Infor Grounds AI Agents in Industry Expertise to Combat Hallucinations

Tailoring artificial intelligence to particular business sectors allows agents to operate with greater contextual awareness when managing enterprise processes. Grounding automation in industry-specific workflows helps mitigate the accuracy and consistency problems that emerge as companies scale their use of AI-driven task handling.

Infor (US) LLC is constructing specialized AI agents across multiple sectors, spanning industrial manufacturing, aerospace and defense, automotive, and food and beverage. The company anchors these agents in its portfolio of industry-focused applications, as explained by Suresh Jayaraman, senior vice president of product management and development at Infor.

Although the generic agents might work, you will always run into the challenge of not getting a deterministic answer every single time. And there will be a lot of hallucinations happening.

Suresh Jayaraman, Infor

Jayaraman and Rick Rider, senior vice president of AI innovation at Infor, shared their perspective during Infor Velocity Week, speaking with theCUBE Research's Christophe Bertrand and co-host Alison Kosik in an exclusive broadcast. Their discussion covered industry-tailored AI approaches, configuration for micro-verticals, and the role of human oversight in agent workflows.

Micro-vertical configuration anchors industry-specific AI

Infor directed its initial agent development toward common operational pain points and repetitive processes, according to Rider. The company's 2026.10 release introduces additional safeguards by way of security measures and operational boundaries.

Every customer is uniquely different, and out-of-the-box AI does not exist in our world. We're working with customers to say, 'What do you want?'

Rick Rider, Infor

Infor leverages shared foundational components across comparable sectors, then applies targeted configuration for specialized micro-verticals such as chemicals or heating, ventilation and air conditioning, Rider noted. Within food and beverage specifically, receiving procedures diverge substantially depending on the product category, Jayaraman explained.

For a dairy, it's a liquid receipt, which means I need to understand what the fat content of the milk is, the thickness of the milk while I'm doing the receiving function. If it's a protein or red meat, I'm bringing an entire animal into my receiving process. I need to know the country of origin and a few other extra specific configurations.

Suresh Jayaraman, Infor

While agents can autonomously generate orders and assess demand levels, transferring a customer's order between accounts demands human intervention, Jayaraman noted. To strengthen its capabilities, Infor is recruiting subject matter experts to collaborate with engineering teams, according to Rider.

https://www.youtube.com/embed/W9WNDO2svDw?feature=oembed

Finding tech people, programmers, it's a little bit easier compared to finding the industry-focused people with that deep industry knowledge. When you're going in front of the customer, you're not talking to IT people; you're actually talking to the business people.

Suresh Jayaraman, Infor