Google Antigravity AI tool changing the workflow

Google announced Gemini 3.6 Flash on July 21, 2026, with sharp benchmark gains over 3.5 Flash: DeepSWE rose from 37% to 49%, MLE Bench from 49.7% to 63.9%, and OSWorld Verified reached 83%. Yet 4AIVN's hands-on experience tells a very different story. The model handles small jobs reasonably well, but a multi-step plan can make it forget the objective, skip steps, and drift halfway through the work. Stronger benchmarks do not reflect real-world use According to Google's official announcement, Gemini 3.6 Flash uses 17% fewer output tokens than 3.5 Flash on the Artificial Analysis Index, while tests such as DeepSWE show token reductions of up to 65%. Its input window reaches 1,048,576 tokens and its output limit is 65,536 tokens, impressive numbers on paper. The problem is that these figures come from designed tests with a fixed objective and a relatively contained run. That is not how a real plan operates. Production work changes continuously in response to feedback rather than ending after one self-contained attempt. Following a long plan is the critical weakness In hands-on use, Gemini 3.6 Flash performs poorly as soon as it moves beyond a single task. Give it a small job with explicit checks and it can work well with few unnecessary loops. Give it a multi-step plan and it may forget the original objective, skip previously agreed steps, or drift after several turns. When corrected, it sometimes apologizes and then repeats the same mistake instead of actually fixing it. A one million token window describes input capacity, not memory quality. The model may be able to “see” the full context and still miss details during execution; one overlooked constraint can push the entire plan off course. This is not a rare random failure but a repeated weakness that is difficult to ignore. Gemini 3.6 Flash is strong at completing one job quickly, but it is not yet dependable at completing a sequence of jobs correctly. That is the gap the benchmarks do not measure. A 17% price cut may not match the quality Gemini 3.6 Flash is priced at $1.50 per million input tokens and $7.50 per million output tokens, about 17% below the $9 output price of 3.5 Flash. On the surface, this is a sensible improvement: lower cost and higher benchmark scores. But if long tasks are executed poorly, the savings can quickly disappear through repeated reminders, corrections, and complete reruns of the plan. Gemini 3.5 Flash Lite is cheaper still at $0.30 per million input tokens and $2.50 per million output tokens, but it targets simple classification and data transformation workloads that do not require the model to preserve a long plan. What do you gain and lose with Gemini 3.6 Flash? Objectively, this is not a failed upgrade. Google has likely made careful tradeoffs among output quality, speed, and cost, even if real-world behavior does not fully meet the high expectations attached to its engineering team. The improvements are real rather than purely theoretical: responses are faster, output costs are lower, and the model is efficient on short, narrow tasks such as content classification, writing one code function, or answering a specific question. In those cases, it keeps unnecessary loops to a minimum. The cost becomes visible when work extends beyond a few steps. The more constraints and earlier decisions the model must preserve, the more likely it is to drift. For coding agents or long workflows already running reliably on Claude Fable 5 or GPT 5.6, there is not yet a convincing reason to switch to Gemini 3.6 Flash solely because of benchmarks or lower pricing. Gemini 3.5 Pro is still the model to wait for Google says Gemini 3.5 Pro is still being tested with partners and will be released broadly when it is ready. The central story of this launch is therefore the sizeable gap between benchmarks and real work. Anyone looking for a dependable agent for long-running workflows may still need to wait and see whether 3.5 Pro delivers a genuine step forward. If future releases remain underwhelming in practice, Google risks surrendering its advantage to competitors including Anthropic, OpenAI, and Meta.

