GenAI PMGemini API
Google's API for accessing Gemini models and related tools. In this newsletter, it is notable for adding simultaneous Maps and Search tool support for PMs building grounded, retrieval-enhanced AI experiences.
Key Highlights
- Gemini API has evolved from a model access layer into a broader platform for agents, retrieval, multimodal generation, and tool-augmented workflows.
- Recent updates made it especially notable for AI PMs building grounded experiences, including simultaneous support for Google Maps and Google Search.
- Managed Agents added hosted execution, scheduling, background tasks, and cost controls that help PMs test autonomous workflows more safely.
- File Search and gemini-embedding-2 simplify multimodal retrieval for PDFs and images, reducing implementation overhead for RAG-style features.
- The API’s rapid release cadence across models, tools, and agent infrastructure makes it a strategic platform to watch for production AI product development.
Gemini API
Overview
Gemini API is Google’s developer interface for accessing Gemini models and related built-in tools across text, multimodal, retrieval, agentic, and workflow use cases. In the newsletter, it shows up as an increasingly important platform layer for shipping production AI products: not just model inference, but file search, managed agents, robotics, video generation, function calling, and grounded access to external tools like Google Search and Google Maps.For AI Product Managers, the Gemini API matters because it represents a shift from “call a model” to “compose a product system.” Recent updates highlight a stack that helps PMs prototype and operationalize agentic experiences faster: hosted sandboxes for managed agents, scheduling triggers, cost controls, multimodal retrieval, and simultaneous Maps + Search tool use for grounded user experiences. That combination makes it especially relevant for PMs building assistants, research workflows, support automation, location-aware products, and retrieval-enhanced applications.
Key Developments
- 2026-05-07: The Gemini API File Search tool added true multimodal PDF and image retrieval with `gemini-embedding-2`, handling chunking, embedding, indexing, and grounding in a single call.
- 2026-05-12: Google’s Gemini API interactions quickstart was highlighted as an easy way for builders to get set up and test the latest Gemini model quickly.
- 2026-05-20: Major Gemini API and Google AI Studio updates included Gemini 3.5 Flash, managed agents with the antigravity harness, workspace integrations, and one-click export workflows.
- 2026-05-22: A GitHub Issue Triage Agent demo showed how a useful operational agent could be built against the Gemini API with a single curl-based setup.
- 2026-06-02: Managed Agents launched in the Gemini API, enabling autonomous agents that can reason, write and run code, and manage files inside a hosted Linux sandbox via one API call.
- 2026-07-01: Gemini Omni Flash launched through the Gemini API and Google AI Studio, extending the platform into high-quality video generation and editing workflows.
- 2026-07-08: Managed Agents received major upgrades including background tasks, remote MCP, function calling, network credential refresh, and free-tier availability.
- 2026-07-17: Managed Agents added stronger cost controls, a free tier for broader testing, and scheduling triggers such as cron-style task execution.
- 2026-07-31: Gemini Robotics ER 2 launched in the Gemini API and Google AI Studio, showcasing advanced real-time multi-robot coordination.
- 2026-08-05: The Gemini API added support for using Google Maps and Google Search simultaneously with Gemini 3.5 Flash and 3.6 Flash, a notable improvement for grounded and retrieval-enhanced product experiences.
Relevance to AI PMs
- Prototype full product workflows, not just prompts. Gemini API now spans model calls, retrieval, tool use, hosted agent execution, and scheduling. PMs can validate end-to-end user experiences—like research assistants, support copilots, and ops automations—without stitching together as many separate vendors.
- Ship grounded AI features faster. File Search, `gemini-embedding-2`, Google Search, and Google Maps support make it easier to build assistants that answer with fresher, more context-aware outputs. This is especially useful for PMs working on enterprise knowledge retrieval, travel and local discovery, or any product needing real-world grounding.
- Manage reliability and cost earlier in the product lifecycle. Managed Agents updates such as free tier access, max token controls, background execution, and scheduled triggers help PMs test recurring agent workflows while keeping spend and runtime risk visible.
Related
- Google AI Studio / AI Studio: The primary companion environment for testing and launching Gemini API workflows, often shipping updates in parallel.
