AgentData: shared definitions. Clearer answers.
Connect your databases and define what customers, orders and measures mean across them. AgentData provides a governed business model for consistent questions and natural-language access, alongside your existing reporting tools.
See AgentData in use.
Your business questions cross systems. Your answers should too.
Customer, finance and operational questions often span several systems. Without shared definitions, teams can get different answers from the same records. AgentData brings those definitions into a governed business model.
A semantic layer is a shared model of business concepts and measures. It gives reports, applications and optional AI clients a consistent way to ask questions.
AgentData helps discover business entities and measures, with human review of the proposed model. The definitions still need to reflect your business rules and be maintained as sources change.
Separate query planning from access to results.
Entity & measure names
The semantic model — table and metric names, never contents.
Your question
The plain-language question being asked, in any language.
Row data
Source data stays in your database; queries return authorised results. If you connect an external AI client, review which results that client can receive.
Governed query
A reviewed, versioned query — executed against your own infrastructure.
Governed data access for people and applications.
Agent-native
Built-in MCP server and REST API with per-user keys: list · describe · query_metric · query_nl. Claude, ChatGPT and your own agents connect directly.
Governed
Approve or reject discovered entities, version queries, full audit log — with query-approval workflows for sensitive answers.
Federated
One question across multiple sources — built-in federation, or scale out with Cube + Trino.
Conversational
Natural-language querying in any language, with conversation memory — for executives, not just analysts.
Standards-compliant
Emits Cube + dbt-semantic YAML — the model you curate is portable, not proprietary.
Auto-discovery
Connect → profile → classify → cluster into entities → emit YAML → human review. Discovery timing depends on your sources and schema.
Fit the access layer to the data you have.
Start by reviewing your source systems, business definitions and access requirements. We can demonstrate AgentData on an agreed sample schema and discuss where it complements your existing reporting stack.
Product discovery does not replace data ownership or validation. Your team reviews the business model; deployment and connected clients determine how query results are handled.
From BI queue to conversation.
- Ad-hoc executive questions — answered without a BI backlog
- Governed data access for AI agents over MCP
- Data-API services and report generation on live data
- Lead enrichment and CRM integration across sources
AgentData also powers our consultancy work: it's the AI-ready access layer we deploy inside data engineering engagements when plain-language access is part of the outcome.
What are you working on?
Fragmented data, a process to automate or a system to build — tell me what needs to change.
Let’s talk
Book a free 30-minute chat with me. We’ll see whether I can help.