GenAI PMInteractions API
An API for which Speakeasy built SDKs in the newsletter’s cited announcement. It appears in the context of developer tooling and ecosystem support for integration.
Key Highlights
- Interactions API was introduced as a unified interface for Gemini models and agents and later became the default GA interface for orchestration.
- Its evolution emphasized practical developer experience improvements, including REST plus SSE support and more precise, human-readable errors.
- Google I/O demos connected the API to secure hosted Linux sandboxes, code execution, and memory management through Gemini Managed Agents.
- Speakeasy later partnered to build SDKs for the Interactions API and supported open-source OpenAPI generator tooling around it.
At a glance
- Category
- API
Overview
Interactions API is a unified API interface for Gemini models and agents, first announced in beta by Google DeepMind in early 2026 and later shipped to general availability as the default interface for orchestrating models and agents together. Across the newsletter mentions, it is positioned as a core developer-facing layer for building agentic products, with a focus on consistency, orchestration, and better integration ergonomics.
For AI Product Managers, the Interactions API matters because it signals a shift from fragmented or RPC-style agent tooling toward a more standard interface based on REST, SSE, and OpenAPI. That makes it easier to evaluate developer experience, SDK availability, partner ecosystem readiness, and how quickly a team can move from model access to production-grade agent workflows such as memory management, code execution, and hosted sandbox usage.
Key Developments
- 2026-01-03: Google DeepMind announced the Interactions API in beta, described by Phil Schmid as a unified interface for Gemini models and agents intended to power agentic features in 2026.
- 2026-05-05: Logan Kilpatrick rolled out major error message improvements for the Interactions API, making errors more readable for both humans and agents.
- 2026-05-05: Philipp Schmid highlighted quality-of-life improvements including exact field and bad-value naming, supported enum options, expected-versus-actual format guidance, and precise field-path reporting such as `input[0].name`.
- 2026-05-23: At Google I/O, Philipp Schmid demoed building an AI agent with a secure hosted Linux sandbox in a single API call using Gemini Managed Agents and the Interactions API for code execution and memory management.
- 2026-05-23: Schmid also clarified that each sandbox session receives its own persistent container ID, which can be shared across agents, with a tradeoff of slower cold starts for persistence.
- 2026-06-23: Logan Kilpatrick announced the Interactions API had reached GA and was becoming the new default interface for orchestrating models and agents together.
- 2026-07-29: Philipp Schmid said the Interactions API shipped to GA with standard REST + SSE, replacing RPC quirks for a more consistent developer experience; quickstart curl examples and the OpenAPI spec were made available in Gemini API docs.
- 2026-09-18: Philipp Schmid announced a partnership with Speakeasy to build SDKs for the Interactions API and support the open-sourcing of Speakeasy’s OpenAPI generator suite, including SDKs, agent CLIs, and MCP servers.
Relevance to AI PMs
1. Assess developer experience before committing roadmap resources. The Interactions API’s move to REST + SSE, better error messages, and OpenAPI availability are practical signals that implementation friction may be lower for internal teams and external developers.
2. Use it to scope agent product capabilities more concretely. Newsletter mentions tie the API directly to orchestration, memory management, code execution, and secure hosted sandboxes via Gemini Managed Agents, which helps PMs evaluate what can be productized without building every control plane component from scratch.
3. Track ecosystem maturity and integration leverage. The Speakeasy SDK work and OpenAPI tooling support suggest a growing integration layer around the API, which matters when planning partner enablement, multi-language SDK distribution, CLI support, or enterprise adoption paths.
Related
- Google DeepMind: The organization associated with the beta announcement and broader Gemini ecosystem context around the API.
- Gemini / Gemini API: Interactions API is described as a unified interface for Gemini models and agents, with documentation and OpenAPI spec availability in Gemini API docs.
- Philipp Schmid / Phil Schmid / Philipp Schmid: A primary public voice in the mentions, covering the beta launch, Google I/O demos, GA details, and the Speakeasy partnership.
- Logan Kilpatrick: Announced GA status and developer-experience improvements such as more readable error handling.
- Gemini Managed Agents: Featured alongside the Interactions API in a demo showing secure hosted Linux sandboxes, code execution, and memory management.
- Agents: The API is repeatedly framed as an orchestration layer for models and agents together.
- OpenAPI: Mentioned as part of the published spec and as the basis for broader tooling and SDK generation.
- Speakeasy: Partnered to build SDKs for the Interactions API and open-source generator tooling for SDKs, agent CLIs, and MCP servers.
- OpenAI: Mentioned in the broader newsletter context but not directly tied to the Interactions API itself.
Frequently asked questions
What is Interactions API?
An API for which Speakeasy built SDKs in the newsletter’s cited announcement. It appears in the context of developer tooling and ecosystem support for integration.
What should AI product managers know about Interactions API?
