Lesson 435 of 2116
Spaces: Building Team Knowledge Bases In Perplexity
Spaces are Perplexity's project containers — system prompts, files, and shared chat history. They turn the search engine into a research workspace.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1What a Space is
- 2spaces
- 3system prompt
- 4file uploads
Concept cluster
Terms to connect while reading
Section 1
What a Space is
A Space is a folder with a system prompt, a set of attached files, optional URL allow-lists, and a shared thread history. Inside a Space, Perplexity follows the instructions you set and weights your uploaded files higher than the open web. Outside a Space, it forgets all of that.
What Spaces are good for
- 1Ongoing research projects with returning context (a market scan, a thesis, a customer)
- 2Team knowledge bases where multiple people query the same docs
- 3Persistent personas — 'always answer as a skeptical M&A analyst'
- 4Document Q&A with the open web as a fallback when the docs are silent
- 5Course-style learning where you upload syllabus + readings
Where Spaces fall short
Spaces are not a full document management system. There is no permission hierarchy inside a Space — anyone with access sees everything. Files are not chunked or indexed the way a purpose-built RAG system would do them. For a 1000-document corpus, a custom pipeline still wins. For 5-50 docs, Spaces is the fastest setup on the market.
Compare the options
| Need | Spaces | Custom RAG | ChatGPT Project |
|---|---|---|---|
| 5-50 docs, fast setup | Best | Overkill | Strong |
| Cited answers by default | Best | Build it | Toggle on |
| Hundreds of docs, search quality | Stretches | Best | Stretches |
| Team-shared workspace | Yes | Build it | Workspace plan |
| Web fallback when docs silent | Yes | Build it | Yes |
Build a Space in five minutes
- 1Pick one current project. Don't make a generic 'work' Space
- 2Write a 4-line system prompt: role, audience, citation rule, fallback rule
- 3Upload the 10 most relevant docs
- 4Run three test queries you'd realistically ask
- 5Iterate the system prompt until the answers feel right
Key terms in this lesson
The big idea: a Space is a Perplexity that knows your project. Build them per-project, not as one mega-space, and treat the system prompt as the contract.
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Spaces: Building Team Knowledge Bases In Perplexity”?
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 · 10 min
The CLAUDE.md File: Project Persona And Rules
CLAUDE.md is how you tell Claude Code what your project values, what your team's conventions are, and what it should never do. It is the single highest-leverage config you write.
Creators · 10 min
Your First Soul: A Ten-Minute Hello World
A minimal soul, a personality, a first message, a peek at memory. The point is not the soul — the point is feeling how OpenClaw thinks. Step 1 — Define the soul A soul lives in a folder, typically under `souls/`, and is defined by a small file that names it, gives it a persona, and points at the model it should use.
Creators · 9 min
What Perplexity Is: Search-Augmented LLM, Not A Chatbot
Perplexity is built around the idea that every answer should cite its sources. Treating it like ChatGPT misses the point — and the reliability gap that comes with it.