# google-antigravity

Google Antigravity is an agentic development platform with an AI-powered IDE, CLI, SDK, and tools for orchestrating autonomous agents and software engineering tasks.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Google launches Gemini 4 Neon, touting lower costs for complex AI coding tasks

DevFeed: [Google launches Gemini 4 Neon, touting lower costs for complex AI coding tasks](<https://devfeed.tech/articles/google-launches-gemini-4-neon-touting-lower-costs-for-complex-ai-coding-tasks-143171.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4250618/google-launches-gemini-4-neon-touting-lower-costs-for-complex-ai-coding-tasks.html>)

Author: Prasanth Aby Thomas

Published: 2026-11-19T09:49:58Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [harvestbench](<https://devfeed.tech/topics/harvestbench.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [api-pricing](<https://devfeed.tech/tags/api-pricing.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [artificial-analysis-intelligence-index](<https://devfeed.tech/tags/artificial-analysis-intelligence-index.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [google](<https://devfeed.tech/tags/google.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Google says Gemini 4 Neon can debug and refactor across large code repositories and, in Antigravity, coordinate parallel Gemini 4 Hydrogen subagents. Positioned between Gemini 4 Carbon for demanding projects and Hydrogen for speed, Neon offers four reasoning levels and a context window up to one million tokens. Its listed API prices are $3 per million input tokens, $15 per million output tokens, and $0.15 per million cached input tokens. Google reports 32% lower cost per task than Carbon in one evaluation and 50%-80% savings against competing models on two other benchmarks; these are company-reported results. The excerpt says enterprises should assess total cost per successful task, code quality, environment compatibility, productivity, and human intervention--not benchmark scores alone. It also notes production risks: generated code can be hard for developers to understand, agents may make conflicting changes, and reliability on complex or long-running tasks remains a concern. Experts describe supervised autonomy, developer oversight, and functional, end-to-end, and regression testing as important for production use.

### Source excerpt

Google is rolling out Gemini 4 Neon, a new model designed for complex software engineering tasks that the company says can complete work more economically than larger models, as it seeks to expand the use of AI coding agents among enterprise developers. Neon can work across large code repositories, performing multi-file debugging and refactoring while making targeted changes to existing code, according to Google. Within Google's Antigravity development environment, Neon can also orchestrate multiple Gemini 4 Hydrogen subagents working in parallel. Neon ranked first on the Artificial Analysis Coding Agent Index with a score of 58.6, while achieving 65.2% on Terminal-Bench 4.1, a benchmark used to evaluate AI agents performing tasks in terminal environments, Google said. Google is positioning Neon between Gemini 4 Carbon, designed for demanding projects, and Gemini 4 Hydrogen, which prioritizes faster execution. The company has set Neon's API pricing at $3 per million input tokens and $15 per million output tokens. Cached inputs cost $0.15 per million tokens, while the model supports a context window of up to one million tokens. Google said Neon delivered a 32% lower cost per task than Gemini 4 Carbon at the default high reasoning setting in Artificial Analysis Intelligence Index evaluations. It also reported savings of roughly 50% to 80% against leading competing models on the Vals Index and Agent Arena benchmarks. Neon offers four reasoning levels, allowing developers to adjust computational effort according to workload requirements. The model is being made available through the Gemini API in Google AI Studio and through Gemini for Business, with access also expanding to Google's Antigravity development platform. Lower costs could shift enterprise model choices Production software development often requires longer context windows, which can push token consumption beyond initial estimates, said Anand Joshi, managing director of market intelligence firm JP Data. This,

## Google DeepMind Releases Gemini 4 Neon: 1M Context, #1 on AA Coding Agent Index

DevFeed: [Google DeepMind Releases Gemini 4 Neon: 1M Context, #1 on AA Coding Agent Index](<https://devfeed.tech/articles/google-deepmind-releases-gemini-4-neon-1m-context-1-on-aa-coding-agent-index-142243.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/18/google-gemini-4-neon-release/>)

Author: Asif Razzaq

Published: 2026-11-19T06:52:26Z

Content type: release

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Google](<https://devfeed.tech/topics/google.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [google-deepmind](<https://devfeed.tech/tags/google-deepmind.md>), [harness](<https://devfeed.tech/tags/harness.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [python](<https://devfeed.tech/tags/python.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

Gemini 4 Neon is a hosted, closed-weight reasoning model positioned between Gemini 4 Carbon and Hydrogen for coding agents, knowledge work, and science. It offers a 1M-token context and costs $3 per million input tokens and $15 per million output tokens; Google says it costs less per task than Carbon and some rivals, though GPT-6.2 Sol has lower listed token prices. In Google-reported benchmarks, Neon scores 61 on the AA Intelligence Index and ranks first on the AA Coding Agent Index, with a notable 95.2% on GraphWalks. It does not lead every comparison: Claude Opus 5.5 scores higher on Terminal-bench 4.1 and FrontierCode 2.0, while GPT-6.2 Sol leads Chartography. Results are self-reported and not independently reproduced in the excerpt. Neon supports multimodal inputs and agent workflows, including context compaction and Antigravity orchestration of Gemini 4 Hydrogen subagents, but is Google-hosted only, with no local or edge builds.

### Source excerpt

Google released Gemini 4 Neon, a 1M-context Gemini 4 model priced at $3/$15 per million tokens. It scores 61 on the AA Intelligence Index and ranks #1 on AA's Coding Agent Index. The post Google DeepMind Releases Gemini 4 Neon: 1M Context, #1 on AA Coding Agent Index appeared first on MarkTechPost.

## Introducing Gemini 4 Neon

DevFeed: [Introducing Gemini 4 Neon](<https://devfeed.tech/articles/introducing-gemini-4-neon-143023.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-neon/>)

Author: Koray Kavukcuoglu

Published: 2026-11-18T21:00:00Z

Content type: release

Language: en

Sources: [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-behavior](<https://devfeed.tech/tags/agentic-behavior.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [arena](<https://devfeed.tech/tags/arena.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [artificial-analysis-intelligence-index](<https://devfeed.tech/tags/artificial-analysis-intelligence-index.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [neon](<https://devfeed.tech/tags/neon.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Neon is presented as a model for complex coding, analytical, enterprise, and scientific work, balancing reasoning depth with speed and cost. The source reports strong benchmark results, including top placements in coding agent, legal research, automation, and science evaluations; results vary by benchmark and harness, including 12.8% on mini-SWE versus 39.0% in Google Antigravity. It describes four thinking levels, with xhigh for deeper reasoning and high offering lower reported cost per task than competing frontier models. The model has a 1 million-token context window and listed pricing of $3 per million input tokens, $0.15 cached input, and $15 per million output tokens. The source also reports safety protections, prompt-injection resistance, and measures of refusal, alignment, and agent overreach, based on its cited evaluations. Rollout is described across the Gemini API, Gemini for business, Antigravity, and the Gemini app, with eligibility varying by service and subscription.

