Infor uses industry-specific AI to address agent hallucinations
Industry-specific AI brings business context to agents handling enterprise workflows. Building around industry processes can help companies address reliability concerns as they automate more tasks. Infor (US) LLC is developing industry-specific AI agents for several key industries, including industrial manufacturing, aerospace and defense, automotive, and food and beverage. It builds those agents…
Infor is enhancing its enterprise workflow agents with industry-specific AI to mitigate agent hallucinations and improve reliability. Suresh Jayaraman, senior vice president of product management and development at Infor, explained that while generic agents function, they often produce non-deterministic answers due to hallucinations.
To address this, Infor is developing industry-specific AI agents tailored to sectors such as industrial manufacturing, aerospace and defense, automotive, and food and beverage. These agents are built on top of Infor's existing industry applications. Jayaraman emphasized the importance of industry context in AI, stating that every customer is unique and cannot be served by out-of-the-box AI.
The company's 2026.10 release introduces guardrails through security and scopes. Infor builds its agents around shared common cores across similar industries, with lightweight configuration for specific micro-verticals like chemicals or HVAC. For example, in food and beverage, the nature of the product significantly affects the receiving process, necessitating unique configurations for each product type.
While agents can autonomously create orders and check demand, human approval is still required for order transfers between customers. Infor is also investing in hiring domain experts to collaborate with technologists, recognizing the scarcity of industry-specific talent alongside technical skills.
Written by urgent.news from SiliconANGLE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.