Gemini use cases
40 real things people got Gemini to do, each with what they asked, how it went, and the prompt to copy.
Analyze 170k LLM logs overnight
A user left a Gemini agent running overnight to analyze 170k LLM logs with the llm CLI and a free model, and it finished the job despite limits.
Appeal a denied travel insurance claim
The poster used Gemini during the appeal of a rejected travel insurance claim and says the appeal succeeded.
Build a browser 4X strategy game with LLM coding help
The poster built the browser 4X game Hexwardia in two weeks using Grok and Gemini to write the combat engine, fog-of-war, map generation and heuristic AI.
Build a match-3 game from a single prompt
An author prompted Gemini 3 Pro once to produce a working Candy Crush-style game with a shareable link, and says a non-technical friend did too.
Build scored sales lead profiles and outreach drafts
The author built a pipeline with Gemini Deep Research, NotebookLM and Sheets that produces a scored lead profile and outreach draft in under 20 minutes, tested on three companies.
Call local stores to check toy stock
A writer used Gemini's calling feature to phone local stores about a Labubu figure and got text or email summaries of availability, price and hours.
Compare grocery prices across stores from a list
A tech worker built a Gemini browser agent that takes a typed or scanned handwritten grocery list and compares prices on Amazon Fresh and Flipkart Minutes.
Configure macOS and dev tooling from the terminal
Gemini CLI ran defaults write commands to set Dock auto-hide, and was also used to install Docker and configure Git GPG signing.
Control robots with generated code and voice commands
Gemini detects objects and writes robot API code, and with 10 in-context demos an ALOHA robot packed boxes and folded a dress; voice commands became robot plans.
Critique blog post drafts for technical errors
A developer built a custom Gemini CLI command that reads a blog draft from disk and critiques it for technical errors, used in an iterative editing loop.
Diagnose and roll back bad config during outages
Google SREs use Gemini CLI to pull logs, find a bad config push, generate a reverting changelist, and file postmortem action items via MCP.
Edit existing video clips with plain-English instructions
A creator tested Gemini Omni Flash over 36 hours, editing clips in place from typed instructions while preserving lighting and camera angle, with variable quality.
Edit raw footage by describing the video you want
Cardboard goes from raw footage to an edited video from natural-language instructions.
Find holiday gifts and check stock and sales
A writer used the Gemini app and its agentic feature to find gift ideas and retailers and check stock and sales, noting some features weren't fully ready.
Find security flaws in open-source software
Google's Big Sleep agent reported about 20 security flaws in open-source software, following its SQLite find.
Fix a broken Delete button in a GitHub repo
The author had Jules clone a repo and fix a Delete button so it disables deletion of content older than two hours, with tests added unprompted; the author reviewed and published the branch.
Handle hotel booking and directions on a business trip
A traveler used Gemini on an international business trip for last-minute hotel reservations matching company policy, plus walking directions through Heathrow and to a venue in Switzerland.
Hunt for unpatched vulnerabilities in SQLite commits
Google's Big Sleep agent reviewed recent SQLite commits starting from a patched bug and found an exploitable flaw, which was fixed before release.
Let AI models trade stocks autonomously with $1k each
Poster ran four AI models on a weekday pre-market prompt to trade $1,000 portfolios each for nine weeks; ChatGPT came out ahead.
Navigate Goat Simulator 3 with a game-playing agent
Gemini-powered SIMA 2 navigates Goat Simulator 3, and a human player can direct it to improve its performance.
Orchestrate a Spot robot through multi-step tasks
Gemini Robotics ER 2 drives a Boston Dynamics Spot, watching video to confirm tasks like tying a trash bag are done before moving on.
Play a button-clicking game via a browser agent
A developer wired Gemini's Computer Use model to Playwright in Java and had it play a simple button-clicking game to verify click-coordinate scaling.
Play Pokémon Blue with an agent
The Gemini Plays Pokémon agent reads game RAM and screenshots, turns actions into button presses, and uses pathfinder and boulder-puzzle sub-agents.
Research hotels and pull tax documents with Chrome auto browse
A tester used Gemini in Chrome to research Lisbon hotels across sites and fetch tax documents from payroll portals; it stopped before placing a grocery order.
Resolve bank customer chats with an AI chatbot
Commerzbank's Bene chatbot, now on Gemini, handles over two million chats and resolves 70% of inquiries.
Resolve customer calls proactively with AI agents
TELUS uses Gemini Enterprise for CX agents to proactively resolve customer calls; Google's case study reports 30% of calls resolved and issues resolved 87% faster.
Reverse engineer legacy systems without source code
Thoughtworks consultants used Gemini 2.5 Pro in a two-week pilot to produce validated blueprints of legacy systems' functionality.
Run multi-step tasks with model switching
@dani_avila7 tested Perplexity Computer on multiple tasks, where it picked Gemini 3 Flash for some steps and Opus 4.6 for code writing.
Run oral final exams with a voice agent
A professor used a voice agent to examine 36 students over 9 days, with an LLM council grading transcripts and surfacing class-wide gaps.
Run voice and chat support assistants with memory
AT&T deploys Gemini-based voice and chat assistants with 60-day memory, reporting 20% more inquiries fully automated.
Scan thrift store items and flag good deals
An agent processes video frames from a thrift store, looks up online prices for items, and alerts the user to good deals.
Search rentals and book apartment tours in a chat assistant
A how-to describes using Zillow Rentals inside Gemini and ChatGPT to get filtered live listings and book a tour time; it is a guide, not a completed tour.
Shop Etsy for party supplies within a budget
Chrome auto browse with Gemini searched Etsy, added items to the cart, applied discount codes and left the cart ready for the user to review.
Solve open math problems autonomously
DeepMind's Aletheia agent on Gemini Deep Think was evaluated on 700 open Erdős problems and autonomously solved four.
Sort waste using local recycling rules
Gemini Robotics-ER 1.5 looks up local recycling rules online, then plans and sorts objects into compost, recycling and trash bins.
Summarize emails and draft replies with Gemini Gem flows
The writer plugged a custom Gemini Gem into Workspace Studio flows that run in the background, summarize Gmail messages and create draft replies to review and send.
Summarize the day's new emails and manage meetings
A user asked an AI assistant to summarize emails received that day and got a summary in under 30 seconds; it also handles meeting summaries, action items, calendar and drafts.
Triage an inbox and plan a trip with Gemini Agent Mode
A writer had Gemini archive messages in 100+ unread emails and leave reply drafts, and describes it comparing hotel prices and holding a room.
Turn a blog post into an animated infographic
A content creator fed a blog post into Gemini Canvas, which produced a coded animated infographic using brand colors and audience details from the chat thread.
Vibe code an HTML5 browser game
The developer of Xenodochium built the game with Gemini, hit repeated errors, and worked around them by starting a fresh chat.