### Source excerpt

hero image for Gemini 4 Neon

## The Unity CLI 1.0 is here!

DevFeed: [The Unity CLI 1.0 is here!](<https://devfeed.tech/articles/the-unity-cli-1-0-is-here-138167.md>)

Original publisher: [Read original article](<https://unity.com/the-unity-cli-1.0-is-here>)

Author: Christopher Addison

Published: 2026-11-17T00:00:00Z

Content type: release

Language: en

Sources: [Unity](<https://devfeed.tech/sources/unity.md>)

Topics: [Unity](<https://devfeed.tech/topics/unity.md>), [Terminal](<https://devfeed.tech/topics/terminal.md>), [builds](<https://devfeed.tech/topics/builds.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [versioning](<https://devfeed.tech/topics/versioning.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [automate](<https://devfeed.tech/tags/automate.md>), [beta](<https://devfeed.tech/tags/beta.md>), [build](<https://devfeed.tech/tags/build.md>), [builds](<https://devfeed.tech/tags/builds.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-build](<https://devfeed.tech/tags/grok-build.md>), [here](<https://devfeed.tech/tags/here.md>), [project](<https://devfeed.tech/tags/project.md>), [terminal](<https://devfeed.tech/tags/terminal.md>), [unity](<https://devfeed.tech/tags/unity.md>)

### AI overview

Unity CLI 1.0 is out of beta and provides terminal-based project setup and control of a live Unity Editor for agents, scripts, tests, and CI. `unity setup` installs official plugins for Claude Code, Codex, Grok Build, or Google Antigravity; Unity skills can also be installed for other agents. The release adds dialog handling, Editor-based builds, version control summaries, project audits, consistent JSON output and exit codes, CI-safe noninteractive behavior, and per-project CLI version ranges. It runs on macOS, Linux, and Windows, and `unity self-update` retains three versions for rollback. Unity says commands, flags, and output will remain compatible through 1.x, with warnings and time to update before removals. Build Server licensing now covers agents and automation; a supported Linux containerized Editor is described as coming soon.

### Source excerpt

Unity CLI 1.0 is out of beta. Connect Claude Code, Codex, Grok Build or Antigravity to your Unity project, and automate builds and tests from the terminal.

## Unite Tokyo 2026 Keynote recap: Built for the speed of your ideas

DevFeed: [Unite Tokyo 2026 Keynote recap: Built for the speed of your ideas](<https://devfeed.tech/articles/unite-tokyo-2026-keynote-recap-built-for-the-speed-of-your-ideas-138166.md>)

Original publisher: [Read original article](<https://unity.com/blog/unite-tokyo-2026-keynote-recap>)

Author: Adam Smith

Published: 2026-11-17T00:00:00Z

Content type: news

Language: en

Sources: [Unity](<https://devfeed.tech/sources/unity.md>)

Topics: [Unity](<https://devfeed.tech/topics/unity.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [GPU rendering](<https://devfeed.tech/topics/gpu-rendering.md>)

Tags: [2019](<https://devfeed.tech/tags/2019.md>), [2026](<https://devfeed.tech/tags/2026.md>), [2d](<https://devfeed.tech/tags/2d.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [all](<https://devfeed.tech/tags/all.md>), [animations](<https://devfeed.tech/tags/animations.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [cli](<https://devfeed.tech/tags/cli.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [fellowship](<https://devfeed.tech/tags/fellowship.md>), [ideas](<https://devfeed.tech/tags/ideas.md>), [keynote](<https://devfeed.tech/tags/keynote.md>), [recap](<https://devfeed.tech/tags/recap.md>), [speed](<https://devfeed.tech/tags/speed.md>), [tokyo](<https://devfeed.tech/tags/tokyo.md>), [unite](<https://devfeed.tech/tags/unite.md>), [unity](<https://devfeed.tech/tags/unity.md>)

### AI overview

The keynote framed Unity 7 around performance across devices, faster creation, and creator support. ECS for All makes each GameObject an Entity, with Unity showing steadier frame rates in a 5,000-ship demo; Unity 7.0 will add Entity inspection and editing. Other graphics announcements included URP Surface Cache GI, Neural Texture Compression (experimental in Unity 6.7 LTS, with full release planned for Unity 7), and Unity Graphics Kernel, which showed a GPU performance increase in the Atrio demo with ray tracing enabled. Unity CLI is generally available and supports custom commands and official coding-agent plug-ins. The Asset Library plug-in searches the Asset Store and owned assets from the Editor or CLI and can adapt Built-in Render Pipeline assets to URP. The Unity Pipeline API is in beta, with general availability planned for 2027. Unity also announced Synty Studios joining the company and an annual Fellowship for ten indie teams, offering $50,000 and support with no revenue share or recoup; teams retain their IP and creative control.

### Source excerpt

Catch every highlight from the Unite Tokyo 2026 Keynote: Unity 7, ECS for All, Unity CLI, Synty Studios joining Unity, and the new Unity Fellowship.

## Advancing science & engineering with Antigravity's /teamwork

DevFeed: [Advancing science & engineering with Antigravity's /teamwork](<https://devfeed.tech/articles/advancing-science-engineering-with-antigravity-s-teamwork-134088.md>)

Original publisher: [Read original article](<https://research.google/blog/advancing-science-engineering-with-antigravitys-teamwork-feature/>)

Published: 2026-11-13T20:47:18Z

Content type: news

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [antigravity](<https://devfeed.tech/tags/antigravity.md>), [education-innovation](<https://devfeed.tech/tags/education-innovation.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [general-science](<https://devfeed.tech/tags/general-science.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [science](<https://devfeed.tech/tags/science.md>), [teamwork](<https://devfeed.tech/tags/teamwork.md>)

### AI overview

Antigravity's /teamwork pairs specialized agents with independent checks to tackle research and engineering tasks over long horizons. Researchers set the questions and constraints; agents explore candidates, while tools such as Lean 4, test suites, simulators, and hardware counters verify results. The system limits context loss by giving agents task-specific files and tools and handing work to fresh agents for review. Reported applications include machine-checked proofs, molecular structure identification, kernel optimization, and large code rewrites. For example, a 30-agent chemistry workflow reached 95% top-1 accuracy on benchmark molecules; a Rust rewrite of libgav1 achieved bit-exact parity and, after profiling-led optimization, ran 20-30% faster than the original on x86_64 and ARM. Gemini 4 with /teamwork and /boost is available in Antigravity, Deep Review is also offered there, and the article says additional formal-proof workflows are forthcoming.

