What's New in Grok for Developers

A short refresher on the latest Grok Build and Grok API 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.

Older Imagine quality image model retiring — What's different: xAI announced grok-imagine-image-quality retires on November 2, 2026, and requests will then be served by the image 2.0 model at low quality. Why it matters for your work: Results from any app still calling the old model will change after the cutoff. Try it (about 2 minutes): Search your code for grok-imagine-image-quality and switch it to grok-imagine-image-2.0 before November 2. Needs: an API key.
Grok Build remembers your project conventions — What's different: Grok Build now saves notes on your conventions and decisions, per project and globally, reads them in later sessions, and lets you browse them with /memory (it became a simple on/off setting on Oct 9). Why it matters for your work: You repeat yourself less, but a wrong note can steer the agent, so it is worth checking. Try it (about 2 minutes): Start a fresh session, finish one small task, then run /memory to see what it saved and fix anything wrong. Needs: the Grok Build CLI. No access? Here's what you'd see: Learners can browse saved notes on project conventions and decisions using the /memory command and see a simple on/off setting.
Set your own content rules in API requests — What's different: Text requests to the Grok API can now include a guidelines list that tells Grok how to handle adult content, violence and profanity in its answers. Why it matters for your work: Teams can match Grok's answers to their own content policy without writing extra filtering code. Try it (about 2 minutes): In a test API call, add a guidelines entry that asks Grok to avoid profanity, send a prompt that might invite swearing, and check that the reply follows your rule. Needs: an API key. No access? Here's what you'd see: Developers will notice a new guidelines list option in text requests to the Grok API.
Grok Voice 3.0 added, Voice 2.0 deprecated — What's different: Grok Voice 3.0 is the new speech-to-speech model, the grok-voice-latest alias now points to it, and Grok Voice 2.0 is deprecated. Why it matters for your work: Voice agents on the latest alias upgraded on their own, but agents pinned to 2.0 should be moved. Try it (about 2 minutes): Search your code or voice agent settings for grok-voice-2.0 and switch it to grok-voice-latest. Needs: an API key.
Session sharing (/share) removed from the CLI — What's different: The /share command and session sharing were removed from the Grok Build command-line tool. Why it matters for your work: Any team habit or doc that relies on sharing CLI session links needs another approach. Try it (about 2 minutes): If you used /share, try /export to save a session to a file you can pass along instead. Needs: the Grok Build CLI. No access? Here's what you'd see: The /share command is no longer available in the Grok Build CLI; use /export to save your session to a file instead.
Also new — - Built-in git worktree commands: Grok Build added built-in git worktree commands to manage separate worktrees for parallel agents. - safety_identifier field for end users: API requests can now include a safety_identifier to tie policy flags to anonymous end-user IDs. - Grok 4.7 model added to the API: Grok 4.7 has been added to the API, with a faster version for Cursor and Grok Build. - Untrusted folders now block most hooks: Untrusted folders now block most hooks and restrict auto mode shell commands to your allowlist. - Image API now defaults to auto quality: The Imagine image 2.0 API now defaults to auto quality and supports new wide aspect ratios. - Grok Build coding agent leaves beta (1.0): The Grok Build terminal agent has reached version 1.0 with stability, dashboard, and session fixes. - Worktrees reuse your saved approvals: Git worktrees now carry over saved always-allow and never-allow answers from the main checkout. - Find past sessions from any folder: The resume command now searches sessions across all folders and matches words in any order. - Simple mode setting retired: The simple mode display setting has been retired, and sessions now always open with the prompt ready.
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 Grok 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: Grok 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

What's New in Grok for Everyone — A short refresher on the latest Grok for Everyone updates
Grok: Core — Skills, Connectors & Automations — A hands-on working level for experienced Grok users in any role. Set Grok up the way you work, get precise answers from long documents, teach Grok your recurring tasks with Skills, bring work in through the connectors and Office or Google add-ins your company allows, track news with sourced search, and put recurring jobs on a schedule with Automations. No code, no command line, no admin settings.
Grok for Developers: Core — Grok Build in the Terminal — Grok Build for working developers: sign in and choose a model, give the agent the right context with AGENTS.md and .grok/rules, control it with permission modes and allow/deny rules, run agentic coding tasks with planning and review discipline, use sandbox profiles for untrusted code, connect tools with MCP servers, work in large codebases, and decide when Grok in Cursor or another editor is the better fit
Grok for Developers: Essentials — Code Review Playbook — A focused playbook for reviewing code with Grok. Learners attach a pull request written by a coding agent to a grok.com chat, ask for severity-ranked, line-referenced findings on correctness, security, risky edits and missing tests, then check each finding against the code instead of trusting it. They leave with a review prompt they can reuse and a short, defensible set of review comments. About 45 minutes including the final.
Grok for Developers: Essentials — Refactoring & Migration Playbook — A focused playbook for safe refactoring and migration with Grok. Learners pin a legacy reminder job's behaviour with characterisation tests, then use a grok.com chat to rename, extract a helper and move off a deprecated Python date function in small steps, checking the tests after each one. They leave with a step-by-step refactor pattern and a migration that changes nothing users see. About 45 minutes including the final.

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-grok-for-developers-fc481bab.