Governed Context for AI Agents

Turn AI agents into governed teammates that can investigate live data, reuse trusted context, and keep monitoring the business with clear boundaries.

Apply for Access Read the Docs

AI and agents

AI-Native

Altertable brings governed data, business context, and tools into one system, with both built-in AI capabilities and MCP-native access for your own agents.

Unified Context

Unify data and business context in one place, so every query runs with the definitions and logic behind it.

Scheduled Task

Schedule tasks to check key metrics, investigate changes, and carry out recurring data work automatically, without waiting for someone to ask.

Tools All the Way Down

In Altertable, data, metrics, charts, queries, and actions can all be exposed as MCP tools, giving agents a structured, governed way to work across the full system.

Scoped Agent Access

Altertable brings OAuth and DCR to MCP so agents can discover, register, and connect with secure, scoped access instead of brittle shared credentials.

Model-Agnostic

Altertable is built to work across models and providers, so we can use the best LLM for each job without changing your data layer.

What AI and data teams get

Agents that inherit trusted data, visible guardrails, reusable context, and always-on monitoring without a separate automation data stack.

Agents inherit trusted context

Agents use the same lakehouse, metrics, permissions, and saved work as BI and SQL, so their answers start from context your team already trusts.

Bring the agents you already use

Connect Claude, GPT, internal copilots, or custom agent frameworks without rebuilding your data layer for every model or vendor.

From answer to always-on watch

When a question should keep being answered, turn the investigation into a scheduled task that watches the same trusted metrics.

Controls every agent inherits

Set permissions, credential access, visibility, and auditability once at the lakehouse layer, then let every agent workflow inherit the same guardrails.

Core AI context capabilities

Governed agent access, responsive investigation loops, visible previews, and context that compounds over time.

Agents connect with guardrails

Claude, GPT, custom agents, and internal tools can work from scoped access and the same permissions your team already uses.

Interactive reasoning loops

Agents need to inspect, query, preview, and follow up without waiting on stale exports. Keep multi-step investigation responsive on live business context.

Preview before work spreads

Let agents preview queries, proposed insights, notifications, and follow-ups before they become shared context. Automation stays useful without becoming silent.

Context compounds over time

Saved insights, organization context, and past decisions give agents a durable memory of how your team thinks, not just a transcript to reread.

Explore the rest of the platform

More workloads on the same engine, governance, and pricing.

Lakehouse

Query live data across systems with DuckDB-powered execution, open storage, and predictable economics. Build on one operational lakehouse instead of another warehouse-centered stack.

Tools & Integrations

Plug Altertable into BI, notebooks, SQL clients, and agents through open standards like Iceberg, Parquet, the Postgres wire, Arrow Flight, and MCP. Adopt it alongside your stack instead of replacing it.

Put agents to work on governed business context

DuckDB workers on open formats, federated SQL across your existing systems,
and an MCP server for agents — at flat monthly pricing.