# Jedify launches Data Agents for building AI data analysts in plain language

published: 2026-10-28T15:05:45.276Z
topic: infrastructure
source: https://siliconangle.com/2026/10/28/jedify-formally-launches-data-agents-for-building-ai-analysts-in-plain-language/
url: https://aiagentnews.io/stories/jedify-launches-data-agents-for-building-ai-data-analysts-in-plain-language

Jedify Inc. has formally launched Data Agents, a product that lets business teams create autonomous AI analysts by describing the work in plain language. The agents run on a context graph of business data and can be called from Claude, ChatGPT, Slack and other agent platforms through the Model Context Protocol.

Jedify Inc. has formally launched Data Agents, which lets business teams set up autonomous AI analysts by describing the questions they want answered. Instead of analysts building dashboards in advance for expected questions, the agents run on a context graph that combines structured data and documents, including metric definitions and record-level permissions. Users decide whether an agent runs on request, on a schedule, or when a condition they define is met.

Data access follows the person asking the question, so anything that user is not allowed to see stays out of the results, even a single table row. Jedify says its agents use far fewer tokens per question than agents that explore raw schemas at query time. Each agent appears as a tool under the Model Context Protocol, and results can be sent to email or Slack.

Online casino game developer RubyPlay is already using the product, with a daily scheduled agent whose reports arrive without a request. RubyPlay's data team says the agent flagged on its own that not all target markets were covered. Data Agents is available now through Jedify's Agents Hub, and companies can start for free. Jedify has raised more than $33 million, including a $24 million Series A led by Norwest in June.

## Why it matters if you build agents

Developers building agents on business data can expose a governed analytics agent as an MCP tool instead of wiring their own text-to-SQL layer. The permission model and token savings are Jedify's own claims, so teams should test them against their own data before relying on them.