Meet Cortex
An answer from your own data shouldn't require a ticket to a technical team. Ask, explore, automate — Cortex turns natural language into governed queries, workflows and notebooks over your own data. The whole platform, one conversation away.
Chat with Your Lakehouse
Ask questions in plain language and get answers grounded in your actual data, not generic model knowledge.
Build Workflows
Describe what you want to happen and Cortex routes the request to the right AI OS workflows.
Create Notebooks
Generate analytical notebooks — Python and SQL over your lakehouse — straight from a prompt.
Cortex is the part you talk to. Ask about your own data in ordinary language, get a chart or a document, set something running — without knowing where anything is stored or which team owns it. It is the everyday way into everything else on this page.
Read this if you're anyone who wants an answer from the organisation's data without learning the organisation's data.
Cortex is Scrydon's sovereign conversational intelligence platform: a natural-language interface to the AI OS. Speak to your data, build and trigger workflows, create analytical notebooks, and interrogate your ontology in plain language — grounded in your enterprise data rather than generic model knowledge.
Most people can't get answers from their data without going through a technical team. Cortex removes that barrier. It understands your enterprise knowledge graph, so questions get precise, context-aware answers; and because it sits on top of the AI OS, a request in plain language can build a workflow, run analysis, or trigger a process — with every conversation logged and attributable.
Cortex in the Scrydon platform
One integrated, sovereign architecture. Here is where Cortex sits — highlighted against the full stack it works with.
The AI OS for Humans & AI Agents
Ontology & Semantic Layer, one connected model for your data, knowledge & processes
Combining the best of data lakes, data warehouses and search
AI agents, workflows & automations that execute across your systems
Integrate across A2A, MCP, legacy systems and data sources
Secure domain federation, trusted data sharing, and cross-boundary intelligence
Sovereign Foundations
Cortex in depth
Cortex is the natural language interface that bridges human conversation and the full capabilities of the AI OS. Speak to your data, trigger complex workflows, and interrogate your knowledge graph — all in plain language, with no technical barrier.
- Ontology-aware: Understands the structure of your enterprise knowledge graph, enabling precise, context-sensitive answers.
- Workflow triggers: Describe what you want to happen and Cortex automatically routes the request to the right Human + AI Orchestrator processes.
- Multi-modal input: Accepts text, documents, and structured data, grounding responses in your actual enterprise data rather than generic LLM knowledge.
- Audit trail: Every conversation is logged, attributable, and reviewable — meeting compliance requirements for regulated industries.
Speak to your data — and act on it
Cortex is the natural-language front door to the platform. Instead of dashboards and queries, you have a conversation: ask, explore, build, and trigger — all grounded in your ontology and lakehouse.
One conversation, two forms of the same answer. The retrieval steps are part of the reply: which ontology was queried, for which object types, and how many records came back — so the answer can be checked rather than taken on trust.
Chat with your lakehouse — Ask questions in plain language; answers are grounded in your real data.
Build workflows — Describe an outcome and Cortex assembles and triggers the right AI OS workflow.
Create notebooks — Generate Python and SQL notebooks over your lakehouse from a prompt.
Ontology-aware — Understands your knowledge graph for precise, context-sensitive answers.
Audit trail — Every conversation is logged, attributable, and reviewable for compliance.
No technical barrier to your own data
When anyone can ask, explore, and act in plain language, data stops being the preserve of a few specialists. Because Cortex is grounded in the ontology and governed by the AI OS, that accessibility comes without sacrificing accuracy, control, or auditability.
What a conversation can — and cannot — do
A conversational interface is only trustworthy if it is clear what it will and will not do on your behalf. Cortex is not a chatbot bolted onto a database: every turn is a governed request through the AI OS, so the answer you get, the workflow you start and the notebook you generate are all bounded by the same identity, policy and audit as any other action on the platform.
| You ask | What Cortex does | What governs it |
|---|---|---|
| A question about your data | Resolves it against the ontology and lakehouse, answers in business terms and cites the source | Your own data permissions — it retrieves what you may read, nothing more |
| "Start the month-end reconciliation" | Assembles and triggers the matching AI OS workflow | The workflow's approval gates and scoped identities, unchanged |
| "Give me a notebook for this" | Generates Python and SQL over the lakehouse | Runs inside your perimeter, under your identity |
| Something outside your access | Does not see it, and says so | Policy enforced fail-closed, before the model is involved |
| Anything at all | Logs the turn, the retrieval and the action | The immutable audit trail, reviewable per conversation |
The refusals are deliberate. Cortex does not answer from generic model knowledge when the question is about your organisation — if the data is not there, it tells you rather than guessing. It does not act with broader permissions than the person asking. And it does not keep a private log: what a conversation retrieved and triggered is the same evidence a reviewer or regulator can inspect afterwards, which is what makes plain-language access safe to hand to everyone rather than a few specialists.
Frequently asked questions
What is Cortex?+
Can I chat with my lakehouse and data?+
Can Cortex build workflows and create notebooks?+
Is Cortex grounded in our data or just an LLM?+
Is every conversation audited?+
Explore the platform
Prefer to write? Email hello [at] scrydon.com and we will get back to you.
Partners
