Claude Projects: Your First Persistent Workspace
From Theory to Practice
Section titled “From Theory to Practice”In Lesson 1, you understood why persistent context matters. Now let’s build one. Claude Projects Persistent workspaces in Claude.ai that bundle a knowledge base (uploaded documents), custom instructions, and chat history in one place. Every chat within a project automatically has access to the full project context. are the most concrete implementation of the “explain your job once” concept — a workspace that brings together knowledge, rules, and conversations.
What a Claude Project Is
Section titled “What a Claude Project Is”A Project consists of three elements:
| Element | What It Does | Analogy |
|---|---|---|
| Knowledge Base | Documents that Claude uses as reference | The shelf with the handbooks |
| Custom Instructions | Rules for behavior, tone, and format | The onboarding document |
| Chats | Individual conversations within the project | Meetings in the same office |
Every chat within a project automatically has access to the knowledge base and instructions. No copying, no explaining — the context is just there.
Important: Individual chats do not share their history with each other. Only the knowledge base and instructions are shared across the project. If you discuss something in Chat A, Chat B doesn’t know about it — unless you add it to the knowledge base.
Step by Step: Setting Up a Project
Section titled “Step by Step: Setting Up a Project”1. Create the Project
Section titled “1. Create the Project”Go to claude.ai/projects (or via the sidebar → “Projects”) and click ”+ New Project”. Enter a name and brief description.
Note: Claude cannot see the project name or description — they’re for your organization only. Everything you want Claude to know belongs in the Instructions or Knowledge Base.
2. Fill the Knowledge Base
Section titled “2. Fill the Knowledge Base”Click ”+” in the right sidebar and upload files:
| File Type | Formats | Limit |
|---|---|---|
| Documents | PDF, DOCX, TXT, CSV, HTML, JSON, EPUB | 30 MB per file |
| Spreadsheets | XLSX (requires Code Execution enabled) | 30 MB per file |
| Images | JPEG, PNG, GIF, WebP | 8000 × 8000 px |
What to upload? Anything Claude should reference when answering: style guides, project documentation, competitive analyses, data sheets, templates.
What not to upload? Sensitive data you don’t want to share with the AI provider. Check your plan’s privacy policy first.
3. Write Custom Instructions
Section titled “3. Write Custom Instructions”Click “Set project instructions” and write your rules. Here’s an example for a content team project:
You are a content strategist for [Company Name].
Context:- Audience: CTOs and VP Engineering at companies with 100-500 employees- Tone: authoritative but approachable (see Brand Guide)- Channels: Blog, LinkedIn, Newsletter
Rules:- Every blog post draft includes headline and meta description- Use the uploaded SEO keyword list- Flag claims that need fact-checking- Paragraphs max 4 sentences4. Start Working
Section titled “4. Start Working”Begin a new chat within the project. Claude immediately has access to all uploaded files and follows your instructions — without you having to repeat anything.
Knowledge Base: Strategies for Practice
Section titled “Knowledge Base: Strategies for Practice”Strategy 1: Reference Documents
Section titled “Strategy 1: Reference Documents”Upload the documents you’d otherwise copy-paste into every chat: style guides, process descriptions, templates.
Strategy 2: Context Anchors
Section titled “Strategy 2: Context Anchors”Summarize background knowledge in a short document that Claude uses as a foundation: “Who are our customers?”, “What’s our product strategy?”, “How do we use certain terms?”
Strategy 3: Living Knowledge Base
Section titled “Strategy 3: Living Knowledge Base”Update the knowledge base regularly. Remove outdated documents, add new ones. The knowledge base is the source of truth for the project — if it’s outdated, the answers will be too.
Custom Instructions: Three Patterns
Section titled “Custom Instructions: Three Patterns”Pattern 1: Role + Rules (most common)
Section titled “Pattern 1: Role + Rules (most common)”You are [role] for [context].Rules:- [Rule 1]- [Rule 2]- [Rule 3]Sufficient for most use cases. Clear, concise, maintainable.
Pattern 2: Workflow Instructions
Section titled “Pattern 2: Workflow Instructions”For every analysis, follow this process:1. Summary (2-3 sentences)2. Key findings (3 points)3. Recommended action4. Open questionsGood for recurring tasks with the same workflow.
Pattern 3: Context + Constraints
Section titled “Pattern 3: Context + Constraints”My context:- [Industry, team, product]
Output rules:- When uncertain: say so, don't guess- No recommendations without evidence- Plain English, avoid jargonFor projects where quality standards matter more than a fixed workflow.
How Personalization Layers Work Together
Section titled “How Personalization Layers Work Together”Claude offers three tiers that work independently or in combination:
| Tier | Scope | Purpose |
|---|---|---|
| Profile Preferences | All conversations, account-wide | Global context about you |
| Project Instructions | Single project | Project-specific rules and context |
| Styles | Per conversation or global | Tone and formatting (no content context) |
Profile Preferences provide the “who I am.” Project Instructions provide the “what this project needs.” Styles provide the “how it should sound.” Combining all three creates the strongest context you can build on Claude.
Availability by Plan
Section titled “Availability by Plan”| Plan | Projects | Knowledge Base | RAG | Sharing |
|---|---|---|---|---|
| Free | Up to 5 | Basic uploads | No | No |
| Pro | Unlimited | Full | Yes (automatic) | No |
| Team | Unlimited | Full | Yes | Yes (team) |
| Enterprise | Unlimited | Full | Yes | Yes (organization) |
On paid plans, the knowledge base automatically scales beyond the Context Window The span of text an AI model can 'see' at once — your entire conversation history plus the current input. Everything within this window influences the response. — Claude activates RAG Retrieval Augmented Generation — a technique where the AI model retrieves relevant information from a knowledge base before responding. This extends capacity beyond the context window. automatically and can process up to 10× more content.
Try It Yourself
Section titled “Try It Yourself”Exercise 1: Your First Project
Section titled “Exercise 1: Your First Project”Create a Claude Project for a recurring task from your workday. Write custom instructions using the “Role + Rules” pattern. Upload a reference document. Test with 3 typical requests.
Exercise 2: Iterate on Instructions
Section titled “Exercise 2: Iterate on Instructions”Use the project for a week. Note where Claude deviates from the desired behavior. Adjust instructions with targeted changes — one rule per problem. Observe whether results improve.
Exercise 3: Knowledge Base vs. Instructions
Section titled “Exercise 3: Knowledge Base vs. Instructions”Experiment: What belongs in instructions (rules, behavior) vs. the knowledge base (facts, references)? Move content between the two. Observe the difference.
Looking Ahead
Section titled “Looking Ahead”Claude Projects are one of several ways to build persistent context. In the next lesson, you’ll learn about Custom GPTs — OpenAI’s approach to the same problem, with its own strengths and trade-offs. The comparison helps you understand which tool fits which situation.