Be part of our day by day and weekly newsletters for the newest updates and unique content material on industry-leading AI protection. Be taught Extra
Open-source AI platform supplier H2O.ai believes a mix of generative and predictive AI fashions makes for extra constant responses which enterprises need from an AI agent.
H2O.ai launched its new multi-agent platform that blends generative and predictive AI and is now typically obtainable.
The platform, h2oGPTe, makes use of the firm’s AI fashions Mississippi and Danube, however may entry different giant and small language fashions obtainable. The corporate stated h2oGPTe works in air-gapped, on-premise and cloud techniques.
Sri Ambati, founder and CEO of H2O, instructed VentureBeat that having each generative and predictive AI offers enterprises extra confidence that the brokers will work precisely as they want with out compromising safety.
“The primary drawback with brokers is consistency. Can I get a constant response from an [large language model] LLM for a similar immediate? I believe you get two completely different, like a number of responses proper now,” Ambati stated. “However you’ll be able to convey a number of fashions that negotiate, plan and ship an end result. Consider it as people can have a little bit of variability with one another, however you continue to count on a constant response, and that’s the area of predictive AI mixed with generative AI.”
Ambati defined that generative AI fashions are “respectable at content material technology and excellent at code technology,” however predictive fashions convey extra state of affairs simulation to the desk. He stated the predictive fashions convey consistency to agentic responses as a result of these don’t simply generate responses however be taught from patterns in knowledge.
The platform is constructed for finance, telecommunications, healthcare and authorities enterprises that must handle multi-step duties. H2O.ai’s agent works finest for organizations that need to get insights into their enterprise and never only a information that runs by way of their workflows. It is because brokers throughout the h2oGPTe platform can learn multimodal knowledge like charts and craft solutions to questions like “Ought to my firm promote extra dolls this 12 months?” that contemplate the enterprise’s historic monetary knowledge or market development info they retailer.
Multimodal brokers
Like different AI brokers, h2oGPTe automates workflow duties so human staff don’t must do these actions themselves. Ambati stated the multimodal capabilities of H2O.ai’s brokers open up extra info that it may possibly be taught from to supply the very best, most constant solutions to customers.
The corporate stated the brokers may create PDF paperwork with charts and tables grounded in enterprise knowledge to visualise info for the human person. H2O.ai ensured that the brokers cite their sources for knowledge traceability and provide customizable guardrails.
H2O.ai’s agentic platform builds in mannequin testing, together with automated query technology, the place an AI mannequin will create variations of a immediate and barrage the agent with inquiries to see if it constantly responds. It additionally has a dashboard the place individuals can establish which sort of database, mannequin, or a part of the workflow the brokers tapped.
Consistency and accuracy in brokers
With the hype round AI brokers predicted to proceed to the next 12 months, there’s a want to make sure brokers present worth to enterprises, together with performing constantly, reliably and precisely.
Reliability is vital as a result of AI brokers are supposed to automate a big portion of an enterprise’s workflow with out human intervention.
H2O.ai’s method of mixing generative and predictive fashions is a technique, however different corporations are additionally methods to make sure AI brokers don’t trigger hassle for enterprises. The startup xpander.ai launched its Agent Graph System for multi-step brokers. Salesforce additionally launched to a restricted preview its Agentforce Testing Middle to check agent response consistency.