Gemini has won big in the most literal sense, right as Messi scored his first hat-trick at the 2026 World Cup, leading Argentina to a crushing 3-0 victory over Algeria and equaling Miroslav Klose's record of 16 World Cup goals. That historic moment became the perfect launchpad for Gemini. Back in March 2026, Google and the Argentine Football Association (AFA) made a bold decision: rather than simply printing a logo on training kits, they signed a deal for the AI to actively support tactical preparation and professional decision-making. That bet has now proven to be the right call. From training kit to the tactical meeting room The agreement between AFA and Google was unveiled at Times Square, New York, a venue deliberately chosen to capture global media attention. The Gemini logo appears across all training apparel for Argentina's men's, women's and youth squads, sitting alongside Adidas and American Express in AFA's top sponsorship tier. But the interesting part isn't the jersey. According to Inside World Football, Argentina's coaching staff will use Gemini for three specific purposes: tactical analysis, injury prevention and decision support. In other words, Gemini now has a seat in meetings that previously belonged only to Scaloni and his assistants. Google has not publicly disclosed which specific Gemini tools have been integrated into AFA's workflow. What is clear is that they are using the World Cup to bring Gemini into the reality of professional football, and the results will be graded in public. What is Gemini actually doing in the dressing room? Argentina arrives at the 2026 World Cup as the reigning champion. Every decision Scaloni makes, from the squad list to the starting eleven, is scrutinized more closely than any other team, and that is precisely why Argentina has become the most ideal testing ground Google has ever had for Gemini in professional football, especially at a major tournament. Tactical analysis Gemini is used to process match data for both Argentina and their opponents, covering movement statistics, attacking patterns and defensive vulnerabilities. Instead of the coaching staff spending hours reviewing footage, AI synthesizes the data and generates tactical diagrams automatically, saving significant preparation time before each match. Injury prevention This is a problem every major team wants to solve, especially when Messi and several key players are at an age that requires careful management of training loads. Gemini analyzes biometric data and injury history to issue early warnings, helping the coaching staff adjust intensity before problems actually occur. That is part of the reason why, immediately after completing his hat-trick, Scaloni chose to substitute Messi off, prioritizing fitness and safety for the matches ahead. AI in injury prevention is nothing new. Premier League clubs have had Microsoft as a partner for similar purposes. What is different this time is that Gemini is integrated directly into the workflow of a national team competing at a major tournament, not just at club level. For fans: create Messi content, follow scores without unlocking your screen Alongside supporting the coaching staff, Gemini has also rolled out a range of features aimed at fans, and this is the side that hundreds of millions of people will actually experience. Gemini lets you create content about players directly Users can generate images, songs and digital content featuring Argentina players like Messi directly inside the Gemini app. The feature is designed to bring the World Cup experience closer to those who cannot attend matches in person. Real-time scores and automated daily briefings On Google Search, live match scores can be pinned to the lock screen and update in real time, with dedicated animations for goals and red cards, all without needing to unlock the phone. For paid Gemini users, the Scheduled Actions feature allows an automated daily football briefing to be set up, covering scores, news and fixtures, delivered at a chosen time without needing to prompt it each day. Match-day infrastructure Google has updated Street View at all 16 host stadiums and optimized routing on Waze for match days. Waze also surfaces live scores when the car is stopped at red lights, so drivers do not need to pick up their phones while on the move. The 2026 World Cup is the real test for AI in sport Google is not sponsoring Argentina alone. Gemini also appears on the kits of France, Morocco, Iraq, Turkey and the United States, while Pixel is the official phone of the French squad, which is also using Gemini for internal communications. This is clearly a comprehensive strategy from Google, not a one-off deal. What makes the 2026 World Cup particularly significant is that it will answer a question no lab environment can: what do users actually do with AI when a World Cup runs for six weeks across 104 matches? Features that run on initial novelty will fade after the group stage. Whatever users keep coming back to all the way through the final is the honest answer to where AI actually fits in everyday life, and Google knows it. Google's communications director for Latin America, Flor Sabatini, stated that the 2026 World Cup will mark a before and after in the history of football because of AI. It sounds like marketing, but the reality is that this is the first time a major AI model has been integrated into the preparation of the reigning world champions, right in the middle of the most-watched sporting event on the planet. The 2026 World Cup is Gemini's real test The most significant part of this entire story is not the Gemini logo on Messi's jersey. It is the fact that Argentina, still the most expected to win and the most scrutinized team, carrying the pressure of defending the title, has committed part of its preparation process to AI. If Argentina succeeds, Gemini will have a case study that no advertising budget can buy. If Argentina falls short and the coaching staff attributes any part of it to AI, the narrative will flip entirely. Either way, this is the first time AI has been held accountable on a stage that genuinely matters, not a benchmark, not a demo, but the World Cup. For AI users, what is worth watching is not just whether Argentina wins, but whether Gemini actually changes how a football team operates, or whether it turns out to be nothing more than a logo on a training kit that looks better than previous years.

