Google now lets Gemini chain built-in tools like Search, Maps, File Search, and URL Context with custom functions inside a single API call. This removes orchestration glue for agent builders and brings Maps grounding into AI Studio for faster prototyping.

The core change is that Gemini can now orchestrate built-in tools and developer-defined functions in one request. In Google's launch thread, the example combines Google Search with a custom check_inventory function, and the model returns a sequence including search calls, results, a "thought," and multiple function calls. The same post says this is available natively in the Interactions API and as an opt-in path through generate_content, with more detail in the Interactions docs and the tool-combination docs.
The other important implementation detail is context handling. Google's follow-up thread says built-in tools now work with function calling and that the platform "do[es] context circulation with built-in tools for better model performance." A supporting practitioner summary in this post adds that every tool call now has an ID, which matters for tracing multi-step chains and asynchronous workflows.
Maps is the newly expanded built-in tool. Google's announcement says Google Maps is now available for Gemini 3 models, and the product thread explicitly describes this as "Grounding with Google Maps" for Gemini 3. That widens the set of built-in tools developers can mix into one-call agent flows beyond Search, File Search, and URL Context.
Testing is already visible in the product surface. The AI Studio screenshot shows a "Grounding with Google Maps" toggle in Playground with Gemini 3.1 Pro Preview selected, which makes this easier to prototype before wiring the same behavior into application code. A smaller developer post in this note underscores the practical use case: teams that had been trying to couple Search or Maps grounding with custom functions can now do that directly instead of stitching separate steps together.
ChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
releaseOpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.
releaseCursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
breakingChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
breakingEpoch AI says GPT-5.4 Pro elicited a publishable solution to one 2019 conjecture in its FrontierMath Open Problems set, with a formal writeup planned. Treat it as an early milestone worth reproducing, not blanket evidence that frontier models can already automate math research.
We shipped one of the most requested Gemini API features! 🥳 You can now combine built-in tools (Google Search, URL Context,…) with your own functions custom in a single API call. Gemini orchestrates everything: 🔧 Combine Google Search, Google Maps, File Search or Url Context Show more
Great work by @mcocirio, @_philschmid, and the team who made this happen!! blog.google/innovation-and…
Google released new updates to the Gemini API, including Google Maps grounding support for Gemini 3. Google Maps grounding option is now also available on AI Studio for you to select.
Lots of great Gemini API updates shipping today 🛠️ 1. Built-in tools (search, maps, file search) now work with function calling 2. We now do context circulation with built-in tools for better model performance 3. Grounding with Google Maps now works with Gemini 3!!