Family-law trainer Stephen Smith built four working tools with AI, one conversation each: a settlement schedule that shows a client how much of an $8,000,000 award is actually spendable and when, a two-sided case chronology with exhibit links, a parenting-time calculator that counts overnights and percentages, and a case-path timeline clients get at the first meeting. The examples use training data, and he warns that the AI wrote the math, so every number must be checked before a client relies on it.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
£350at stake
This one went wrong. See what happened before you try it.
He drives for an assisted living facility that tracked every resident trip on spreadsheets the front desk found hard to use. He built a web app with AI that shows all trips past, present and future with conflicts and updates, from his desktop or phone. It improved his daily work and the front desk’s, and took a few months where the old way would have taken about a year.
A user runs an AI named Reaper against his credit card debt: the balance went from $8,400 to $7,912 by day six, with daily progress reports from the bot. The paydown is small, tracked and reported like a coach with a ledger.
Chris William Young (40 followers), juggling a 9-to-5, Ironman 70.3 training, and investing in a climbing gym, showed screen recordings of the AI building DoorDash grocery carts from Jewel-Osco ($130.02) and H Mart ($50.33), noting substitutions and missing items like Thai tea mix, then placing the order for delivery. He explained he avoids DoorDash himself out of exhaustion, and walked through the workflow: prompt, the AI searches memory, takes over the browser to shop, requires user approval befor
An agent researched available tools, built an eval set, and tested tools against each other to pick the set used for his singing app, cutting build time from months or a year to about 10 days.
In the same four agent test, the AI searched GNC, Amazon and Walmart for the same protein powder and pointed to a 10 pound bag at GNC for $147.99, about $0.92 an ounce. The link it gave led to a page not found error. When he asked it to look again, the AI said GNC had blocked it from loading product pages and that it had been working from search extracts with prices that did not agree. It also said it could not check Costco, Target or Bodybuilding.com.
This one went wrong. See what happened before you try it.
Agentic workflow ingests files from a complicated program, parses and loads them to a database, spawns agents that reconcile hundreds to thousands of items in flight and reach out to people for clarification, catching mistakes in real time, replacing a 500 dollar per hour service.
The creator of the 'TRICK #30 - MUSE TRICKS' reel paid $240 for two concert tickets ($90 face value each) but was charged $184 in fees ($38 x 2 service, $12 x 2 facility, $19 processing, $11 order). Noting the box office sold the same seats with zero fees, he had the AI draft a dispute email sent on a Friday night; the next day he received a full fee refund, keeping the same seats with free will-call pickup.
Luke Davies runs Davies Construction with a team of the AI set up like a company org chart, with bots for estimating, admin, books, sales and project work. Day to day the bots sort the inbox and draft replies, pull tasks out of meeting notes into a list a person approves, and create and update the job tasks in ClickUp as work moves on the Wunderbuild board.