Palantir AI skills
Palantir AI skills are delivered by Bonfire Terminal's on-device AI. Grounded in your Palantir project context, local intelligence helps structure investigations, explain datasets, and prepare analytics narratives, ensuring sensitive data work stays private on your own hardware, never a public cloud.
What Bonfire can do in Palantir
Real actions from the Palantir API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List objects | Ontology | GET /api/v2/ontologies/{ontology}/objects/{objectType} |
| Get object | Ontology | GET /api/v2/ontologies/{ontology}/objects/{objectType}/{primaryKey} |
| Search objects | Ontology | POST /api/v2/ontologies/{ontology}/objects/{objectType}/search |
| Aggregate objects | Ontology | POST /api/v2/ontologies/{ontology}/objects/{objectType}/aggregate |
| Apply action | Ontology | POST /api/v2/ontologies/{ontology}/actions/{actionType}/apply |
| Execute query | Ontology | POST /api/v2/ontologies/{ontology}/queries/{queryApiName}/execute |
| Create dataset | Datasets | POST /api/v2/datasets |
| Create transaction | Datasets | POST /api/v2/datasets/{datasetRid}/transactions |
Palantir agents in action
On your machine, not a SaaS
Bonfire Terminal
- Your keys & data stay on your device
- Perpetual license — no per-seat SaaS fee
- Any connected model — Claude, GPT, Gemini or Grok
- Offline Llama for local, private reasoning
- Driven from chat you already use
Cloud AI middleman
- Keys & data pass through a third-party server
- Recurring subscription, usage caps
- Model locked to the vendor
- Yet another dashboard to log into
Palantir — questions
Can Bonfire automate Palantir?
Yes. Bonfire runs on your machine, holds your Palantir credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Palantir API to run the actions you ask for in chat.
Does my Palantir data go to the cloud?
Bonfire runs on your desktop and keeps your keys local — it isn't a SaaS holding your data. Only the specific request you approve is sent to your chosen AI model.
Which AI models can I use?
Any connected model — Claude, GPT, Gemini or Grok. A fully offline Llama model runs locally for private reasoning but can't reach live APIs.