Gemini for Developers: Core — Antigravity CLI & Google Antigravity
Use Google’s current coding tools for a scoped repository change, review the diff, verify tests and manage execution permissions
What this course covers
The course runs across 8 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.
- Antigravity CLI: a scoped repository task — Current Google terminal coding tool is Antigravity CLI. One migration note only: Gemini CLI is now Antigravity CLI. Inspect task scope and approved environment; no legacy CLI instruction.
- Google Antigravity: editor and agent context — Distinguish Google Antigravity development platform and Antigravity CLI from Gemini chat and managed API agents. Select approved interface; current names on the learner screen win.
- Repository context and instructions — Supply relevant architecture, interfaces and test commands; exclude credentials and unneeded private files. Give an exact acceptance test and prohibited edits.
- Single-task plan before execution — Ask for a narrow plan, approve commands and permissions, and separate suggestions from actual execution. No production deployment or broad network access.
- Review a focused diff — Inspect changed lines, validation and security; reject unrelated refactoring. Verify claims with relevant tests, not agent confidence.
- Tests, failures and safe iteration — Use boundary/regression tests; report unavailable execution honestly. Diagnose one failure and revise task instructions without widening permissions.
- Connector and tool permission boundaries — Any repository/tool connector is optional and company-approved. Use the local invented repo or supplied transcript if unavailable; never grant personal access.
- Capstone: one verified patch — Complete the invented pagination patch with minimal diff, tests, root cause and handoff. This course is single-agent scoped coding; multi-agent orchestration belongs in Advanced.
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
Software developers and technical builders. The material is pitched at intermediate level, and takes roughly 150 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 of 5 items, 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
- All Gemini training courses →
- Gemini: Core — Google Workspace — This course goes deep on Gemini across Google Workspace. Learners use Gemini in Docs, Sheets, and Slides, in Gmail and Meet, and apply NotebookLM and Deep Research for grounded answers. The outcome is meaningfully faster, AI-assisted Workspace workflows.
- What's New in Gemini for Everyone — A short refresher on the latest Gemini for Everyone updates
- What's New in Gemini for Developers — A short refresher on the latest Gemini API, AI Studio and Antigravity updates for developers
- Gemini: Essentials — Data & Analysis Playbook — A focused playbook for doing data and analysis work in Gemini. Learners run real tasks end to end - data cleanup, analysis, charts, and interpretation - and leave with repeatable workflows they can use the same day. About 45 minutes including the final.
- Gemini for Developers: Essentials — Refactoring & Migration Playbook — A focused playbook for safe refactoring and migration with Gemini. Learners pin down what legacy code must keep doing, rename and extract functions in small behaviour-preserving steps, then move off deprecated Python date helpers without breaking the nightly job. They leave with a step-by-step refactor plan and the habit of checking what the tests do not cover. About 45 minutes including the final.
- Gemini for Developers Pathway — Gemini for developers from coding in Gemini chat to the Antigravity CLI and Google Antigravity, agentic engineering, and guarded production integrations on the Gemini API and AI Studio. Also includes 4 optional playbooks (Testing, Code Review, Refactoring & Migration, Docs & Onboarding) to take any time after Essentials; they don't count toward the certificate.
Related
- Browse the full Vero AI Catalog
- How the OneRange platform assesses and measures skill
- What OneRange Vero is
Frequently asked questions
How long does this course take?
It runs roughly 150 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 TUL-GEM-DEV-201.