"Last week, Google DeepMind made the Interactions API available as a public beta. The new API represents a fundamental change in how developers work with AI models: from stateless to a stateful architecture with server-side context management. With this move, Google is following the path that OpenAI embarked on in March 2025 with its Responses API. Over the past two years, developers have been working with generative AI via a so-called 'completion' model."
"The new Interactions API aims to solve this by supporting server-side state. Developers no longer need to manage and send the entire conversation history. Instead, they send a so-called previous_interaction_id. Based on that previous_interaction_id, Google can retrieve the conversation history from its servers. This includes previous results from tools and AI models. Background execution for long-running tasks Another major change is background execution. As soon as you start working with complex workflows that take more than a few minutes to complete, you can encounter timeout errors."
The Interactions API enables server-side state management so developers can reference a previous_interaction_id rather than resending full conversation histories. The API retrieves conversation context and prior tool outputs from DeepMind's servers, simplifying context-heavy workflows. Background execution allows agents to run asynchronously by setting background=true, disconnecting the request and enabling later retrieval of results. This design addresses HTTP timeout limits for multi-minute tasks such as searching many pages or analyzing reports. The approach supports more complex AI agents that use multiple tools, maintain extensive context, and perform extended reasoning to produce better solutions.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]