AI that answers from your governed data model — and shows its work
Your agents get a typed, permission-checked map of your business instead of raw tables — and every answer they give opens into the plan that produced it.
Point an AI at raw tables and it guesses which column means revenue, in which currency, for whom. A confident wrong number looks exactly like a right one.
SemanticFed gives it a published model to bind to, and stores the plan behind every answer — so any number can be opened and checked.
AI-native by architecture, not bolted on
Four architectural choices that make AI a first-class part of SemanticFed rather than a chat window on the side.
Answers bind to your published model
Agents work from your published entities, metrics and relationships, so a query names fields that really exist — not ones that merely sound right.
Agents get your permissions, not new ones
Every action is checked against the same roles and workspace limits a person faces. An agent is just another signed-in caller, with no private door.
Every answer opens into its plan
Each run keeps which sources it touched, which filters reached them, the join order and estimate versus actual — so a disputed number is checkable.
An API agents can already drive
Everything in the product is reachable through one permission-checked GraphQL API, so agents, the command line and the SDKs do what a person can.
From intent to a governed action
Walk the path a request takes. Select any stage to see what happens there and what backs it.
Stage 1 of 5 · Connect
Register sources and watch their health
Databases, warehouses, lakes and APIs are catalogued, validated and health-checked on a recorded lifecycle.
Each source moves through draft, connected, degraded, disconnected or disabled, and every health check records a verdict, a latency and a message. People and agents read the same recorded history, so a degrading source is visible before anyone queries it.
What the AI in SemanticFed actually does
Pick an area, then open any capability for the detail and how it works.
Where the AI shows up
The places AI meets the work in SemanticFed, from your own agents to the query engine underneath them.
MCP & external agents
A Model Context Protocol server that hands your whole governed model to an agent, under your own identity.
- 40 tools for sources, health, models, metrics, relationships, queries, runs and policies
- Two guided recipes: build a model end to end, and author, govern, run and inspect a query
- Acts with your account and your permissions — grant agent access deliberately
See it as a real scenario
Every AI capability above shows up in a concrete SemanticFed story. Open one to read the full walk-through.
Let an AI agent run your data platform40 tools, guided recipes and your live catalogue — under exactly the permissions you already have.Read the story
Make every AI answer openable, not just plausibleEach run stores join order, what was pushed down to which source, and estimate against actual cost.Read the story
Keep AI from becoming a way around your access rulesAgents checked against the same roles and workspace limits as people, with no private door for automation.Read the story
Start modelling from a draft instead of a blank pageTurn a connected source into reviewable draft entities, metrics and relationships. Publishing stays human.Read the story
Catch a degrading source before your analysts doHealth history reconciled into a status change on a cadence, with the source owner notified.Read the story
Get caching suggestions from your own run historyHot, slow, repeated queries surfaced with a suggested cache setting and the evidence. You apply it.Read the story
Catch a new PII column the day it appearsLikely-sensitive fields flagged with a deny policy that stays switched off until a person approves it.Read the storyAI you can actually let near your data
An AI-native product has to be governable. These are the controls SemanticFed puts between an agent and your data.
One place where permission is decided
Every operation declares the action, resource and scope it needs, checked in one single place for people, scripts and agents alike. There is no second path around it.
Workspace isolation on every write
Writes are filtered to your workspace and must match exactly one record, so an identifier leaked from another tenant resolves to nothing. Agent calls included.
Provenance you can open
Every run keeps which sources were touched, which filters reached them, the join order, and estimate against reality — so a disputed number is verified, not argued about.
Nothing becomes AI-only
Modelling, publishing, querying and policy changes can all be done by hand. Automation is an accelerator, never the only route.
Confirmation before irreversible actions
Deleting an entity or archiving a published model is treated as a different kind of act from reading one, with an explicit confirmation step for agents.
Row and column policy when a query runs
Row, column and entity policies with allow or deny effects, defined once and attached to a model or an entity, for people and agents alike.
Models
SemanticFed uses the shared platform AI runtime rather than a bespoke integration, so credentials and cost stay in one place and no model choice is baked into the product. Bring-your-own-key is not offered.
- The shared platform AI runtime
- Provider-switchable by design
- Your own agent's model, when it drives SemanticFed over MCP
The honest answers
Through the Model Context Protocol server: your agent signs in as you and gets 40 tools, two guided recipes and your live catalogue. Underneath sit the typed model, cheapest-first planning, real queries against your own sources, and a stored plan per run.
Put SemanticFed’s AI to work
Your agents get a typed, permission-checked map of your business instead of raw tables — and every answer they give opens into the plan that produced it.