A random mix from the whole library. Shuffle for a new set.
A legal librarian at a law firm had to check ten references for a Belgian lawyer working on warranty of liabilities cases. Three references had errors, one of them serious, and the AI Pro with skills and Google AI Overviews found the right reference in a badly protected PDF on revue-banque.fr where another tool pointed to the wrong one, and one more error was fixed using the next year's index of decisions.
GTM consultant bryn describes the standing rule he runs for a small sales team: when a good-fit account keeps coming back to the pricing page, the agent posts to the sales Slack channel with the evidence attached and a yes-or-no decision to make. The point is that reading and assembling evidence is the agent's job, not the rep's.
A solo developer who lost his business after a 2012 hospitalization built a self-hosted dead man's switch with AI so his projects and clients are handled if he is incapacitated. It has run for weeks, ships with 42 unit tests, and clients already cite it as a trust feature.
Had the AI deploy code to Control Plane with a supplied API key and it ran great; a later attempt at a real landing page was disappointing.
Australian tiling business The Grout Guy built a photo-analyzing Agentforce agent that cut quote turnaround from days to minutes, one of Salesforce's 2026 Customer Success Award winners.
Analyzer agents audited and trimmed skill files, cutting about 18 percent then about 600 more lines, and extracting bash into scripts turned up bugs.
The AI wrote a minor pull request for an open source webapp and on its own suggested and actually used Cloudflare Quick Tunnels to test over HTTPS.
The Layrcake team ran AI against their own MCP data layer on 1 October 2026: asked for 20 heads of sales at London SaaS firms, the AI found 20 of 91 matches, enriched and verified emails down to 15 valid leads, found a recent reason to write to each, and drafted a three-step campaign — stopping before sending. The logged run took under ten minutes and 145 credits, about $1.45.
A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.
A swarm of AI agents ran 4,654 searches to catalogue AI product names and trends, published as a public page.
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.