- Google Search and Google Maps: Built-in tools that extend Gemini API outputs with web and location grounding; simultaneous support is especially relevant for richer consumer and enterprise assistants.
- Gemini 3.5 Flash, Gemini 3.6 Flash, Gemini 3 Pro Preview, Gemini 3.1 Flash Lite: Model variants associated with speed, capability, and different product tradeoffs on the API.
- Managed Agents / Managed Agents Quickstart: Google’s hosted agent framework inside the Gemini API, important for PMs exploring autonomous or semi-autonomous workflows.
- File Search and `gemini-embedding-2`: Retrieval components that simplify multimodal indexing and grounding for PDFs and images.
- Function Calling, Remote MCP, Background Tasks: Key building blocks for connecting Gemini-based agents to external systems and long-running workflows.
- Gemini Robotics ER 2 and Gemini Omni Flash: Examples of the API expanding beyond chat into robotics coordination and multimodal video generation/editing.
- Logan Kilpatrick and Philipp Schmid: Frequent sources of product announcements, demos, and quickstarts that help the ecosystem understand new Gemini API capabilities.
Newsletter Mentions (24)
“Logan Kilpatrick announced that the Gemini API now supports using Google Maps and Google Search tools simultaneously with Gemini 3.5 Flash and 3.6 Flash, an update that had long been on the backlog.”
#1 𝕏 Logan Kilpatrick announced that the Gemini API now supports using Google Maps and Google Search tools simultaneously with Gemini 3.5 Flash and 3.6 Flash, an update that had long been on the backlog.
“Logan Kilpatrick launched Gemini Robotics ER 2 in the Gemini API and Google AI Studio, featuring standout multi-robot collaboration demos that highlight its advanced real-time coordination.”
#9 𝕏 Logan Kilpatrick launched Gemini Robotics ER 2 in the Gemini API and Google AI Studio, featuring standout multi-robot collaboration demos that highlight its advanced real-time coordination. Also covered by: @Philipp Schmid , @Logan Kilpatrick , @Philipp Schmid #10 𝕏 LlamaIndex 🦙 launched Parse Gateway, which uses LiteParse’s is_complex to classify each PDF page (scanned, tables, text, images) and route easy pages in-process or hard pages to advanced LlamaParse tiers.
“#5 𝕏 Logan Kilpatrick introduced new cost controls for managed agents, a free tier for everyone to try, and the first scheduling triggers for agent tasks, highlighting weekly improvements in the Gemini API’s managed agents.”
#5 𝕏 Logan Kilpatrick introduced new cost controls for managed agents, a free tier for everyone to try, and the first scheduling triggers for agent tasks, highlighting weekly improvements in the Gemini API’s managed agents. #13 𝕏 Philipp Schmid launched a free tier for Managed Agents in Google AI Studio’s Gemini API, plus two cost-control updates: a max_total_tokens parameter to pause and resume tasks safely and native cron triggers (e.g., “0 9 * * *”).
“Logan Kilpatrick rolled out major updates to Managed Agents in the Gemini API—adding background task support, remote MCP & function calling, and network credential refresh—and now you can try them on the free tier.”
#2 𝕏 Logan Kilpatrick rolled out major updates to Managed Agents in the Gemini API—adding background task support, remote MCP & function calling, and network credential refresh—and now you can try them on the free tier. Also covered by: @Logan Kilpatrick
“Google DeepMind shipped Nano Banana 2 Lite, its fastest, cheapest Gemini Image model, and rolled out Gemini Omni Flash via the Gemini API and Google AI Studio to enable high-quality video generation and editing.”
Google AI unveiled Gemini Omni, Flash, Nano, and Banana 2 Lite—a suite of multimodal models designed for rapid idea exploration and scalable visual concept creation. Also covered by: @Logan Kilpatrick , @Philipp Schmid , @Google AI #8 𝕏 Google DeepMind shipped Nano Banana 2 Lite, its fastest, cheapest Gemini Image model, and rolled out Gemini Omni Flash via the Gemini API and Google AI Studio to enable high-quality video generation and editing. Also covered by: @Logan Kilpatrick , @Philipp Schmid , @Google AI
“Philipp Schmid launched Managed Agents in the Gemini API, allowing users to spin up autonomous AI agents that reason, write and run code, and manage files inside a hosted Linux sandbox with just one API call.”
