Interactions API hits general availability

// 1h agoPRODUCT UPDATE

Interactions API hits general availability

Google has transitioned its Interactions API to general availability, establishing a unified interface via a single /interactions endpoint. The release introduces a stable schema and new capabilities for model inference and autonomous agents, including managed agents that spin up secure, remote Linux environments.

// ANALYSIS

Transitioning from stateless requests to a unified, stateful interactions framework is a crucial step toward standardizing developer tools for complex, multi-step AI agents. Consolidating inference and agent orchestration into a single endpoint simplifies API integration, while native stateful loops are purpose-built for multi-turn agentic workflows. Furthermore, simplifying the deployment of secure, remote Linux sandboxes via managed agents removes significant infrastructure and security hurdles for developers.

// TAGS

googleinteractions-apigeneral-availabilityagentdevelopersapi

DISCOVERED

1h ago

2026-06-22

PUBLISHED

2h ago

2026-06-22

RELEVANCE

8/ 10

AUTHOR

googleaidevs

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

TUTORIAL30m ago

Three-step guide deploys GLM-5.2 on Baseten

Ray Fernando published a three-step developer guide on how to set up the GLM-5.2 open-weights flagship model using Baseten's inference platform. This guide enables developers to easily deploy and run the model via Baseten's OpenAI-compatible API, leveraging its optimized infrastructure for long-horizon agentic workflows and complex coding tasks.

MODEL1h ago

Krea 2 weights leak via torrent

According to developer @cheatyyyy, Krea AI's 12-billion parameter Krea 2 foundation model weights have reportedly been released via a magnet torrent link. The release includes a 'raw' base variant for fine-tuning and a speed-optimized 'turbo' variant for rapid real-time generation, allowing users to run the model locally.

NEWS1h ago

Meta Applied AI engineers revolt over surveillance

Meta established a 6,500-person Applied AI engineering unit tasked with generating training data and coding challenges for its frontier models. The division has faced severe employee backlash, with staff describing the repetitive work as "literally the gulag" and protesting keystroke surveillance.