Jedify formally launches Data Agents for building AI analysts in plain language
SiliconANGLE Duncan Riley
Jedify launched Data Agents, which lets teams build AI analysts by describing the job in plain English. It’s meant to replace dashboard wrangling with agents that can run on a schedule and keep data access locked down.
Based on reporting by SiliconANGLE, Duncan Riley — read the original for the full story.
Summary, retelling and take written by AI under human oversight; images are AI-generated illustrations. How we work · Report an error
Jedify has formally launched Data Agents, a new product for teams that want to spin up autonomous AI analysts without first stitching together a dashboard for every question. The pitch is simple: describe the work in plain language, and the agent does the rest.
The product sits on top of Jedify’s context graph, which folds structured data and documents into one model of how a business works. That graph already handles joins, schema mapping, metric definitions and record-level permissions, so the agent starts from a clearer picture than a generic assistant poking through raw tables.
That matters because Jedify is aiming at a familiar business-intelligence pain point. Analysts keep getting the same dashboard requests. Business users keep asking for something slightly different. And generic AI tools, in Jedify’s view, still guess too much when they’re dropped onto schemas and tables without enough context.
Data Agents can run when a user asks, on a schedule or when a defined condition is met. Jedify says that makes it suitable for things like spotting when a market starts underperforming and then using its deep research engine to figure out what probably caused the change. Access is still governed by the person asking the question, so if that user cannot see a row, the agent cannot surface it either.
The company is also pushing beyond its own interface. Through the Model Context Protocol, each agent can show up as a tool inside Claude, ChatGPT, Slack or other agent platforms a company uses. Results can also be sent directly to email or Slack. RubyPlay Ltd. is already using it, with one agent scheduled to run daily and send a report without being prompted. Jedify says its venture-backed startup has raised more than $33 million, including a $24 million Series A led by Norwest in June, and Data Agents is available now through its Agents Hub, with free entry for companies getting started.
My take — AI-written commentary, not fact-checked reporting
This is the sensible version of enterprise AI: fewer chatbot costumes, more work that actually lands in a business process. The real tell is the permission model, not the demo. If AI is going to touch analytics, it should be constrained like a junior employee, not let loose like a drunk intern with SQL.
Read more about this at: SiliconANGLE