Token management is a hot topic in the AI community. In summer 2026, two open-source skills for saving tokens are being widely discussed: Ponytail cuts generated code lines by up to 54%, while Caveman slashes agent response tokens by 65%. Both target a familiar pain point for users of AI coding agents like Claude Code, Codex, or Gemini CLI—ballooning token costs—yet solve it from completely different angles: one trims unnecessary code, while the other trims unnecessary words.The Token Waste Problem in the AI Agent EraToday's AI Agents do not just answer single prompts; they operate in autonomous agentic loops by reading files, analyzing project structures, writing code, running builds, and checking for errors. Throughout this process, tokens are wasted mainly across three channels:Over-engineering (Excess Code): Instead of using native language or browser features, agents frequently install extra dependencies or construct unnecessarily complex components.Input Overhead (Excess Context): Build logs, JSON payloads, search results, and instruction files (SKILL.md) consume tens of thousands of input tokens on every API call.Output Bloating (Verbose Prose): Agents explain basic concepts at length before delivering the core answer.Ponytail: Turning your AI Agent into a "Lazy Senior Dev"Created by Dietrich Gebert, Ponytail is designed with a core philosophy: "The best code is the code you never wrote." Ponytail forces an AI Agent to think like a seasoned senior developer who always looks for the simplest, lowest-effort solution.Self-Questioning Ladder Before Writing CodeBefore touching any code, Ponytail requires the agent to run through a self-questioning ladder:YAGNI: Is this feature really necessary? If not, skip it immediately.Reusability: Is there an existing function or component in the codebase?Standard Library: Can the language's standard library handle it?Native Platform: Is it supported natively by the browser or OS? (e.g., using a native <input type="date"> instead of installing a heavy Flatpickr library)Installed Dependencies: Can already installed packages in package.json resolve it?One-liner: Can it be written in a single line of code?Only when the above steps fail will the Agent proceed to write the minimal working code required.Do Benchmark Results Match Reality?In tests using Claude Code (Haiku 4.5) on a full-stack FastAPI + React template, Ponytail reduced lines of code by 54% while maintaining 100% application safety.This figure was published by the author after the community pointed out baseline flaws in the initial benchmark (which claimed 80-94% reductions), so it should be treated as a reference signal rather than an independently verified statistic.Caveman: A Token Compression Ecosystem, Not Just a SkillWhile Ponytail targets generated code, Julius Brussee's Caveman attacks both agent input and output with the catchy slogan: "why use many token when few token do trick". Current Caveman is no longer a single skill, but a multi-layered toolkit.Caveman Proxy: Compressing Input DataA local proxy sits between the Agent and the API provider, automatically routing all traffic. It detects payload types like JSON, error logs, git diffs, or search results, compressing them to keep only essential content needed for the answer, while saving copies on disk for byte-exact recovery when required. In a 54-run pinned benchmark on Claude Code, this mechanism used 33.2% fewer input tokens than direct runs while passing all exact-answer checks.Caveman Skill: Compressing Response LanguageThis part returns agent communication to primal caveman-speak: dropping conversational filler and getting straight to the point without altering code or command integrity. Code, commands, and error logs remain byte-exact, with only explanatory prose compressed.Pixel Mode: Rendering Skill Files to ImagesVerbose SKILL.md files are rendered into PNG images upon skill installation, leveraging vision capabilities of modern LLMs to lower prompt token loads. Measured on Caveman's own skill file, this reduced size from ~1,069 down to an estimated 415 tokens, or 61%.The 61% reduction was measured on a single case (Caveman's own SKILL.md), not as an average across all skill files—actual results will vary based on file length and structure.Caveman Learn: Self-Diagnosing Token BottlenecksThe caveman learn command automatically reads local agent session history (running locally without accounts), scores the current setup, and pinpoints exact token sinks for user remediation.Numbers to Keep in Mind Reading Caveman MarketingCaveman's official documentation includes an "honest number warning": Caveman Skill alone reduces output tokens, while input and reasoning tokens remain mostly unchanged unless the proxy is enabled, adding ~1,000-1,500 input tokens per turn for the skill prompt. The 65% output token, 33.2% input token (via proxy), and 61% skill token (via Pixel Mode) metrics are separate measurements and do not stack into a single combined number—read context carefully before quoting.Can Ponytail and Caveman Be Combined in One Session or Project?Ponytail and Caveman do not conflict. Caveman keeps what the agent reads (input) and says (output) as concise as possible, while Ponytail ensures what the agent writes (code) is strictly minimal. Because their mechanisms do not overlap, they can be used side-by-side in the same session.While no independent benchmark has measured the exact savings of using both simultaneously, combining their individual metrics theoretically reduces overall session tokens significantly—making it well worth testing on your real codebase.Workflow Integration GuideBoth Ponytail and Caveman support quick installation for popular AI coding tools like Claude Code, Codex, Gemini CLI, Cursor, and Windsurf.Installing PonytailFor Claude Code:claude plugin marketplace add DietrichGebert/ponytail && claude plugin install ponytail@ponytailFor other agents without plugin marketplace support, copy rule files directly from the GitHub repository into your project directory.Installing CavemanFor Claude Code:claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@cavemanFor Gemini CLI:gemini extensions install https://github.com/JuliusBrussee/cavemanInstalling for Cursor, Windsurf, Cline, and OthersCaveman can be installed via the unified registry:npx skills add JuliusBrussee/caveman -a <agent-name>Will You Choose Ponytail, Caveman, or Both?Token optimization is not just about saving money; it keeps AI Agent context clean and prevents context drift during long sessions. However, the larger takeaway from both skills is not to blindly accept advertised percentages—even from authors—since each figure typically measures a specific scenario rather than a general average. The surest approach is running benchmarks on your own codebase before adding Ponytail, Caveman, or both to your daily workflow.

