Operator Workspace Blueprint: giving humans and agents one source of truth
How to structure a knowledge system and agent stack so your operating context builds up in one place instead of scattering across chats and docs.
who it's for: Operators and teams who've outgrown ad-hoc AI use and want a shared system underneath it.
Most teams adopt AI one chat at a time. Context lives in scattered histories and people's heads, so every agent starts cold and nothing carries over.
An Operator Workspace fixes this with a single source of truth that both humans and agents read from and write to. Set up well, each session leaves context the next one can use.
Start with a structured, plain-text knowledge base (we use an Obsidian/Markdown vault). It holds three things: SOPs (how work is done), decisions (what you chose and why), and project context.
Plain text matters because it's diffable, version-controlled, and equally readable by a person and an agent. Avoid locking your operating knowledge inside a SaaS you can't query.
Give each agent one clear job (research, drafting, review, or operations) rather than one do-everything assistant. Specialization makes behavior predictable and easy to trust.
Every agent reads from and writes back to the vault. Outputs aren't trapped in a chat window; they land in the source of truth where the next agent and the next person can use them.
The workspace pays off when work flows through it: a decision gets recorded, an agent drafts against it, a human reviews, and the result goes back into the vault.
Onboarding becomes reading the workspace instead of shadowing someone for weeks, because the operation is written down in a form both humans and agents can use.
Don't dump raw transcripts into the vault. Curate durable facts and decisions, or the useful parts get buried.
Don't build one giant agent. Don't store operating knowledge somewhere agents can't read. And don't expect a workspace tuned to one team to transplant to another without customization.
- ·Operating knowledge lives in plain text (diffable, version-controlled)
- ·Vault holds SOPs, decisions, and project context as distinct layers
- ·Each agent has one clear job, not a do-everything mandate
- ·Agents read from and write back to the same vault
- ·Work flows through the loop: record, draft, review, store
- ·Durable facts are curated; raw noise is kept out
- ·Onboarding is reading the workspace, not shadowing a person
Do I need Obsidian specifically?
No. The principle is plain-text, version-controlled knowledge that humans and agents can both read. Obsidian is what the studio uses, but the blueprint works with any Markdown-and-Git setup.
How many agents should I start with?
Fewer than you think. Start with two or three with clear jobs (say research, drafting, review), prove the loop works, then add specialists as real needs appear.