### Source excerpt

Education Innovation

## Take Claude Code Above Average: Let Antigravity Review It

DevFeed: [Take Claude Code Above Average: Let Antigravity Review It](<https://devfeed.tech/articles/take-claude-code-above-average-let-antigravity-review-it-132382.md>)

Original publisher: [Read original article](<https://medium.com/google-developer-experts/take-claude-code-above-average-let-antigravity-review-it-a945412e7dcf?source=rss----a67bd6fa7d58---4>)

Author: Daniel Gwerzman

Published: 2026-11-13T14:21:02Z

Content type: opinion

Language: en

Sources: [Google Developer Experts](<https://devfeed.tech/sources/google-developer-experts-medium.md>)

Topics: [Code review](<https://devfeed.tech/topics/code-review.md>), [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [design](<https://devfeed.tech/tags/design.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4-argon](<https://devfeed.tech/tags/gemini-4-argon.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>), [google-developer-expert](<https://devfeed.tech/tags/google-developer-expert.md>), [november-2026](<https://devfeed.tech/tags/november-2026.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [process](<https://devfeed.tech/tags/process.md>), [review](<https://devfeed.tech/tags/review.md>), [security](<https://devfeed.tech/tags/security.md>), [stage](<https://devfeed.tech/tags/stage.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

The author's central finding is that independent review works best as a dialogue between different AI tools and models, with a human resolving disagreements. In the described setup, Claude Code leads while Antigravity with Gemini 4 Argon reviews; a second review caught concurrent-session risk and missing backups, and later discussion exposed a proposed fix that would fail from a subfolder. The four-stage loop briefs an outside reviewer, requests structured findings and evidence for assumptions, lets the author challenge findings once, then sends changes back for verification and escalates unresolved questions. The author's agy-bridge MCP server connects Claude Code to Antigravity's headless `agy` CLI, preserving review conversations and backing up and comparing project state each turn. Reviewers can read files and run tests but are instructed to write only in scratch space; shell commands cannot be similarly restricted, and project `.agents/` skills may steer review, so the author advises checking them in untrusted repositories. The method is intended for consequential work; reviews take minutes and are unnecessary for throwaway tasks.

### Source excerpt

In November 2026, I spent a day building a small tool with Claude Code: a bridge that lets a second AI agent review Claude's work, run the tests in my project, and argue about what it finds. Partway through the day, the design was revised, the code was written, the tests passed, and Claude was satisfied with its work. Then I gave the same design and code to a different model, running in a different tool. It came back with two findings marked high. Two terminal windows could drive the same review at the same time, each starting its own process behind the other's back. And the reviewer could run shell commands in my project, but nothing backed up my uncommitted work before its turn. One stray git reset --hard would have wiped it. Both were real. Both were cheap to fix. Neither was the kind of thing the author finds by "double-checking". That was the first fix of the day. There were two more. One more thing about that reviewer. It wasn't a second Claude session. It was Antigravity, Google's agentic development platform, running a Gemini model. Today, every review I run goes to Gemini 4 Argon. That pairing is what this article is about: why Claude Code does better work when Antigravity reviews it, the four-stage review I run between them, and the open-source bridge I built so Claude Code can call Antigravity on its own. Why the Author Can't Be the Reviewer Start with what these models are. They learned from everything people have put online: the brilliant answer and the one that ships a security hole, the masterpiece and the first draft. They learned the distribution. So by default, they give you the middle of it. Ask for a function and you get the average function: it works on the happy path and carries the usual number of subtle problems. That isn't a flaw. It's the mathematics of the system. Average is the floor, not the ceiling. The same model has seen far better work than the average. But getting it there takes a process, not a cleverer prompt. The second thing to

## Anthropic and Google Make Their Best AI Models Cheaper

DevFeed: [Anthropic and Google Make Their Best AI Models Cheaper](<https://devfeed.tech/articles/anthropic-and-google-make-their-best-ai-models-cheaper-133360.md>)

Original publisher: [Read original article](<https://realpython.com/ai-news-weekly-2026-11-13/>)

Author: Philipp Acsany

Published: 2026-11-13T14:00:00Z

Content type: news

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [API Business Models](<https://devfeed.tech/topics/api-business-models.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [Google Search](<https://devfeed.tech/topics/google-search.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-companies](<https://devfeed.tech/tags/ai-companies.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-news](<https://devfeed.tech/tags/ai-news.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [claude](<https://devfeed.tech/tags/claude.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [google](<https://devfeed.tech/tags/google.md>), [models](<https://devfeed.tech/tags/models.md>), [python](<https://devfeed.tech/tags/python.md>), [weekly](<https://devfeed.tech/tags/weekly.md>)

### AI overview

Anthropic's Claude Fable 5.2 and Mythos 5.2 share an underlying model; Fable has stronger safeguards and is broadly available, while Mythos is limited to vetted organizations. Anthropic lists API rates of $8 per million input tokens and $40 per million output tokens, with an optional mode at double the price, and reports faster replies and fewer tokens per task than version 5.1 at default settings. Google's Gemini lineup separates harder work (Carbon and Argon) from routine tasks (Hydrogen). Carbon's introductory API price of $2/$10 per million input/output tokens rises to $4/$20 after November 30, 2026; Hydrogen costs $1.50/$7.50 and is available across Google products. Google reports speed and benchmark gains for Hydrogen. These performance and cost comparisons are provider claims. The excerpt also describes Gemini Decisions API, which scores up to 1,000 questions against one input and returns confidence values, and Google's Orchestrator, which routes coding tasks to Hydrogen or Carbon.

### Source excerpt

Real Python's weekly AI news for November 7-13, 2026, explained in plain language: Cheaper Claude, Google's Strongest Gemini, and a Faster Gemini.

## Google adds multi-model Orchestrator, Gemini 4 Hydrogen, to Antigravity

DevFeed: [Google adds multi-model Orchestrator, Gemini 4 Hydrogen, to Antigravity](<https://devfeed.tech/articles/google-adds-multi-model-orchestrator-gemini-4-hydrogen-to-antigravity-132376.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4248403/google-adds-multi-model-orchestrator-gemini-4-hydrogen-to-antigravity.html>)

Author: Anirban Ghoshal

Published: 2026-11-13T12:37:34Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Model Routing](<https://devfeed.tech/topics/model-routing.md>), [code security](<https://devfeed.tech/topics/code-security.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-powered-development](<https://devfeed.tech/tags/ai-powered-development.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [builds](<https://devfeed.tech/tags/builds.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [combines](<https://devfeed.tech/tags/combines.md>), [configure](<https://devfeed.tech/tags/configure.md>), [consulting](<https://devfeed.tech/tags/consulting.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [orchestrator](<https://devfeed.tech/tags/orchestrator.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Antigravity's Orchestrator automatically hands coding work between a planning model and Gemini 4 Hydrogen within one response. Carbon or Argon first explores the codebase, identifies dependencies, resolves ambiguities, and plans; Hydrogen edits files, writes code, and runs builds and tests. If it hits repeated test failures or unexpected behavior, it returns control to the planner to revise the plan. Unlike conventional routing that assigns an entire task to one selected model, Orchestrator transfers control as work progresses without manual switching or configuration. The excerpt says Carbon planning is available to Google AI Ultra subscribers and Argon planning to Pro and Ultra subscribers; Hydrogen can also be selected alone. Hydrogen has a 1-million-token context window and costs $1.50 per million input tokens and $7.50 per million output tokens. Analysts suggest task-specific model use could improve productivity and token efficiency, while raising questions about model-level attribution, auditability, credential access, human approval, and handling of source code and intellectual property. The excerpt does not establish measured productivity or cost savings.

