Relevance AI
Relevance AI
Sign inTalk to sales
Press release

Relevance AI Launches Invent 2.0 to Help Companies Quickly Build, Test, and Iterate Autonomous AI Agent Workforces

With Invent, customers report agent workforces going from concept to production workflow with full evaluation, monitoring, and optimization in hours instead of weeks. It’s already helping companies increase process efficiency and effectiveness, as well as drive revenue.

SAN FRANCISCO, CA, September 29, 2026 — Relevance AI today announced Invent 2.0, the latest version of its powerful, collaborative agent for designing, building, and managing AI agent workforces. Invent works like a solutions engineer, interviewing you and analyzing your documentation to help map out processes and understand how to track value. Invent then creates a new, end-to-end agentic business process built from a coordinated team of specialist agents, featuring the tools, integrations, testing, and governance required for enterprise-class performance and reliability.

Invent replaces the effort previously required of human teams to hand-build and maintain every agent, tool, and workflow themselves.

Invent 2.0 - making it easy to build and manage enterprise-class agent workflows

Invent 2.0 is the gateway to enterprises developing more autonomous agentic workflows that can evaluate, monitor, and improve themselves.

  • Process mapping. Invent engages in a collaborative dialogue to understand a business process end to end, identifying which decision points need human judgment and which parts of the workflow should become tools, agents, or workforces.
  • Agent construction and integration. The system builds multi-agent architectures automatically, wiring agents together with the right tools, connecting to the external systems where the work happens, and orchestrating the triggers that keep everything running.
  • Quality assurance and performance monitoring. Invent sets performance benchmarks before an agent goes live, then samples live runs against those standards on an ongoing basis. When quality drifts, it diagnoses the root cause and proposes fixes — to prompts, tools, examples, models, or orchestration logic — with built-in testing before anything ships.
  • Continuous improvement. Invent reviews live agent activity, error patterns, and evaluation results to surface automation opportunities and recommend refinements over time, rather than leaving that work to a human team.

Invent has been tested and proven by enterprise partner customers

Invent 2.0 was refined over a multi-month enterprise design partner program, in which business builders and operations teams put Invent to work on real, high-stakes workflows.

Secure Code Warrior, the AI software governance and secure coding training company, has fully switched over to building and running its internal automation on Invent. According to Matt Wilson, VP of FP&A and Revenue Operations at Secure Code Warrior, the company's deal desk function now runs entirely on a small number of Invent prompts, improving speed and quality at a fraction of the cost of the prior manual process.

"Invent makes building and managing powerful agent workflows straightforward and easy," Wilson said. "I'm so impressed by what we experienced. Invent has reduced what used to be weeks of building time alone to less than a day. My teams can’t imagine building and managing agent workflows without Invent."

Invent is the pathway to fully autonomous agentic workflows

Invent is what makes it possible for organizations to easily move from Level 1 and Level 2 agentic deployments, such as chatbots and copilots, to the more autonomous Level 3 (Autopilot Agents) and Level 4 (Self Improving Agents) deployments.

“With the launch of Invent, Relevance AI has made it incredibly easy for organizations to move beyond agents that improve individual productivity, such as copilots, to fully autonomous workflows that elevate the productivity of an entire department or company” said Daniel Vassilev, Co-CEO, Relevance AI. “Making that leap from individual productivity to Level 3 and Level 4 systemic productivity requires enterprise-class governance, testing, monitoring, and self-improving loops. That’s what makes Invent so powerful - it can deliver efficiency and effectiveness on an entirely new level.”

To go deeper on Invent 2.0 and where Relevance AI sees AI-built agent workforces heading next, please check out:

About Relevance AI

Relevance AI helps organizations build and manage AI workforces — teams of specialist AI agents that automate business processes end to end. Relevance AI is the preferred AI agent management platform for mid-sized and large enterprises. Its platform is used by leading companies including Canva, Confluent, Autodesk, and AVEVA to design, deploy, and continuously improve agents across sales, customer success, marketing, support, operations, HR, and finance. Learn more at www.relevanceai.com

Media Contact: Relevance AI Communications marketing@relevanceai.com