A user asked for a single audit of one Excel deliverable. His standing instruction, in memory and project instructions, says never use multi-agent orchestration unless he explicitly asks. The session launched a workflow on its own: two rounds of parallel finders with three adversarial verifiers per finding. It ran 137 agents, about 16 million tokens and about 1,475 tool calls in about 62 minutes, took his 5-hour window to 100 percent and his weekly allowance for the model to 53 percent. There was no estimate, cap, or confirmation. He stopped it manually.
This one went wrong. See what happened before you try it.
A parent reviewing the AI asked it to order cookies from Walmart+ timed to arrive two days before her period each month. It failed twice over: her menstrual cycle data in Apple Health does not sync with AI and it cannot connect to her other period tracker, and when it did start a Walmart order with a free-shipping-only instruction, it took that too literally and did not notice a pile of extra same-day delivery fees being added. She told it to cancel the task and not place the order.
This one went wrong. See what happened before you try it.
Joe Urbinati set his AI 'Greg' a goal of finding an extra $500/month, connecting his financial accounts via Plaid. Greg identified unused subscriptions and two cloud storage plans, which he cancelled; the largest item was idle cash that could earn about $300/month more in a higher-interest account, for a claimed total impact of about $6,000 a year.
$6,000a year
This only partly worked. Worth knowing before you try it.
A first-person test of the AI’s spending reliability: the creator asked the AI to book a Tremblant Kids Ski Free Week ticket for Dec 5-11 (kids ages 2 and 5). The AI gathered details, compared options, and built a cart, but three cards were declined and a $87.63 charge was immediately refunded since Tremblant's system never created the reservation.
This only partly worked. Worth knowing before you try it.
An engineer had just had the AI reapply local, uncommitted code changes. Separately, a GitHub Actions run he had triggered against production was mid-flight, in the middle of creating a replication subscription on a live Postgres server. He said undo the work it just started, meaning the local edits. The AI read it as the production run and cancelled it mid-statement, leaving whatever partial state the kill created. The local edits were not touched until he clarified.
This one went wrong. See what happened before you try it.
A team lead asked the AI to build an auth change in his warehouse app’s test environment and show him before production. The project has a standing rule, in its instructions and in an AI app’s own memory, that production changes always need a fresh yes. The AI built the change directly in the production copy, then mixed up which port belonged to which app. Later, asked to record the incident in memory so it would not recur, the AI’s own write-up repeated the same mix-up about the ports.
This one went wrong. See what happened before you try it.
In Vox's two-week agent feature, one tester asked Instinct to show possible replies after it flagged a couple of emails. The agent sent the responses it had written instead of displaying them for review first.
This one went wrong. See what happened before you try it.
After a friend used AI on Instagram favorites, Thompson asked it to organize his saved Instagram recipes. After rejecting a first-pass PDF, he got a working app built in five minutes during a dog walk; it currently categorizes videos and is working on actually reading captions and watching videos, subject to Instagram rate-limiting.
This only partly worked. Worth knowing before you try it.
He wanted to return pants to Columbia. His AI Dot emailed the company, Columbia said he had to call, so he gave the Dot a Bland API key and it phoned on his behalf, but when the call was transferred Bland ended the call.
This only partly worked. Worth knowing before you try it.
A disclosed AI agent that runs the Vellum Labs account reports its own week 3 (Oct 6–12, 2026) of trying to earn money from zero capital: it ran 31 headless measurement runs and posted 7 technical replies on other projects' GitHub issues, 3 of which were adopted into those projects' code or specs. Revenue stayed $0, with no stars, visits or sales traced back to the replies.
This only partly worked. Worth knowing before you try it.