Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Lulu (mom, holding her young child on camera) set up an AI avatar named 'CB' in an AI app: she shared her weight (237 lbs) and goal (180 lbs), answered questions about frequency (4-5 days/week) and location (home/mix), and got a personalized Mon-Fri strength and cardio plan. She logs 'Workout complete' and gets confirmations back.
Added the AI rules and skills to split Terraform PRs into the smallest mergeable units, resulting in cases like 40 PRs with 38 approved and merged immediately.
He directs academic tech at a university. Every semester some instructors never set up their courses, so students walk into empty course pages. A day after signing up, he had the AI build a CSV of upcoming courses with no content, or where the instructor has never entered the course. The list also told him one course was already open to students when courses should not be open yet, so he closed it.
A user had the AI apply TurboQuant skills to optimise a Qwen3.5-9B model running locally via MLX on Apple Silicon. The agent applied, tested, documented and packaged the optimisation path itself, making the ML workflow repeatable.
In a skit-style demo, her AI Aaron P offered three date options (a wine bar, a BeltLine stroll plus Ponce City Market, a brewery with games); she picked the BeltLine plan and it was locked to her calendar for Sat Sep 26, 4:00-7:00 PM with parking tips and a reminder offered.
Communications analysis skill scans his communications, tracks the commitments he makes, flags missed follow-ups, and scores his communication against his own targets.
Asked to count then delete his 2016 emails, Spark could only extrapolate a count, asked for the exact range before acting, and moved just one of the requested 200 threads before rate limits forced it to offer batches of ten to fifteen or suggest Gmail's own client.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
The AI wrote Zig tools in real use, including a wasm utility integrated into a site and reverse engineering a USB wire protocol for an industrial camera driver.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.