Automating Excel and Google Sheets reporting is no longer exclusive to software engineers. With the rapid evolution of AI models like GPT, office workers can now create custom workflow automation tools using simple instructions with Codex, freeing up hours of repetitive daily tasks. Why Excel Formulas and VBA Are No Longer Enough For weekly recurring reports or automated integrations with email, Slack, and messaging apps, traditional methods like nested Excel formulas or recording VBA (Visual Basic for Applications) macros require specific technical skills and break easily whenever a single column in the source file changes. This is the exact gap that OpenAI Codex fills: you describe precisely what needs to be done in natural language, and Codex generates complete Python or Google Apps Script code ready to run in seconds. Codex Is Not a Single Product A common misconception is how Codex is accessed: it can be used via CLI in the terminal, IDE extensions in VS Code, Codex Web on the cloud at https://chatgpt.com/codex/cloud for developers and coding enthusiasts, as well as desktop applications for both macOS and Windows. For office workers unfamiliar with command-line tools, the easiest way to start is downloading the Codex desktop app. It lets you manage multiple agents simultaneously right from a visual interface without opening a terminal or configuring API keys—just log in with your existing ChatGPT account. What an Example Prompt Looks Like You only need to provide Codex with a detailed prompt like: "Write a Python script that reads the Excel file 'sales_raw.xlsx', filters orders with status 'Completed', calculates total revenue by branch, and exports the result to 'revenue_report.xlsx' with dark blue header styling." Codex will instantly generate standard, high-quality code, and you simply run the script to get your finalized report. Automating Local Excel Reports with Python and Codex For Excel files stored locally, combining Codex with two popular Python libraries—pandas and openpyxl—delivers outstanding processing speed. Pandas handles hundreds of thousands of data rows in seconds, while openpyxl manages cell formatting, header colors, and formula insertion as illustrated in the example above. Automating Google Sheets in the Cloud When your team collaborates on Google Sheets instead of offline Excel files, the Python library gspread or Google Apps Script is the ideal choice. Codex can write code that connects directly to the Google Sheets API via a Service Account (JSON credential file) to read and write data continuously without opening a browser. A Sample Workflow Automatically pull new form submissions from Google Forms into the spreadsheet Automatically categorize customer feedback by priority Automatically send daily summary emails to leadership at 17:00 This entire pipeline runs in the background with zero manual intervention once configured. 4-Step Implementation Process for Non-Coders Step 1 - Standardize input data: Ensure the Excel or Google Sheets file has clean, clear headers without arbitrary merged cells. Step 2 - Write clear prompts for Codex: Explicitly mention file names, column names, filtering/calculation steps, and desired output formats. Step 3 - Test and paste errors for AI auto-debugging: If the script encounters an error, copy the full error traceback and paste it back into Codex for automatic correction. Step 4 - Schedule automatic runs: Use Windows Task Scheduler (Windows) or Cron jobs (macOS/Linux) to run the script automatically on a set schedule. Risks and Considerations Before Handing Reports Over to AI Codex is powerful but not completely free; however, simple operations with Excel or Google Sheets consume very little quota, so light users can comfortably rely on the free tier. If heavier workloads are required, consider Plus or Pro plans—avoid the Go tier as Codex capabilities there offer little advantage over the free plan. Never paste system passwords, financial records, or real customer data into public AI chat interfaces. When asking Codex to generate code, always substitute sensitive details with dummy data of the same structure. For critical validations such as monetary amounts or tax formulas, do not trust AI-generated code blindly on the first run. Always cross-check the output during the first 1-2 executions to ensure the logic perfectly matches your actual business requirements. Automating reports with Codex does not make you a programmer, nor should it. The true value lies in understanding your own data and business processes well enough to describe them clearly to AI—Codex handles the coding. If your company has weekly recurring reports, start today by picking the simplest one, writing a prompt following the sample above, and running your first automated test.