### Source excerpt

Google is adding a new feature, Orchestrator, to Antigravity, its AI-powered development environment, to help enterprises improve software development efficiency by automatically coordinating multiple Gemini models, including the newly introduced Gemini 4 Hydrogen. The new feature, which allows developers to delegate planning, coding, and review tasks to different models within a single coding session, combines a planning model, such as Gemini 4 Carbon or Argon, with Hydrogen, which the hyperscaler describes as a lighter execution model. While the planner models explore the codebase, identify dependencies, and develop an implementation plan, Hydrogen handles execution, including editing files, writing code, and running builds and tests, the hyperscaler wrote in a blog post. That execution differs from conventional model routing, which typically selects a model based on a prompt and assigns it the entire task. Orchestrator, instead, transfers control between the planning and execution models as work progresses, with the planning model first exploring the codebase, identifying dependencies, resolving ambiguities, and preparing an implementation plan before handing control to Hydrogen for execution, the hyperscaler explained in the feature's documentation. Hydrogen hands control back to the planner if it encounters problems, such as repeated test failures or unexpected behavior, allowing the latter to reassess the execution and revise the plan before Hydrogen resumes implementation, according to the documentation. These handoffs, the hyperscaler said, happen automatically within a single response, without developers having to manually switch models or configure the transitions. Improved developer productivity, reduced token consumption The new Orchestrator's ability to use different models for different tasks in a single coding session is likely to boost productivity for developers, according to Pareekh Jain, principal analyst at Pareekh Consulting. "This is like pairi

## Google Releases Gemini 4 Hydrogen: 2.5x Faster Than Gemini 3.8 Flash

DevFeed: [Google Releases Gemini 4 Hydrogen: 2.5x Faster Than Gemini 3.8 Flash](<https://devfeed.tech/articles/google-releases-gemini-4-hydrogen-2-5x-faster-than-gemini-3-8-flash-131644.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/13/google-gemini-4-hydrogen/>)

Author: Michal Sutter

Published: 2026-11-13T09:45:48Z

Content type: release

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Google AI](<https://devfeed.tech/topics/google-ai.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [releases](<https://devfeed.tech/topics/releases.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [harness](<https://devfeed.tech/tags/harness.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [python](<https://devfeed.tech/tags/python.md>), [releases](<https://devfeed.tech/tags/releases.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

Google's Gemini 4 Hydrogen is a closed, Google-hosted model for coding and agent workflows, with a shared 1M-token context window. Google reports a 57% Terminal-Bench 4.1 score versus 18.2% for Gemini 3.8 Flash and says Hydrogen is 2.5x faster at the default high thinking level; the excerpt also reports a #5 Agent Arena rank. API pricing is $1.50 per million input tokens and $7.50 per million output tokens, including thinking tokens. Developers can choose low, medium, high or xhigh thinking; high is the default, while minimal errors. In Google Antigravity's model split, Carbon plans and explores while Hydrogen edits files, updates packages and runs tests. Google reports this pairing used 24% less quota and finished 19% faster than Carbon alone on Terminal-Bench 4.1. Hydrogen has no downloadable weights or self-hosting option, and synchronous output is capped at 65,536 tokens.

### Source excerpt

Google released Gemini 4 Hydrogen, a fast agentic model with a 1M-token window, 4 thinking levels and $1.50/$7.50 pricing. Google reports a 51 Artificial Analysis score and 57% on Terminal-Bench 4.1. The post Google Releases Gemini 4 Hydrogen: 2.5x Faster Than Gemini 3.8 Flash appeared first on MarkTechPost.

## Google's Gemini 4 coding agent now switches models mid-task -- and finishes 19% faster

DevFeed: [Google's Gemini 4 coding agent now switches models mid-task -- and finishes 19% faster](<https://devfeed.tech/articles/google-s-gemini-4-coding-agent-now-switches-models-mid-task-and-finishes-19-faster-130928.md>)

Original publisher: [Read original article](<https://thenewstack.io/gemini-4-hydrogen-orchestrator/>)

Author: Amanda Caswell

Published: 2026-11-12T21:26:08Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Google](<https://devfeed.tech/topics/google.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [changes](<https://devfeed.tech/tags/changes.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [google-s](<https://devfeed.tech/tags/google-s.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [models](<https://devfeed.tech/tags/models.md>), [post](<https://devfeed.tech/tags/post.md>), [switches](<https://devfeed.tech/tags/switches.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

Google's Antigravity Orchestrator assigns demanding reasoning tasks such as architecture and debugging to Gemini 4 Carbon, while Gemini 4 Hydrogen handles code changes and testing, with work handed back to Carbon when a failing test requires a new approach. Google says this pairing achieves nearly Carbon's standalone results while using 24% less quota and finishing 19% faster. The evidence is limited: Google has not published Carbon's standalone success rate, per-task results, Orchestrator's routing rules, or the token and latency costs of model handoffs. Benchmark reporting also differs between the main Gemini announcement (Terminal-Bench 4.0) and the Antigravity announcement (4.1). Orchestrator is currently limited to Google AI Ultra subscribers; Hydrogen is rolling out to paid Antigravity users.

### Source excerpt

Google launched Gemini 4 Hydrogen on Thursday alongside a new system that changes how coding agents use AI models. Rather The post Google's Gemini 4 coding agent now switches models mid-task -- and finishes 19% faster appeared first on The New Stack.

## Google's coding agents now /swarm for one developer. Cursor's go multiplayer so teammates' agents can talk.

DevFeed: [Google's coding agents now /swarm for one developer. Cursor's go multiplayer so teammates' agents can talk.](<https://devfeed.tech/articles/google-s-coding-agents-now-swarm-for-one-developer-cursor-s-go-multiplayer-so-teammates-agents-can-talk-130927.md>)

Original publisher: [Read original article](<https://thenewstack.io/cursor-google-multiplayer-swarm/>)

Author: Paul Sawers

Published: 2026-11-12T21:22:46Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Google](<https://devfeed.tech/topics/google.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [bug](<https://devfeed.tech/tags/bug.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [google](<https://devfeed.tech/tags/google.md>), [multiplayer](<https://devfeed.tech/tags/multiplayer.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [swarm](<https://devfeed.tech/tags/swarm.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

Google's Antigravity Swarm coordinates agents on one developer's assignment: a coordinator splits the work among workers, who message on a shared board, and a verifier checks their changes. Cursor's multiplayer Projects coordinates work across teammates: each person has a coordinator and workers, with shared task boards and documents and direct coordinator messages to flag overlaps or dependencies. Cursor says teams can set shared rules; its documentation treats teammate-agent messages as untrusted and requires agents to ask before sharing private files or connector data. The article notes that the documentation does not specify role-based rules for these exchanges. It also reports an Anthropic study in which multi-user agent teams performed 10-45 percentage points worse than a single agent in four simulated environments; some mitigations helped, with results varying by task. Cursor Projects was in beta for team accounts, and Swarm in preview for Google AI Pro and Ultra subscribers.

