We sell to operations leaders at 50 to 500 person companies in the Pacific Northwest. Northwind Pro is discontinued and must not be positioned in any new opportunity.
Target market narrowed from national to Pacific Northwest. 47 prospects archived in the same change.
Build, review, and use knowledge together.
Connect Claude Code, Codex, Grok Bot, or any MCP client.
Connect through API or MCP without creating another silo.
Developers connect an agent or build Nicia into a product. Teams start from the documents they already rely on. Both write to the same governed record.
Connect first. Your Brain is created when you connect, and every agent you add reads and updates the same one.
Pick Claude Code, Codex, Grok Bot, or another MCP client, paste the one command Nicia shows you, and sign in when your agent asks.
Your agent saves what it reads as records, then updates those records when a second source says something new. Each change shows up before and after.
A new session, a teammate's agent or a different tool asks the same Brain and gets the current answer. You see exactly what it was served.
Building it into a product? Copy the build prompt and paste it into Claude Code, Codex, OpenCode, or any coding agent. It provisions a Brain per customer over the HTTP API.
Bring the few documents your team already relies on, not everything. Then have your agent record the rules and decisions they state, each citing the passage it came from.
Copy the import prompt and paste it into Claude Code, Codex, OpenCode, or any coding agent. The prompt is the whole procedure, so there is nothing to install first. Import is a copy, so your existing tools keep working exactly as they do today.
Notion, Docs, Drive and Confluence are editing surfaces built for people, and they are good at that. Their unit is a page, their API is designed around a person clicking, and nothing in them carries a typed field, a review step, or a record of why something changed. An agent pointed at them is reading a layout to guess at facts.
They never held the truth. They held documents about it, and a person did the reconciling. Hand that job to agents and the reconciling does not disappear, it just happens faster, in more places, with nobody watching. A document is a fine rendering and a bad database.
Wiring N agents to M tools is N × M links to build, authorise and keep correct. Routing them through one Brain is N + M.
Three tools, three integrations, and it works. This is the demo everyone gives.
Each one wires their own agent to their own accounts. Nobody agrees on which doc is current.
Two more tools got adopted. Every link is a credential someone holds and nobody audits.
Hosted runners join the laptops. Same tools, more endpoints, and now an outage has a blast radius.
Every agent reads one accepted answer. Every tool contributes to one place. The wiring stops multiplying.
Ask in plain language. The agent resolves it against the Brain's records and stages the whole batch as one change. Approve it once, and the moment it lands every surface that reads this Brain is current.
See how a change landsArchive every prospect outside the Pacific Northwest. We are changing our focus.
region across 1,284 recordsCompanies are handing work to agents and swapping models every few months, and nothing records what they've learned. Databases store rows, documents and agent memory store loose text, and agents built on them end up confidently out of date. A Brain is one governed record your people and agents build together. Change it once and everything that reads it is current.
Three sources. Three answers. One of them reaches a customer.
One change. Every agent current the same minute.
Open a branch and let agents rework the knowledge in parallel: a new pitch, a different pricing structure, a rewritten escalation policy. The version everyone else reads does not move. Propose the changes that earned it back to the main Brain and leave the rest on the branch.
Code got fast when changing it stopped being risky. Knowledge gets the same loop.
See how a proposed change landsReview is not a brake on your agents, it is the reason you can turn them loose. Every change arrives with its intent and its evidence. Approve the exact assertion or reject it, and what you accept stays connected to the source it came from.
See how Review worksNorthwind Pro — available, all segments.
Northwind Pro — discontinued. Offer Atlas.
Every rule and decision says what it rests on: another decision, an assumption, a passage in a document. When that changes, the record reopens and reads as needing review until a person revises it or says it still holds. Every answer carries citations and a receipt for exactly what was served, so the receipts name every agent that relied on the old version.
See what reopensOperations leaders at 50 to 500 person companies in the Pacific Northwest. Northwind Pro is discontinued.
0198f3a2-7c41Every answer an agent reads through a Connection is recorded with the exact sources behind it, pinned to the versions the reader saw. That is how a reopened belief finds the agents that relied on it. Open any one of them and run a context check: it reports where the sources contradict each other, where the same passage was sent twice, and where you paid for words that carried nothing.
Point one agent at a few documents and you can check the first answer it gets.
See how reads are recordedOne source says Northwind Pro is available in all segments. Another says it is discontinued.
icp-definition · product-statusThese two sources share 84% of their wording. The agent was shown both.
q3-pricing · pricing-reviewEvery team that gives its customers their own context ends up writing the same four things badly. We know because they keep describing them to us in the same words.
Start in Nicia, connect the desktop agents your team already uses, or provision one Brain per tenant from your backend. All three paths meet at the same review, policy, and provenance boundary.
Open the activation guidecurl -X POST "$API/v1/brains/$HANDLE/context" \
-H "authorization: Bearer $AGENT_KEY" \
-H "content-type: application/json" \
-d '{
"prompt": "Who are we selling to right now?",
"consumerId": "sales-agent",
"format": "text"
}'
# cited context + consumption receiptA Brain is the unit, and it is the one you already bill on. Review, receipts, the API, MCP and full export are in every tier including the free one, because a Brain nobody can audit or leave is not worth having.
10 Brains included.
Enough for a team, a handful of clients, or a product in development.
Plus $40 per Brain, up to 50 Brains.
Agencies and consultancies with a Brain per client.
Plus $12 per Brain, up to 500 Brains.
Products that give every customer their own Brain.
Thousands of Brains and up.
AI companies reselling a Brain per end customer. Anyone whose fleet outgrew our limits. Talk with us
You arrived with a folder. You leave with a model.
Export any Brain and you get plain markdown with your frontmatter intact, a catalog, a greppable activity log, revision history, and an AGENTS.md that teaches any agent how to read the whole thing. No proprietary envelope, on every tier including the free one.
Bring a folder, a wiki export, or just a description of what your agents keep getting wrong. We build the Brain on the call, point an agent at it, and you watch it answer from your own material. Thirty minutes, no deck.
You keep the export either way, whether or not you buy anything.
Start with your agent, your documents, or your product. Every path builds the same thing: one governed Brain that your agents improve and your people steer.