OUT · Extended Thinking stays IN · Enterprise searches YOUR stuff  ·  Skills ≠ Plugins  ·  Cowork ≠ Claude Code
Quick Recall — Exam Cheatsheet

If the exam asks about…

Claude 101 · Module 1
Topic The answer The trap
Good Prompt elements Stage + Define + Rules (SDR) Only 2 of 3 is a bad prompt
4D Framework origin Dakan (Ringling) + Feller (UCC) research It's academic — not just Claude lore
4D = what order? Delegation → Description → Discernment → Diligence Don't confuse Description with Discernment
When to use Research Multi-source synthesis, citations, comprehensive report Not for quick facts — use web search instead
When to use Extended Thinking Complex reasoning with NO external data (math, logic, code) Not for anything requiring web sources
When to use Enterprise Search Internal org knowledge only — Slack, emails, docs, policies Not for public web information
RAG mode trigger Auto-activates when knowledge base approaches context limit You don't turn it on — it's automatic
RAG capacity boost Up to 10× Not 5×, not unlimited — 10×
Project permissions View / Edit / Owner View = can chat; Edit = can change instructions
Skill types Anthropic (auto) + Custom (uploaded by you/org) Skills ≠ Plugins (plugins = external data)
Skills requirement Code execution + file creation must be ON first Skills won't load without that dependency
Cowork vs Claude Code Cowork = desktop app. Claude Code = terminal CLI. They are completely separate products
Computer use availability Research preview · Pro/Max plans · Mac only Not GA, not all plans, not Windows yet