Casepoint Expands Casepoint IQ With First Purpose-Built AI Agents

Relevance Determination Agent and Issue Coding Agent are part of a growing portfolio designed to automate complex government, legal, and compliance workflows with human oversight built in.

WASHINGTON, Sept. 23, 2026 /PRNewswire/ -- Casepoint, a leading provider of secure, unified government, legal, and compliance solutions, today announced a portfolio of purpose-built agents powered by Casepoint IQ™, including the Relevance Determination Agent and the Issue Coding Agent. Now live within Casepoint's eDiscovery application and in use by early access customers, the agents mark the first deployment in a broader pipeline of specialized AI agents Casepoint is building for government, legal, and compliance teams.

The announcement follows the launch of Casepoint IQ earlier this month, the intelligence foundation spanning Casepoint's agentic AI, assistive AI, machine learning and predictive coding, and MCP enablement. Rather than building standalone AI tools for individual tasks, Casepoint is developing a growing portfolio of agents that can operate within the same secure platform, data environment, and governance framework customers already use.

"Government and legal teams don't need one general-purpose AI agent trying to do everything. They need specialized agents that understand the work, operate within established controls, and can ultimately work together across complex workflows," said Paul Colangelo, CEO at Casepoint. "That's what we're building on Casepoint IQ. The Relevance Determination Agent and the Issue Coding Agent are the first proof points, with a much broader pipeline of agents being developed across the workflows our customers manage every day."

Putting Agents to Work

Casepoint IQ agents target document-intensive work that traditionally requires significant human review:

• Relevance Determination Agent evaluates documents to determine whether they are relevant or responsive, provides the reasoning behind each determination, and assigns a likelihood score. Every human and AI decision is recorded in an audit trail.
• Issue Coding Agent evaluates documents against specific legal, factual, or investigative issues defined for a matter. An optional post-run quality-control process calculates final recall and precision accuracy at the individual issue-code level.

Both agents use a proprietary multi-model process that analyzes and cross-checks outputs before returning results to a reviewer. Built-in workflows require users to validate performance against a sample set before the agents run across the full scope of documents. Recall and precision metrics measure accuracy, while estimated time and cost savings give legal teams visibility into the potential impact before proceeding. The approach combines agentic automation with measurable performance and human oversight.

"These agents aren't simply generating an answer and asking users to trust it," said Vishal Rajpara, Founder and Chief Technology Officer at Casepoint. "They show their reasoning, measure their performance, and pause for human validation at critical points. That architecture gives us a repeatable foundation for building increasingly sophisticated agents while maintaining the transparency and control that legal and government work requires."

Building a Portfolio of Specialized Agents
Casepoint is actively developing additional agents designed to address other labor-intensive legal, investigative, and information-governance tasks. Casepoint's architecture is designed to allow specialized agents to work sequentially across a workflow to move a matter from relevance analysis to issue identification and other review and data-handling tasks without requiring teams to move between separate technologies.

The strategy reflects Casepoint's broader vision for Casepoint IQ: agentic AI as an integrated operating layer across its unified platform rather than a collection of disconnected AI applications.

Both currently available agents run within Casepoint's unified platform security boundary and operate under existing customer permissions, governance, and access controls. The Relevance Determination Agent and Issue Coding Agent are available for demonstration alongside the broader Casepoint IQ platform. To request a demonstration, visit casepoint.com/iq-agents.

About Casepoint
Casepoint empowers government agencies and regulated enterprises to discover, secure, and act across their most critical legal, regulatory, and compliance workflows. Casepoint brings together 30+ years of deep government expertise with a decade of cloud-native eDiscovery innovation, serving federal civilian and defense agencies and enterprises — including the U.S. Department of War — and unifying legal hold, eDiscovery, investigations, FOIA, regulatory, and compliance workflows in one secure platform.

Built on a cloud-native foundation with FedRAMP® High and DOD Impact Level 5 and 6 authorizations, Casepoint is an AI-forward platform that leverages assistive, predictive, and agentic AI, along with an open MCP for "bring your own agent" support. Every AI-driven decision is transparent and auditable, with human-in-the-loop governance built in. Backed by a white-glove, partnership-oriented approach to every customer relationship, Casepoint helps teams move faster, reduce risk, and maintain control under constant scrutiny. For more information, visit www.casepoint.com.

Media Contact
Carolyn Depko
Plat4orm PR
Media Relations Manager
[email protected]
908-565-3709

View original content to download multimedia:https://www.prnewswire.com/news-releases/casepoint-expands-casepoint-iq-with-first-purpose-built-ai-agents-302887139.html

SOURCE Casepoint