### Source excerpt

Coding agents are pretty good at working in parallel: one writes a new API endpoint, another updates the tests, while The post Google's coding agents now /swarm for one developer. Cursor's go multiplayer so teammates' agents can talk. appeared first on The New Stack.

## Introducing Gemini 4 Hydrogen

DevFeed: [Introducing Gemini 4 Hydrogen](<https://devfeed.tech/articles/introducing-gemini-4-hydrogen-130707.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/introducing-gemini-4-hydrogen/>)

Author: Koray Kavukcuoglu

Published: 2026-11-12T18:00:50Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [design to code tools](<https://devfeed.tech/topics/design-to-code-tools.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-tasks](<https://devfeed.tech/tags/agentic-tasks.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [airtable](<https://devfeed.tech/tags/airtable.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [argon](<https://devfeed.tech/tags/argon.md>), [business](<https://devfeed.tech/tags/business.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [daily](<https://devfeed.tech/tags/daily.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [none](<https://devfeed.tech/tags/none.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Gemini 4 Hydrogen is presented as a fast, efficient model for everyday coding and agentic work, available across Google developer, enterprise, consumer, and Search products. The article says it exceeds Argon on the Artificial Analysis Intelligence Index at high thinking (51 vs. 50), costs $1.50 per million input tokens and $7.50 per million output tokens across its 1M-token context window, and offers low, medium, high, and xhigh reasoning levels. In Google Antigravity, Orchestrator can switch between Carbon and Hydrogen; on Terminal-Bench 4.0 it reached near-Carbon success while using 24% less quota and finishing 19% faster on average. Against Gemini 3.8 Flash, Hydrogen is reported to finish tasks 2.5 times faster and score 57% vs. 18.2% on Terminal-Bench 4.1. The article also describes gains in coding, multimodal knowledge work, Search, and agent safety, while noting these performance and safety figures are company-reported.

### Source excerpt

Today, we're introducing Gemini 4 Hydrogen, our daily driver for agentic workflows

## Gemini 4 Hydrogen: everyday coding and agentic workflows for developers

DevFeed: [Gemini 4 Hydrogen: everyday coding and agentic workflows for developers](<https://devfeed.tech/articles/gemini-4-hydrogen-everyday-coding-and-agentic-workflows-for-developers-131031.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-4-hydrogen/>)

Author: Robby Stein

Published: 2026-11-12T18:00:00Z

Content type: release

Language: en

Sources: [Developer tools](<https://devfeed.tech/sources/developer-tools.md>), [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [argon](<https://devfeed.tech/tags/argon.md>), [build-faster](<https://devfeed.tech/tags/build-faster.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cost](<https://devfeed.tech/tags/cost.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [developers](<https://devfeed.tech/tags/developers.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [google](<https://devfeed.tech/tags/google.md>), [google-ai-studio](<https://devfeed.tech/tags/google-ai-studio.md>), [model](<https://devfeed.tech/tags/model.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Hydrogen is presented as a cost-efficient model for everyday coding and agentic workflows, including repository coding and debugging, interactive web development, and multimodal tasks. It can run on its own with four configurable thinking levels or alongside Gemini 4 Carbon and Gemini 4 Argon. The excerpt claims tighter instruction following and fewer fabricated claims, but gives no benchmarks or detailed comparisons. Developers can access it through the Gemini API in Google AI Studio and Android Studio, Gemini for business, or Google Antigravity for paid Google AI Pro and Ultra subscribers. The Gemini API What's New Guide covers model details, setup, and thinking-level controls.

### Source excerpt

Build faster with Gemini 4 Hydrogen, Google's new model for cost-efficient agentic coding and debugging. Start building in Google AI Studio today.

## Introducing Gemini 4 Hydrogen

DevFeed: [Introducing Gemini 4 Hydrogen](<https://devfeed.tech/articles/introducing-gemini-4-hydrogen-131400.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/>)

Author: Koray Kavukcuoglu

Published: 2026-11-12T18:00:00Z

Content type: release

Language: en

Sources: [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [airtable](<https://devfeed.tech/tags/airtable.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [arena-ai](<https://devfeed.tech/tags/arena-ai.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Hydrogen is presented as a fast model for everyday coding and agentic work, with four thinking levels (low, medium, high by default, and xhigh) to vary reasoning depth, latency, and cost. Google says it exceeds Argon on the Artificial Analysis Intelligence Index at high (51 vs. 50), reaching 54 at xhigh, and is priced at $1.50 per million input tokens and $7.50 per million output tokens across its 1-million-token context window. In Antigravity, Orchestrator can switch between Carbon and Hydrogen; on Terminal-Bench 4.0 it reportedly approached Carbon's task success while using 24% less quota and finishing 19% faster. Hydrogen is also positioned as a standalone upgrade from 3.8 Flash: Google reports 2.5x faster task completion and Terminal-Bench 4.1 scores of 57% vs. 18.2%. The article describes developer, enterprise, Gemini app, and Search availability, alongside claimed safety improvements. These are the company's reported results and rollout details.

### Source excerpt

an image of carbon with the number 4 around it

## Agentic software development with CodeRabbit and Google Antigravity

DevFeed: [Agentic software development with CodeRabbit and Google Antigravity](<https://devfeed.tech/articles/agentic-software-development-with-coderabbit-and-google-antigravity-130673.md>)

Original publisher: [Read original article](<https://coderabbit.ai/blog/agentic-software-development-coderabbit-google-antigravity>)

Author: Sahil Bansal

Published: 2026-11-11T12:00:00Z

Content type: tutorial

Language: en

Sources: [CodeRabbit](<https://devfeed.tech/sources/coderabbit.md>)

Topics: [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-loop](<https://devfeed.tech/tags/agentic-loop.md>), [agentic-software](<https://devfeed.tech/tags/agentic-software.md>), [agentic-software-development](<https://devfeed.tech/tags/agentic-software-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-code](<https://devfeed.tech/tags/ai-code.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [code](<https://devfeed.tech/tags/code.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [development](<https://devfeed.tech/tags/development.md>), [english](<https://devfeed.tech/tags/english.md>), [featured](<https://devfeed.tech/tags/featured.md>), [google](<https://devfeed.tech/tags/google.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>), [product](<https://devfeed.tech/tags/product.md>), [review](<https://devfeed.tech/tags/review.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [software](<https://devfeed.tech/tags/software.md>), [software-development](<https://devfeed.tech/tags/software-development.md>)

### AI overview

Google Antigravity can use CodeRabbit to review local code changes, receive contextual findings, apply fixes, and request another review in one agentic loop. Install the CodeRabbit plugin from Antigravity's Plugin Marketplace or with `agy plugin install coderabbit`; the separate CodeRabbit CLI performs local reviews and must be installed before the first review. Sign in with `coderabbit auth login`. The plugin's review skill guides Antigravity through fixing findings and reviewing again. Its Autofix skill applies existing GitHub pull request feedback, with approval for each change, and requires the GitHub CLI installed and signed in. The excerpt says CodeRabbit reviews for functional and logical errors, race conditions, security vulnerabilities, test coverage, and architectural concerns using codebase context and team guidelines; it does not provide comparative performance results.