#4 𝕏 Philipp Schmid launched Managed Agents in the Gemini API, allowing users to spin up autonomous AI agents that reason, write and run code, and manage files inside a hosted Linux sandbox with just one API call.
“Philipp Schmid built a GitHub Issue Triage Agent using a single curl to the Gemini API.”
#9 𝕏 Philipp Schmid built a GitHub Issue Triage Agent using a single curl to the Gemini API.
“Logan Kilpatrick launched major updates to Google AI Studio and the Gemini API—Gemini 3.5 Flash, managed agents with the antigravity harness, native Android app creation in AI Studio, workspace integrations, and one-click antigravity export.”
#17 𝕏 Logan Kilpatrick launched major updates to Google AI Studio and the Gemini API—Gemini 3.5 Flash, managed agents with the antigravity harness, native Android app creation in AI Studio, workspace integrations, and one-click antigravity export.
“Philipp Schmid shares Google’s Gemini API interactions quickstart guide, helping PM builders quickly set up and test the new Gemini AI model.”
#20 𝕏 Philipp Schmid shares Google’s Gemini API interactions quickstart guide, helping PM builders quickly set up and test the new Gemini AI model. #21 𝕏 Lenny Rachitsky shares eight actionable insights from Eric Ries—spanning financial gravity, CEO retention post-IPO, public-benefit corp structures like AnthropicAI, mission protection, and principled decision-making exemplified by Cloudflare.
“The Gemini API File Search tool now offers true multimodal PDF and image retrieval using `gemini-embedding-2`, handling chunking, embedding, indexing and grounding in one call.”
#4 𝕏 Philipp Schmid : The Gemini API File Search tool now offers true multimodal PDF and image retrieval using `gemini-embedding-2`, handling chunking, embedding, indexing and grounding in one call. #5 𝕏 Google DeepMind partners with EVE Online’s developers to use the game’s complex, player-driven universe as a sandbox for AI agents focused on memory, continual learning, and long-term planning.
Related
AI developer advocate/product voice associated with Google’s Gemini API ecosystem. He is mentioned shipping agent controls and API improvements for managed agents.
Google’s AI research organization, mentioned here for sharing a blog post about Gemini Robotics 2 and whole-body intelligence for robots.
AI product leader known for announcing Google AI and developer platform updates. Here he is cited for sharing a Gemini API feature update relevant to AI builders.
Google’s AI assistant/model family mentioned as part of DeepMind leadership oversight. It matters for PMs tracking product ownership and roadmap changes.
A major technology company with a large AI research and product footprint. The newsletter references Google’s open-source commitment and its Gemma platform via DeepMind.
Google's research organization responsible for experimental AI and science systems. It introduced the Science One Framework in this newsletter.
Google's prompt-to-prototype studio for Gemini and related developer workflows. It is mentioned as a place to access Gemini Robotics ER 2.
CEO of Alphabet/Google, mentioned for announcing leadership changes at Google DeepMind. He is relevant for company strategy and AI org structure.
Google model recommended for OCR and VQA workloads. It is highlighted for speed, cost, and accuracy tradeoffs relevant to PM decision-making.
An opinionated build environment for coding with AI that uses a coding agent. The newsletter notes that projects can be exported from it directly to Antigravity.
Google's search product used for web retrieval. In this context it is being exposed as a tool inside Gemini API to support grounded answers and tool-augmented reasoning.
A Gemini model variant that was noted as moving out of preview status.
A research capability embedded into Perplexity Computer as a built-in skill. For PMs, it indicates the packaging of advanced research into agent workflows.
An embedding model powering multimodal file search in the Gemini API. Relevant for PMs designing retrieval, citation, and metadata-aware workflows.
Google's mapping and local search platform. Here it appears as a tool that can be invoked alongside Google Search inside Gemini API workflows.
Stay updated on Gemini API
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free