Platform · our product

AgentData: the semantic layer that lets AI agents query your data — safely.

Connect your databases read-only, auto-discover the business entities inside them, and let people and AI agents ask questions in plain language — answered locally, against your own data. No SQL. No data movement.

The problem

Everyone wants AI on their data. Nobody wants to hand an LLM the keys.

Organisations want AI agents and business users to ask questions of their data — but the data sits fragmented across databases, warehouses and files, and nobody wants to give an LLM raw access to it. Most GenAI pilots stall exactly here: the model is fine, the data context is missing.

The industry's answer is a semantic layer — a governed model of your business that grounds AI in what your data actually means. Enterprise knowledge-graph platforms (Stardog, Palantir-class tooling) prove the category works, at enterprise-programme cost: ontology teams, long implementations, contact-sales pricing.

Hand-building a semantic layer takes months of modelling work, and it's stale the day it ships. AgentData auto-discovers entities (Customer, Order, Product), metrics and dimensions across your systems, and puts them behind a governed review workflow — so the model of your business stays alive as your data changes.

Privacy by design

Only the model and the question ever reach the LLM.
Never your row data.

→ SENT

Entity & measure names

The semantic model — table and metric names, never contents.

→ SENT

Your question

The plain-language question being asked, in any language.

✕ NEVER

Row data

Stays in your database. Queries execute locally, results go straight to the user.

← BACK

Governed query

A reviewed, versioned query — executed against your own infrastructure.

Deterministic and explainable: every answer comes from a governed, versioned query — not text-to-SQL guesswork — so every number traces to its source. Runs where your data lives: self-hosted, on-premises or fully air-gapped, with local LLM backends (Ollama, vLLM) when data can't leave the building.
Capabilities

Built for agents. Governed for enterprises.

A.01

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.

A.02

Governed

Approve or reject discovered entities, version queries, full audit log — with query-approval workflows for sensitive answers.

A.03

Federated

One question across multiple sources — built-in federation, or scale out with Cube + Trino.

A.04

Conversational

Natural-language querying in any language, with conversation memory — for executives, not just analysts.

A.05

Standards-compliant

Emits Cube + dbt-semantic YAML — the model you curate is portable, not proprietary.

A.06

Auto-discovery

Connect → profile → classify → cluster into entities → emit YAML → human review. First entities typically the same day.

PostgreSQLMySQLSQL ServerOracleSnowflakeRedshiftSynapseS3 / GlueAzure BlobSaaS APIs & files — read-only, encrypted credentials
Where AgentData sits

The semantic-layer outcome. Without the platform programme.

AgentData is built for organisations that want AI grounded in their data this quarter — not after a knowledge-graph programme.

VS.01

Enterprise semantic platforms

Knowledge-graph platforms (Stardog, Palantir-class) are powerful but sized for enterprise programmes — ontology specialists, months of modelling, opaque pricing. Warehouse-native SaaS layers cover Snowflake/Databricks/BigQuery only, in their cloud, not yours.

VS.02

Hand-built semantic layers

dbt/Cube models written by hand give control, but take months of engineering and go stale the day the source schema changes — and still need an NL/agent access layer on top.

VS.03

AgentData

Auto-discovers the semantic model from your databases (first entities same day), human-reviewed, emits portable Cube + dbt YAML, agent-ready over MCP/REST from day one — across operational databases and warehouses alike, self-hostable, fixed-scope delivery by the engineer who built it.

Same category, honest scale: if you're a global enterprise with an ontology team, the heavyweight platforms are excellent. If you want governed, grounded AI access to your data in weeks — delivered forward-deployed — that's AgentData.
Where teams use it

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.

Contact

Let's scope your first outcome.

A free 30-minute discovery call — no sales pitch, just an honest conversation about what AI and good engineering can do for your business.

Book a Discovery Call

Pick a time that works for you. We'll talk through your goals, current systems and where the first measurable win is.

info@biskilled.com LinkedIn ↗ North London, UK · on-site & remote

Or send a message