### Source excerpt

Bring CodeRabbit's specialized AI code reviews into Google Antigravity for a build -> review -> fix agentic loop

## llm-gemini 0.36

DevFeed: [llm-gemini 0.36](<https://devfeed.tech/articles/llm-gemini-0-36-127727.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/10/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-10T20:09:44Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [3D](<https://devfeed.tech/topics/3d.md>), [browser-game](<https://devfeed.tech/topics/browser-game.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-317](<https://devfeed.tech/tags/ai-2-317.md>), [animation](<https://devfeed.tech/tags/animation.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [blender](<https://devfeed.tech/tags/blender.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-game](<https://devfeed.tech/tags/browser-game.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-201](<https://devfeed.tech/tags/gemini-201.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-056](<https://devfeed.tech/tags/generative-ai-2-056.md>), [google](<https://devfeed.tech/tags/google.md>), [google-419](<https://devfeed.tech/tags/google-419.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6-1](<https://devfeed.tech/tags/gpt-6-1.md>), [gpt-6-1-sol](<https://devfeed.tech/tags/gpt-6-1-sol.md>), [js](<https://devfeed.tech/tags/js.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-649](<https://devfeed.tech/tags/llm-649.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-241](<https://devfeed.tech/tags/llm-release-241.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-020](<https://devfeed.tech/tags/llms-2-020.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [medium](<https://devfeed.tech/tags/medium.md>), [model](<https://devfeed.tech/tags/model.md>), [music](<https://devfeed.tech/tags/music.md>), [nano](<https://devfeed.tech/tags/nano.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-157](<https://devfeed.tech/tags/pelican-riding-a-bicycle-157.md>), [yonkers-rising](<https://devfeed.tech/tags/yonkers-rising.md>)

### AI overview

Gemini 4 Carbon became generally available after an initial release to a subset of cyber defenders. The excerpt reports launch pricing of $2 per million input tokens and $10 per million output tokens, scheduled to rise to $4 and $20 on December 1. Thinking effort has low, medium, and high settings, with medium as the default. In Google's Antigravity IDE, a prompt produced a Three.js animation of a mech stomping through New York; a follow-up prompt was needed to make the HTML standalone without external dependencies. A separate video description reports an Antigravity /swarm project that coordinated subagents to build a Three.js campus exploration game with Blender assets, WebGL shaders, Web Audio effects, and Lyria music. These are examples, not a comparative evaluation.

### Source excerpt

Release: llm-gemini 0.36 Gemini 4 Carbon was announced two weeks ago for "a subset of cyber defenders", but today it's available to everyone else. This is Google's best ever Gemini, priced at $2/million input and $10/million output at launch (that's GPT-6.1 Sol / Claude Sonnet 5.5 prices) but scheduled to double in price to $4/$20 on December 1st (same as Opus 5.5). Here are three pelicans for the low, medium and high thinking efforts (it defaults to medium). This is the pelican I got for high: Gemini pelicans have all been great for a while now, so I also tested it out using Google's Antigravity IDE with a prompt I first tried with Claude Fable 5.2 yesterday: Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's the HTML result (I had to prompt "build that into a standalone HTML file" to get a version with no external dependencies). I then screen-captured that as a video: Update: Huh, just saw this on YouTube: Using Google Antigravity's /swarm feature, Carbon built an open-world 3D game where you explore Google's Mountain View campus as a pelican riding a GBike -- coordinating subagents to model 3D assets in Blender from Omni and Nano Banana references, build the browser game in Three.js with WebGL shaders, and pair procedural Web Audio sound effects with Lyria music. Tags: llm-release, gemini, llm, google, generative-ai, ai, llms, pelican-riding-a-bicycle

## Google says its new AI proved Signal's encryption in weeks

DevFeed: [Google says its new AI proved Signal's encryption in weeks](<https://devfeed.tech/articles/google-says-its-new-ai-proved-signal-s-encryption-in-weeks-126607.md>)

Original publisher: [Read original article](<https://thenewstack.io/gemini-4-carbon-swarm/>)

Author: Amanda Caswell

Published: 2026-11-10T16:17:22Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [End-to-End Encryption](<https://devfeed.tech/topics/end-to-end-encryption.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [encryption](<https://devfeed.tech/tags/encryption.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [google](<https://devfeed.tech/tags/google.md>), [signal](<https://devfeed.tech/tags/signal.md>)

### AI overview

Google positions Gemini 4 Carbon for demanding software, scientific and cybersecurity work, while recommending Gemini 4 Argon for everyday tasks. Carbon launches at the same API prices as Argon--$2 per million input tokens and $10 per million output tokens--then doubles to $4 and $20 after November 30. Google says its AlphaProof Code framework used Carbon alongside other models to help prove selected security properties of Signal's cryptographic code: agents generated millions of lines of Lean over weeks, but the verified scope, human involvement and public availability of proofs are unspecified. Google reports strong benchmark and internal security results, including vulnerability discoveries and safeguards against simulated attacks; these evaluations do not establish resistance to all real-world attacks. Carbon is available through paid developer and enterprise offerings, with some access via Google AI Ultra; `/swarm` agent orchestration is in preview, and advanced cybersecurity tools require Fairwind approval.

### Source excerpt

Google released Gemini 4 Carbon to paying developers Tuesday, positioning its newest frontier model above Gemini 4 Argon for complex The post Google says its new AI proved Signal's encryption in weeks appeared first on The New Stack.

## Cursor and Google join OpenAI in giving coding agents a voice. Claude Code stays silent.

DevFeed: [Cursor and Google join OpenAI in giving coding agents a voice. Claude Code stays silent.](<https://devfeed.tech/articles/cursor-and-google-join-openai-in-giving-coding-agents-a-voice-claude-code-stays-silent-124171.md>)

Original publisher: [Read original article](<https://thenewstack.io/cursor-antigravity-voice-agents/>)

Author: Paul Sawers

Published: 2026-11-09T18:22:41Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [cursor](<https://devfeed.tech/topics/cursor.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Google](<https://devfeed.tech/topics/google.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [google](<https://devfeed.tech/tags/google.md>), [openai](<https://devfeed.tech/tags/openai.md>), [voice](<https://devfeed.tech/tags/voice.md>)

### AI overview

Cursor and Google are adding two-way voice conversations so developers can give instructions and check on coding agents while they work. Google's Antigravity keeps a live call open in its desktop app and CLI; users can hear progress, approve commands, interrupt, and follow up, then review the written summary and code changes. Cursor's Voice Chat with Agents uses Grok Voice and is available on desktop, web, and iOS. OpenAI's Codex also supports two-way voice in its desktop app and CLI. Claude Code remains limited to one-way dictation: `/voice` turns spoken instructions into prompt text, and the agent responds in writing, though the separate Claude app has two-way voice. The excerpt frames the broader shift as keeping developers in the conversation after an agent starts work, so they can clarify or redirect it before completion.

