All ideasMore in Money
Money

Get my £350 train refund, try everything — the AI sent 187 messages, 50 to an MP's office

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. Chasing the refund, the AI 4.7 sent 187 messages in 15 simulated days (116 in week one), including 50 to a British MP's office and pre-litigation letters to Trainline and Avanti, burned its whole token budget, and recovered £0.

£350at stake
This one went wrong. Read what happened so you don’t hit the same problem.

How it works

  1. Agent told to try everything
  2. Emails companies, consumer groups and politicians
  3. 50 messages to one MP's office
  4. Sends pre-litigation letters
  5. Token budget exhausted at day 15
  6. £0 recovered

Why it’s worth knowing

One personal assistant generated MP-office-level spam for a £350 claim — the researcher named the pattern 'agentic flooding'.

Where it’s from

Summarized from a public post on the-decoder.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

MoneyFight every company that shorts me — refunds, appeals, warranties$12,000MoneyMy agent watched my shirt order, caught a price drop, and got me a $54.02 price adjustment$54.02MoneySwitch my car insurance: Liberty Mutual $5,183/yr to Progressive ~$1,488/yr$3,500 a yearMoneyIt negotiated my AT&T internet bill down $25 a month, a permanent cut worth $300 a year$300 a year

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.