Galde

AI with Palantir AIP and the Ontology

We model the objects, relationships and actions of your business in the Ontology, build operational applications and take AI use cases with AIP into production, with permissions, evaluation and human oversight.

The Ontology, at the centre of everything

The Ontology is the model of your business inside Foundry. Applications, analysts and AI agents all work on it, with the permissions of the data. That is why it deserves the most attention: every later use case is built on it.

What we do

Ontology design

Objects, relationships and actions that reflect how your operation really works.

Operational applications

The screens, alerts and actions your team uses on the Ontology every day.

Agents and automation with AIP

Tightly scoped AI use cases, connected to the Ontology with the right permissions.

Integration through the OSDK

To use the Ontology from your own applications, outside Foundry.

Evaluation and guardrails

How AI responses are evaluated and where human oversight is needed.

With MVP60™

The first use case reaches production in 60 days, and every technical decision is documented so your team can maintain it.

Frequently asked questions

What is the Ontology and why does it matter?

It is the model of your business inside Foundry: objects, relationships and actions. Applications and agents work on it, with the permissions of the data.

How do you take an AIP use case into production?

By scoping the case tightly, connecting it to the Ontology with the right permissions, evaluating its responses and keeping human oversight where the risk calls for it.

Can we use the Ontology from our own applications?

Yes, through the OSDK, which lets you work with the Ontology from applications outside Foundry.

All our Palantir lines of work

Our articles on Palantir

What we learn in every implementation, explained for the people who have to decide.