### Source excerpt

Two of the biggest players in the AI coding space are betting that developers want to talk to their agents The post Cursor and Google join OpenAI in giving coding agents a voice. Claude Code stays silent. appeared first on The New Stack.

## Skills across coding assistants

DevFeed: [Skills across coding assistants](<https://devfeed.tech/articles/skills-across-coding-assistants-123782.md>)

Original publisher: [Read original article](<https://blog.frankel.ch/skills-across-coding-assistants/>)

Author: Nicolas Fränkel

Published: 2026-11-08T00:00:00Z

Content type: tutorial

Language: en

Sources: [Nicolas Fränkel](<https://devfeed.tech/sources/nicolas-frankel.md>)

Topics: [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [GitHub Copilot alternatives](<https://devfeed.tech/topics/github-copilot-alternatives.md>)

Tags: [antigravity](<https://devfeed.tech/tags/antigravity.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-assistant](<https://devfeed.tech/tags/coding-assistant.md>), [coding-assistants](<https://devfeed.tech/tags/coding-assistants.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [mistral](<https://devfeed.tech/tags/mistral.md>), [model](<https://devfeed.tech/tags/model.md>), [skills](<https://devfeed.tech/tags/skills.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

Mistral Vibe failed to use the author's custom skills, which the author attributes to Claude Code storing skills in nonstandard locations. To make skills available across assistants, the author recommends keeping them in `~/.agents/skills` and `./.agents/skills`, then symlinking Claude Code's `~/.claude/skills` and `./.claude/skills` to those folders. If Claude skill folders already contain files, move them first. This recommendation follows the author's review of assistant documentation; the excerpt does not detail individual providers' support or differences.

### Source excerpt

I love Claude Code, but I use it so much that I regularly exhaust my weekly quota before the week ends. When that happens, I usually switch to other free-tier CLIs, e.g., Google Antigravity, GitHub Copilot, and, just last week, Mistral's Vibe. I really wanted to try Vibe to evaluate the feasibility of moving away from Claude Code in favor of a more sovereign solution. Vibe only offers a single model by default, Mistral Medium 3.5.

## AI workflow demo - create a skill with evals in antigravity

DevFeed: [AI workflow demo - create a skill with evals in antigravity](<https://devfeed.tech/articles/ai-workflow-demo-create-a-skill-with-evals-in-antigravity-113368.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/ai-workflow-skills-evals/>)

Published: 2026-11-01T17:01:30Z

Content type: tutorial

Language: en

Sources: [Maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [evals](<https://devfeed.tech/tags/evals.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [repo](<https://devfeed.tech/tags/repo.md>), [resources](<https://devfeed.tech/tags/resources.md>), [skill-creator](<https://devfeed.tech/tags/skill-creator.md>), [skills](<https://devfeed.tech/tags/skills.md>), [summary](<https://devfeed.tech/tags/summary.md>), [test](<https://devfeed.tech/tags/test.md>), [testing](<https://devfeed.tech/tags/testing.md>), [want](<https://devfeed.tech/tags/want.md>), [work](<https://devfeed.tech/tags/work.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

The author recommends pairing important skills with evals so their behavior can be checked, repeated, and revisited. Evals record triggering prompts, expected outcomes, and optional fixtures or code snippets. In the Antigravity demo, Anthropic's `skill-creator` builds a repository-history catch-up skill and two eval cases; the author reviews and edits the evals, then runs them with and without the skill using the currently loaded model. The reported result suggests the skill helps in that scenario. Evals are also presented as a way to check whether newer models can do the task without the skill. For reusable skills, the author found Antigravity's `~/.gemini/config/skills` location unavailable to other agents, so chose `~/.agents/skills` with symlinks to agent-specific locations. The Anthropic version of `skill-creator` stores results in a sibling `<skill-name>-workspace` folder, which the author says Claude Code ignores and some agents may error on; they changed it to store results beside the evals.

### Source excerpt

What When I create an important skill for me or my team it is useful to know if it works. To do this I also create an eval that contains what prompt is used to trigger the skill and what the outcome should be. The eval can also contain fixtures and sample code snippets to work on. This workflow isn't specific to antigravity but I tested it there. Why Sharing If I am sharing skills with other people I want to make sure they work as expected. Initially I would test them by hand a few time but I would have to rely on my memory to know if the work. Also this manual testing takes a long time. With evals I can automate these steps. Model changes Models become more powerful and sometimes the skills become obsolete because newer models know how to do the tasks. With an eval I can see if the model can perform better than the skill. If it does then the skill can be deleted and the context freed up. Future me If I come back to a skill after some time, sometimes I can't remember how it worked. If I read the eval I can see what I expected it to do Resources A useful open source skill that you can use to create skills and evals and run evals is skill-creator from anthropic. A good tutorial explaining how to create a skill including the evals. General skills documentaion Demo Creating a skill and an eval Use the skill-creator to create a new skill. The detail of what the skill does doesn't matter. How you ask for it and checking that the evals are created is the most important part of this workflow. For our example I am creating a skill to pull the history on a repo after I come back from some time away touching grass. The prompt is this use skill creator to create a user level skill that will pull the history of a git repo and give me a summary of what happened while I was away. The time period could be anything but typically 6 weeks. Summarise by type of tasks, features, chores and show who did the work. Also group related tasks. I want to use this to get a scanable overview of

## Vercel Plugin is now available in Antigravity

DevFeed: [Vercel Plugin is now available in Antigravity](<https://devfeed.tech/articles/vercel-plugin-is-now-available-in-antigravity-106554.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/vercel-plugin-is-now-available-in-antigravity>)

Author: Melkey Moksyakov

Published: 2026-10-29T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Vercel](<https://devfeed.tech/topics/vercel.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Web APIs](<https://devfeed.tech/topics/web-apis.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [apis](<https://devfeed.tech/tags/apis.md>), [backend](<https://devfeed.tech/tags/backend.md>), [build](<https://devfeed.tech/tags/build.md>), [demo](<https://devfeed.tech/tags/demo.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [functions](<https://devfeed.tech/tags/functions.md>), [google](<https://devfeed.tech/tags/google.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [install](<https://devfeed.tech/tags/install.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [products](<https://devfeed.tech/tags/products.md>), [python](<https://devfeed.tech/tags/python.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

The Vercel Plugin is available in the Google Antigravity marketplace, where it gives agents guidance on Vercel APIs and recommended patterns. Its skills cover products including AI SDK, Vercel Functions, and Workflow. The excerpt also describes a demo in which an Antigravity agent builds and deploys a Python backend with Vercel Sandbox. To install the plugin, open Customizations -> Marketplace in the Antigravity app and search for Vercel; the plugin documentation lists its skills and guidance.

