Lesson 71 of 2116
Projects and Spaces — Persistent Context Is the Future
Claude Projects, ChatGPT Projects, Notion AI, Perplexity Spaces. How persistent context changes AI from search box to actual assistant.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1Why standalone chat has a ceiling
- 2Claude Projects
- 3ChatGPT Projects
- 4Notion AI
Concept cluster
Terms to connect while reading
Section 1
Why standalone chat has a ceiling
One-off conversations are forgetful. You paste your resume, you discuss your goals, you refine a cover letter. Two days later you open a new chat and start from scratch. Every AI lab's answer to this is the same: persistent 'containers' with shared context — Projects, Spaces, or Custom GPTs.
The four major container products
Compare the options
| Product | What you add | How AI uses it | Cost |
|---|---|---|---|
| Claude Projects | Docs, instructions, knowledge files | Every chat in the project grounds in those files | Claude Pro+ |
| ChatGPT Projects | Files, instructions, sidebar chats | Shared memory across project chats | ChatGPT Plus+ |
| Perplexity Spaces | PDFs, websites, custom instructions | Searches inside Space sources first; builds memory over time | Free, Pro for more |
| Notion AI (in a database) | Your entire Notion workspace | AI answers from your docs, pages, databases | Notion Business |
| Custom GPTs (ChatGPT) | Knowledge files + instructions + actions | Reusable personas you can share publicly | ChatGPT Plus+ |
When a Project beats a chat
- A research paper — upload your readings, talk to them over weeks.
- A job search — resume, target companies, sample cover letters, persistent coaching.
- A coding project — codebase loaded as context, AI knows your patterns.
- A class — syllabus, lecture notes, study guides, reusable across all your work.
- A book — chapters so far, character notes, style guide.
A Claude Project setup template
One thoughtful Project setup is worth more than a hundred casual chats.
Project name: Senior Thesis — AI Ethics
Project Knowledge (files you add):
- Syllabus.pdf
- Core readings (6 PDFs)
- Draft outline v1.md
- Advisor's feedback (Feb 12).txt
- My own notes.md
Project Instructions:
You are helping me write a 25-page thesis on AI alignment.
My writing voice is academic but not stiff.
Favor counterarguments over confirmation.
Always ask a follow-up question before generating long prose.
Cite sources from the Project Knowledge when possible.Perplexity Spaces vs Claude Projects
Compare the options
| Feature | Claude Projects | Perplexity Spaces |
|---|---|---|
| Primary strength | Reasoning over your docs | Web search grounded in your docs |
| File support | PDFs, markdown, code | PDFs, URLs, text |
| Can search the web too | Yes (with Cowork on) | Yes, natively |
| Memory across chats | Project-wide | Per-space, growing |
| Good for | Deep thinking on curated material | Research expanding into new sources |
Notion AI as a different beast
Notion AI doesn't have 'Projects' — your Notion workspace IS the project. The AI sees all your docs, databases, and pages (that it has access to). When you ask it something, it queries across your Notion and Google Drive (via connections). On the Business plan and above, that includes shared team knowledge.
Custom GPTs — the oldest and weirdest of these
ChatGPT's Custom GPTs were first (late 2023). Three years later, they're more mature: they can call external APIs (Actions), use files as knowledge, and be shared publicly. They're closer to 'mini apps' than Projects. If you want a reusable 'recipe extractor' or 'DBT coach' you can share with friends, Custom GPTs are the only product that does this easily.
The pattern underneath all of them
- 1Add persistent context (files, instructions, memory).
- 2Grant the AI selective access to that context.
- 3Every conversation starts with that context pre-loaded.
- 4You build value over time instead of re-pasting.
- 5You can often share the container with teammates.
“The shift from chat to Projects is like the shift from email to shared docs. Less ephemeral, more accumulating.”
Key terms in this lesson
The big idea: the future of AI isn't more chats — it's fewer, deeper containers. Invest in one or two Projects for work that truly compounds. Start adding knowledge today.
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Projects and Spaces — Persistent Context Is the Future”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 38 min
Building a Personal AI Stack for School and Career
Assemble the four or five AI tools that actually belong in your daily life. A tested template for the stack that earns its keep.
Creators · 30 min
Perplexity Comet — the AI browser
Perplexity Comet is a full web browser that treats AI as a first-class citizen. It reads, summarizes, and acts on pages you visit.
Creators · 35 min
Codex CLI: OpenAI's Answer to Claude Code
Codex CLI is OpenAI's open-source terminal coding agent. Look at how it compares to Claude Code, what it does uniquely, and why it matters to non-Anthropic shops.