Google adds agent-driven workflows to Opal

"With this expansion, Opal is shifting from a low-code orchestration tool to a platform in which an AI agent independently determines which actions, tools, and models are needed to achieve a goal. The new agent runs on the Gemini 3 Flash model and automatically selects the tools needed to complete a task."

"A technically relevant detail that TechCrunch highlights is that the agent can also use memory across multiple sessions by enabling existing Google services, such as Google Sheets. This allows applications to keep track of a continuous list or user context, for example, without having to build explicit state logic for it."

"The agents in Opal are also natively interactive. When information is missing or additional choices are needed, the agent itself asks the user follow-up questions before continuing. This lowers the threshold for non-technical users but also means that workflows are less deterministic than those of traditional automation solutions."

Google is expanding Opal with an agent step that transforms it from a low-code orchestration tool into a platform where AI agents independently determine necessary actions, tools, and models. Running on Gemini 3 Flash, users define goals in natural language while the agent autonomously plans execution paths. Unlike traditional workflows with predefined steps, this approach eliminates the need to explicitly specify model calls and inputs. The agent leverages memory across sessions through Google services like Sheets, enabling context persistence for business applications. Agents are natively interactive, asking follow-up questions when information is missing, lowering barriers for non-technical users while introducing less deterministic workflows that require IT governance considerations.

Read at Techzine Global