OneRange

What's New in Gemini for Developers

A short refresher on the latest Gemini API, AI Studio and Antigravity updates for developers

What this course covers

The course runs across 7 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

  • A new frontier Gemini model for paid plans — What's different: Google released a new top-tier Gemini 4 model, Argon, for Google AI Pro and Ultra users in the Gemini app and for developers in the API and Antigravity. Why it matters for your work: It is built for long, multi-step work like analyzing reports or building decks, and it gives shorter, more direct answers. Try it (about 2 minutes): Open the model menu in the Gemini app, choose the new Gemini 4 model, and give it a multi-step task, such as turning a long report into a summary table. No access? Here's what you'd see: A new Gemini 4 model option appears in the model menu of the Gemini app for selection.
  • Older Deep Research API agent shut down — What's different: The Gemini API's Deep Research agent preview from December 2025 was shut down on October 23, 2026. Why it matters for your work: Apps still calling the old agent will fail until they switch to a newer Deep Research agent. Try it (about 2 minutes): Search your code for deep-research-pro-preview-12-2025 and replace it with deep-research-preview-04-2026 or deep-research-max-preview-04-2026. Needs: the Gemini API. No access? Here's what you'd see: Calls to the deep-research-pro-preview-12-2025 API agent fail, requiring developers to use deep-research-preview-04-2026 or deep-research-max-preview-04-2026 instead. Renamed or removed: deep-research-pro-preview-12-2025 removed; use deep-research-preview-04-2026 or deep-research-max-preview-04-2026
  • Skills creation options and SKILL.md format — What's different: Skills can now be created using the open SKILL.md format, either manually, with Gemini, from a template, or by uploading a SKILL.md file. Why it matters for your work: This allows you to easily import, export, and share custom instructions in a standardized markdown format, making your custom skills highly portable. Try it (about 2 minutes): Go to Customize > Skills, click to create a new skill, and explore the options to create manually or upload a SKILL.md file.
  • New Gemini API command-line tool (beta) — What's different: Google released the Gemini API CLI in beta, a command-line tool for calling Gemini from scripts, CI pipelines and coding agents. Why it matters for your work: You can test prompts, analyze files or generate media from the terminal without writing app code first. Try it (about 2 minutes): Install the gemini-api CLI from the Gemini API docs, set your API key, and send one text prompt from your terminal. Needs: the gemini-api CLI.
  • API request storage now on by default for new projects — What's different: New paid-tier Gemini API projects now store Generate Content requests by default, matching the Interactions API. Why it matters for your work: If your data rules forbid stored prompts, you now need to turn storage off yourself in new projects. Try it (about 2 minutes): Open the Logs settings in Google AI Studio for a new project and check whether logging is on, or send requests with store=false.
  • Also new — - Computer Use tool is now fully released in the API: The Gemini API's Computer Use tool is now generally available in the Interactions and GenerateContent APIs. - Custom agents in Google Antigravity: Google Antigravity 2.0 and its CLI now support custom, file-based agents.
  • Try one on your own work — Pick the one main change from this course that is most useful to your job. Try it in your own Gemini on a real task, then paste or describe what you got. The coach gives short, specific feedback. No access to the app or plan it needs? Describe how you would use it on a real task this week. That counts too. There is no score and no pass or fail: finishing this completes the course.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

The material is pitched at intermediate level, and takes roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: Gemini track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

Related

Frequently asked questions

How long does this course take?

It runs roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code what-s-new-in-gemini-for-developers-d2fbe57b.