Your company already knows the answer. It just can't find it.
Hippo turns what your business already knows into one connected picture: meetings, emails, spreadsheets, the things in people's heads. Ask a question in plain English and get the answer with the evidence behind it. The decision intelligence big companies take for granted, without their budget.
Nothing to install. One connector.
# Add Hippo as a connector. Once, per machine.claude mcp add --transport http hippo \ https://hippo.gisanalytics.uk/mcp# Sign in with the key we issue you, then just talk to it:# "remember this"# "what do we know about Acme?"// claude_desktop_config.json{ "mcpServers": { "hippo": { "type": "http", "url": "https://hippo.gisanalytics.uk/mcp" } }}// .cursor/mcp.json{ "mcpServers": { "hippo": { "url": "https://hippo.gisanalytics.uk/mcp" } }}Every write reviewed before it lands
Connect it once
Add Hippo as a connector in Claude, Cursor, or anything else that speaks MCP. There is no library to import and no pipeline to change.
Access is by invitation while we are in beta. Ask us for a key and we will set your organisation up.
Tell it to remember
Say remember this at the end of a piece of work. Hippo records what happened, the facts worth keeping, who was involved and what is still open, attached to the project it concerns rather than buried in a transcript.
The tool is push.
Ask it anything, months later
“What do we know about Acme?” returns every fact, decision and open action attached to Acme, gathered from every session that ever touched it, each with the evidence behind it.
The tool is pull.
See how it connects
Ask for a picture and you get the map: what touches what, and on what basis. picture draws it, status tells you the connection is healthy and whether your writes go live or wait for review.
In daily use at
Dept of Information Studies
Built for <teams>
that have to show
their working
Most tools give you an answer. Hippo gives you the answer and the trail behind it: which document, whose report, which decision it followed from, and who approved it.
That is the difference between an assistant you have to double-check and a record you can hand to a board, a client, or an auditor.
Institutional memory, with structure.
The thing small teams are missing: one connected record of your people, clients, projects, decisions and the evidence behind them, built from the documents you already produce.
It records not just what was decided but why: who proposed it, what evidence supported or contradicted it, what followed. You can ask in plain English. The audit trail assembles itself.
Knowledge fragmentation
Decision opacity
Governance gap
Transcripts, email, exports and notes become structured records. Each one keeps a link back to the document it came from.
Everything gets linked to whatever it relates to. The result looks like your business, not a database.
A question pulls in everything connected to it: prior context, and the evidence for and against. The answer arrives with its sources attached.
Recommendations become actions, and every outcome links back to the decision that produced it.
One connected map of how the business runs.
This is the real viewer, embedded live. It shows a made-up example company: its people, clients, projects, decisions, evidence, and how they all connect.
About this data: the company shown is made up. Nothing about a client business appears on this site.
Specific Q&A
Ask a question, get the answer with its evidence attached: who decided, when, and on what basis. Not a document search: the answer comes from what the company actually knows.
Qualitative advice
Recommendations argued from the firm's own context: prior decisions, commitments, cash position, with supporting and contradicting evidence attached.
Simulations
See the knock-on effects before they happen: which projects, people and revenue are exposed, traced along the firm's real relationships rather than guesswork.
Company check-up
A structured review of the graph itself: stale decisions, contradicted evidence, orphaned actions, concentration risk. The business, audited by its own structure.
A working session with GIS Analytics takes one hour: we map a slice of your company into the graph, and you ask it questions.
In the real world
The graph changed the way we see the whole operation. For the first time we can look at the entire ecosystem in one place, how our kitchens, projects and partners connect, and act on it.
Taz Khan MBE · Founder, London's Community Kitchen
London's Community Kitchen runs a café, a water brand, a youth academy and a climate hub, all in service of one food-security mission. We mapped the programmes, partners, decisions and the evidence behind them into one connected picture.
- 778nodes in their graph
- 4ventures in one graph
- First clientoutside our own walls
Answers you can take to a review.
Each decision is a first-class node linked to its context, its evidence on both sides, the people involved and the actions that followed. The audit trail is not written after the fact; it is the shape of the data.
Property graph, not RDF.
The data model treats nodes and relationships as first-class objects, each carrying properties of its own. It is close to how a founder describes their business: this client, on this project, with that contract.
The choice was made early, in consultation with the UCL team: property graphs trade some of RDF's semantic rigour for queryability, tooling maturity and a model the team can extend without recompiling an ontology.
Dept of Information Studies · not GIS Analytics staff
Talk to the team.
Hippo is a working system, available now. If you run a small business, ask for the one-hour walkthrough: we map a slice of your company into the graph and you question it. Academic groups with adjacent work, and funders looking at this space, are welcome too.