Interactions API was introduced as a unified interface for Gemini models and agents and later became the default GA interface for orchestration. Its evolution emphasized practical developer experience improvements, including REST plus SSE support and more precise, human-readable errors. Google I/O demos connected the API to secure hosted Linux sandboxes, code execution, and memory management through Gemini Managed Agents.
Explore this topic
Newsletter Mentions (6)
“Philipp Schmid announced that his unidentified group partnered with Speakeasy to build SDKs for the Interactions API and supported Speakeasy in open-sourcing its OpenAPI generator suite, including SDKs, agent CLIs, and MCP servers.”
GenAI PM Daily September 18, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 20 insights for PM Builders, ranked by relevance from Blogs, X, and YouTube. Google DeepMind shared AlphaGenome Atlas, a freely accessible database intended to help researchers decode the genetic causes of disease. Researchers can explore it on DeepMind’s website. Also covered by: @Google DeepMind #8 𝕏 Philipp Schmid announced that his unidentified group partnered with Speakeasy to build SDKs for the Interactions API and supported Speakeasy in open-sourcing its OpenAPI generator suite, including SDKs, agent CLIs, and MCP servers.
“Philipp Schmid shipped the Interactions API to GA, replacing RPC quirks with standard REST + SSE for a more consistent dev experience; quickstart curl examples and the OpenAPI spec are available in the Gemini API docs.”
#10 𝕏 Philipp Schmid shipped the Interactions API to GA, replacing RPC quirks with standard REST + SSE for a more consistent dev experience; quickstart curl examples and the OpenAPI spec are available in the Gemini API docs.
“Logan Kilpatrick shipped the Interactions API into GA as the new default interface for orchestrating models and agents together, setting the stage for a new era of agents.”
The item says Logan Kilpatrick shipped the Interactions API into GA and positions it as the default interface for model and agent orchestration.
“Philipp Schmid at Google I/O demoed how to build an AI agent with its own secure, hosted Linux sandbox in a single API call using Gemini Managed Agents and the new Interactions API to execute code and manage its memory.”
#8 𝕏 Philipp Schmid at Google I/O demoed how to build an AI agent with its own secure, hosted Linux sandbox in a single API call using Gemini Managed Agents and the new Interactions API to execute code and manage its memory. #9 𝕏 Philipp Schmid clarifies that each sandbox session gets its own persistent container ID—shareable across agents—and that they’re currently trading persistence for slower cold starts.
“#8 𝕏 Logan Kilpatrick rolled out extensive error message improvements for the Interactions API, making its feedback far more human- and agent-readable.”
#7 📝 OpenAI News How OpenAI delivers low-latency voice AI at scale - OpenAI explains engineering techniques to achieve low-latency voice AI at scale, covering system design, model optimizations, and infrastructure approaches. The post outlines how these measures reduce end-to-end latency for real-time voice applications. #8 𝕏 Logan Kilpatrick rolled out extensive error message improvements for the Interactions API, making its feedback far more human- and agent-readable. #9 𝕏 Philipp Schmid launched a QoL upgrade for the Interactions API: errors now name the exact field and bad value, list supported enum options, show expected vs. actual formats, and pinpoint field paths like `input[0].name`. #10 𝕏 Guillermo Rauch launched npx deepspec, an open-source agent orchestrator that leverages thousands of parallel coding agents in Vercel Sandbox to uncover critical security vulnerabilities in minutes.
“GoogleDeepMind Interactions API in beta : Phil Schmid @_philschmid announced the Interactions API , a unified interface for Gemini models and agents , set to power agentic features in 2026.”
Google DeepMind Announces Interactions API Beta From X AI Product Launches & Updates GoogleDeepMind Interactions API in beta : Phil Schmid @_philschmid announced the Interactions API , a unified interface for Gemini models and agents , set to power agentic features in 2026. Qwen-Image-2512 7s high-res image generation : Qwen @Alibaba_Qwen showcased high-resolution images in ~7s from Qwen-Image-2512 , crediting @PrunaAI for support. Agent Workflows integration with ACP : Llama Index @llama_index unveiled an integration of Agent Workflows with the Agent Client Protocol (ACP) , enabling fully customizable agentic systems.
Related
An AI company mentioned through Tony Deng and the Codex event context. It is one of the central companies in the AI ecosystem.
AI/ML developer advocate and commentator at Google DeepMind. Mentioned as part of the public discussion around Genie 4.
Google's AI research lab that builds frontier models and applied AI systems. In this newsletter it is credited with building PlanAssist with Gemini for UK Government planning workflows.
AI product and developer relations leader associated with Google. Included among the accounts covering the Genie 4 announcement.
Google's foundation model family used here as the model behind PlanAssist. Relevant to PMs as an example of a model being embedded into a public-sector workflow.
Google’s API for accessing Gemini models. The newsletter says Gemini 3.7 Flash is available in it and being rolled out to paid users.
AI product and developer advocate who shares predictions on generative AI trends. Relevant for AI PMs tracking market direction and product strategy.
Stay updated on Interactions API
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free