Objects and relationships
What your business runs on and how it connects, mapped from your systems.
A live model of how your business runs. It defines the levers that drive your results and lets people and agents act on them safely.
What your business runs on and how it connects, mapped from your systems.
Calculations and predictions computed on your objects.
The changes people and agents can make, with approvals, write-back, and reconciliation.
Policies, interviews, and documents, each linked to the objects they explain.
Dock 3 only takes six trucks before noon. Anything booked after that waits for the afternoon crew.
Roles decide who can see and change every object, property, action, and document. Agents act with the permissions of the person they work for.
AI FDE Builds every part with your team, and keeps it running.
The canonical objects that make up your business and how they connect to each other with typed relationships.
| Property | Type | Source | As of |
|---|---|---|---|
| promised_date | Date | ERP | Nov 1, 9:12 |
| value | Money | ERP | Nov 1, 9:12 |
| status | Open, Allocated, Shipped, Delivered | Canopy actions | Nov 1, 9:40 |
| delivery_terms | Text | Contract, section 6 | Mar 3 |
Enrich your objects with functions that make first class the logic of your business. From expressions to powerful ML models, you can encode the levers that actually drive your results.
(value − product.unit_cost × quantity − shipment.freight_cost) ÷ value
The changes people and agents are allowed to make. Each action has its inputs, its checks, who approves it, and the system it writes back to. After it runs, the ontology confirms the change happened.
Policies, interviews, documents, and agent traces, linked to the objects they explain. Agents cite it, and AI FDE uses it to see what should move into the model next.
Orders delivered more than two days after the promised date earn a credit of 5% of the order value.
Dock 3 can't take more than six trucks before noon. Anything booked into a late-morning slot usually slips a day.
Every object, property, action, and document has roles that can see it or change it. Agents act with the permissions of the person they work for. Because permissions live in the ontology, every application and workflow enforces them the same way.
| Account manager | Logistics planner | Supply agent | |
|---|---|---|---|
| Order.margin | View | Hidden | View |
| Contract.pricing | View | Hidden | Hidden |
| Shipment.carrier | View | Edit | View |
| Employee.pay_rate | Hidden | Hidden | Hidden |
| Expedite shipment | No | Run | Propose |
It extends the ontology as your business changes. Every change comes with its evidence, and your team approves what ships.
AI FDE maps your systems onto object types, interviews the people who do the work, and drafts the first expressions and actions.
New sources, new object types, new rules. AI FDE proposes each change, and your team reviews it like any other.
Before a model's output lands on an object, AI FDE backtests it on outcomes you already know.
When agents keep escalating the same case, AI FDE drafts the action, its approvals, and its permissions for your sign-off.
New policies, interviews, and traces get linked to the objects they explain, so nothing important sits in a folder.
Agents, applications, and workflows inherit the ontology’s actions, permissions, and audit trail.
Agents and people change your systems only through actions you've defined, with approvals where they matter and a check that each change happened.
Every read and every write is checked against roles, down to a single property.
Every run records what was read, what was proposed, who approved, and what changed.
Because those controls hold, agents can work whole queues, apps ship in days, and workflows span teams.