Cortex features

Every capability that ships with Cortex — grouped by the job it does. Two agent types, citation-backed grounding, enterprise governance, model choice, and delivery paths from internal tool to embedded product.

Two agent types, one platform

Knowledge Agents

Answer strictly from the sources you connect, with a citation on every response.

Skills Agents

Codify multi-step expert workflows so anyone on the team can run them consistently.

Agent composition

Chain agents together — a Knowledge Agent can feed a Skills Agent that produces a deliverable.

Grounded in your knowledge

Citation-backed answers

Every fact links to the exact document and passage it came from.

Broad source coverage

PDF, Word, PowerPoint, Excel, SharePoint, Notion, Drive, S3/GCS, databases, transcripts, audio and video.

Freshness controls

Schedule re-indexing per source; agents always answer from the current knowledge state.

Enterprise-grade by default

SSO, RBAC, audit logs

Shipped on day one — not gated behind an enterprise-tier upsell.

EU data residency

GDPR compliant. SOC 2 in progress. Your IP never trains a public model.

Per-agent access policy

Scope who can query, edit, or deploy each agent — down to a single user.

Model-agnostic by design

Best model per job

Route each agent to the foundation model that fits — GPT, Claude, Llama, Mistral, and more.

Swap without rebuilding

Change the underlying model and keep the agent, sources and evaluations intact.

Open-weight in-country

Run open-weight models fully inside your Swiss/EU boundary when required.

From workspace to product

Self-serve build

Domain experts ship agents themselves — no engineering backlog required.

White-label & embed

Ship agents in your own product, under your own brand, or expose them via API.

Real-time deploy

Preview, publish, iterate — deploy behaviour and content changes without redeploy cycles.

Keep exploring