### Source excerpt

The Vercel Plugin is now available in the Google Antigravity marketplace. Use the Vercel Plugin to give your Antigravity agent guidance on Vercel APIs and recommended patterns, with skills for products such as AI SDK, Vercel Functions, and Workflow. This demo shows an Antigravity agent using the Vercel Plugin to build and deploy a Python backend with Vercel Sandbox: Install the Vercel Plugin by opening Customizations -> Marketplace in the Antigravity App and searching for Vercel, then see the Vercel Plugin documentation for available skills and guidance. Read more

## What's new in Android developer tools and performance at Android Dev Summit

DevFeed: [What's new in Android developer tools and performance at Android Dev Summit](<https://devfeed.tech/articles/what-s-new-in-android-developer-tools-and-performance-at-android-dev-summit-105739.md>)

Original publisher: [Read original article](<https://developer.android.com/blog/posts/android-dev-summit-26-developer-tools-performance>)

Author: Adarsh Fernando

Published: 2026-10-28T00:00:00Z

Content type: news

Language: en

Sources: [Android Developers](<https://devfeed.tech/sources/android-developers-blog.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Jetpack](<https://devfeed.tech/topics/jetpack.md>), [mobile devops](<https://devfeed.tech/topics/mobile-devops.md>), [Android XR](<https://devfeed.tech/topics/android-xr.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [perfetto](<https://devfeed.tech/topics/perfetto.md>), [Google Play](<https://devfeed.tech/topics/google-play.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [accelerate](<https://devfeed.tech/tags/accelerate.md>), [acp](<https://devfeed.tech/tags/acp.md>), [adb](<https://devfeed.tech/tags/adb.md>), [added](<https://devfeed.tech/tags/added.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agents](<https://devfeed.tech/tags/agents.md>), [android](<https://devfeed.tech/tags/android.md>), [dev](<https://devfeed.tech/tags/dev.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [events-programs](<https://devfeed.tech/tags/events-programs.md>), [help](<https://devfeed.tech/tags/help.md>), [performance](<https://devfeed.tech/tags/performance.md>), [summit](<https://devfeed.tech/tags/summit.md>), [this](<https://devfeed.tech/tags/this.md>), [tools](<https://devfeed.tech/tags/tools.md>), [what-s-new](<https://devfeed.tech/tags/what-s-new.md>)

### AI overview

Android Dev Summit announcements cover three connected workflows: using agents within Android Studio, building and testing through Android CLI, and improving app performance from production signals. Android Studio's stable Bring Your Own Agent supports over 40 ACP-compatible agents with project context and tools such as Compose Preview and Logcat; other updates include agent change reviews and an XML-to-Compose migration assistant in Canary. Android CLI extends builds, profiling, previews, and device access to terminals and CI, with plugins for Google Antigravity, Claude Code, and Codex. Performance updates include LeakCanary analysis, Android Performance Analyzer tracing, Crashlytics and Android vitals signals, and tools for R8 optimization and Compose recomposition analysis. Lightbuild is an early preview recommended for experimental projects, while production apps should continue using Gradle and AGP. Availability varies by feature across stable, Canary, early access, and forthcoming releases.

### Source excerpt

This year at Android Dev Summit we shared how Android's developer tools are evolving to help you be more productive alongside your agents.

## Agentic and Flexible: A next era of Android development

DevFeed: [Agentic and Flexible: A next era of Android development](<https://devfeed.tech/articles/agentic-and-flexible-a-next-era-of-android-development-105740.md>)

Original publisher: [Read original article](<https://developer.android.com/blog/posts/build-it-your-way-a-next-era-of-android-development>)

Author: Matthew McCullough

Published: 2026-10-28T00:00:00Z

Content type: news

Language: en

Sources: [Android Developers](<https://devfeed.tech/sources/android-developers-blog.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Android Studio](<https://devfeed.tech/topics/android-studio.md>), [Large Screen](<https://devfeed.tech/topics/large-screen.md>), [Android XR](<https://devfeed.tech/topics/android-xr.md>), [Jetpack](<https://devfeed.tech/topics/jetpack.md>), [Jetpack XR SDK](<https://devfeed.tech/topics/jetpack-xr-sdk.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [ML Kit](<https://devfeed.tech/topics/ml-kit.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Android Testing](<https://devfeed.tech/topics/android-testing.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [android](<https://devfeed.tech/tags/android.md>), [android-apps](<https://devfeed.tech/tags/android-apps.md>), [android-development](<https://devfeed.tech/tags/android-development.md>), [apis](<https://devfeed.tech/tags/apis.md>), [apps](<https://devfeed.tech/tags/apps.md>), [availability](<https://devfeed.tech/tags/availability.md>), [build](<https://devfeed.tech/tags/build.md>), [dev](<https://devfeed.tech/tags/dev.md>), [development](<https://devfeed.tech/tags/development.md>), [era](<https://devfeed.tech/tags/era.md>), [everyday](<https://devfeed.tech/tags/everyday.md>), [flexibility](<https://devfeed.tech/tags/flexibility.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [great](<https://devfeed.tech/tags/great.md>), [next](<https://devfeed.tech/tags/next.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [summit](<https://devfeed.tech/tags/summit.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Android's announced tools aim to reduce development friction through agent choice, agent-ready workflows, new APIs, and broader form-factor support. Android Studio Rabbit 2 is stable and supports Claude Agent, Codex, Antigravity, and 40+ ACP-compliant agents. Android CLI adds Firebase-powered remote device testing, Compose previews, Perfetto profiling, bundle and library analysis, and 30+ Android skills; official plugins are also available for Antigravity, Claude Code, and Codex. For agentic apps, AppFunctions is in beta, while A2UI for Compose and ML Kit's Gemini Nano 4 Agentic API are in alpha. Connected Apps can be prototyped before applying for the production preview. Adaptive development updates include alpha AppState, stable Navigation 3 1.2, and adaptive layout features planned for Compose 1.13. The excerpt also announces stable Jetpack XR libraries, Android Studio XR emulators, XR Engine Hub, and geospatial APIs. Google Play foldable requirements are to be detailed later.

### Source excerpt

Today, at the Android Dev Summit, we are announcing the broad availability of many tools and APIs designed to remove everyday friction and give you more flexibility to build great Android apps.

[Next page](<https://devfeed.tech/topics/google-antigravity.md?cursor=WyIyMDI2LTEwLTI4VDAwOjAwOjAwKzAwOjAwIiwgIjI5YTJkNTM1LTYyY2ItNDAxMS05YWE2LTJlNTI2ZDRmMzA0YiJd>)