Jedify Data Agents Bring Autonomous Analysts to Business Teams

Jedify has launched a new product that turns business analytics into a job for AI agents rather than a queue of dashboard requests. The company announced Jedify Data Agents on October 28, 2026, a tool that lets teams build autonomous analysts in plain language, with no code and no workflow builder required. According to the announcement, the agents monitor business metrics, investigate changes, and run recurring analyses on their own, drawing on Jedify's context graph technology to understand what an organization's numbers actually mean.

Jedify describes itself as an autonomous context graph for data-intensive agentic applications and workflows. Its platform connects structured operational data, including data warehouses, customer relationship systems, and financial tools, with unstructured material such as documents, playbooks, and meeting recordings. That connected picture is what the new Data Agents reason over, instead of inferring business meaning from raw tables and schema at query time. The product is available now through Jedify's Agents Hub, and a live overview with a customer session is scheduled for October 29.

From dashboards to analysts that come to you

Traditional business intelligence asks analysts to define questions in advance and build dashboards around them. Generic AI assistants, by contrast, often guess at business meaning from raw schema. Jedify positions Data Agents between those two poles: a user describes the analytical outcome in plain language, and Jedify creates and refines the agent conversationally. The agent can then run on demand, on a schedule, or when a defined condition is met, so recurring analysis happens without someone asking for it each time.

The proactive angle is central to the pitch. According to the company, Data Agents do not wait for someone to ask the right question. They surface what needs attention, such as a gap, an anomaly, or an underperforming market, the moment it emerges, rather than letting it sit undiscovered in a report nobody opened. Root-cause investigation is built in: grounded in the context graph and a deep research engine, the agents monitor metrics, investigate anomalies, and identify likely drivers behind a change.

Two design choices matter for enterprise buyers. Agents inherit the requesting user's existing data permissions, so an agent never surfaces a row, column, or metric the user is not already entitled to see. And because agents reason from a pre-resolved context graph instead of exploring raw schema at query time, they use far fewer tokens per question than a schema-inferring agent, according to Jedify. Efficiency at scale is becoming a selling point across the agent stack, as teams move agents from pilots into always-on production work.

Built for the teams that live in the data

Jedify says Data Agents serve both data teams and the business teams they support. Data and analytics teams can stop rebuilding the same dashboards on request, while business users in finance, revenue operations, customer success, product, and sales can build their own analysts. The context graph already handles the schema, the joins, and the definition of what a metric means, so all a user needs is the question they want investigated, described in plain language.

Results reach people where they already work. Through the Model Context Protocol, a Data Agent is exposed as a tool that teams can call from Claude, ChatGPT, Slack, or any agent platform they run, and results can also be delivered directly through Slack and email. Early customers cited in the announcement point to that shift in habit: one data executive at RubyPlay said the team set the agent up once on a daily schedule, and now the report comes to them instead of the other way around, even flagging on its own that some target markets were not yet covered. An enterprise technology leader at ESL FACEIT Group said the agent's habit of flagging a specific cost line that moved sharply in a month, rather than burying it in a trend chart, produced insight the team could actually act on.

Why context graphs matter for agent reliability

The launch lands in a week crowded with agent infrastructure news, and it reflects a shared diagnosis: agents fail less on language than on context. Without a grounded picture of the business, an agent can produce a fluent answer built on the wrong metric definition or an incomplete join. Jedify argues that its Semantic Fusion approach, which automatically builds a proprietary context graph from connected sources, gives agents accuracy and consistency without the hallucinations or token waste associated with context-free approaches. The platform is model-agnostic, so enterprises can build on the AI platforms they choose without single-vendor lock-in.

Related coverage on GenZ NewZ this week has traced the same pattern in other domains. Virtana's agentic observability launch put teams of agents at the center of IT incident response, while Nuix's Neo agent tied every investigative answer back to its source. Jedify's entry applies the same lesson to analytics: the agent is only as trustworthy as the context it reasons over.

Jedify will demonstrate Data Agents at the Gartner Supply Chain Planning Summit, and the company says teams can get started with the product for free. The broader question for buyers is whether autonomous analysts earn trust the way dashboards did: not by answering faster, but by flagging the right thing, with the right permission, before anyone thought to ask. According to the company, that is the shift from analytics that answers questions to analytics that does meaningful work, and Data Agents is its bet on that future. For more detail, see the official announcement and the Jedify Data Agents product page.