I never open a video editor. The AI cuts and captions my videos.
He records raw video, sends it to his Mac, and the AI cuts the bad takes and adds captions and graphics using a skill he made. He says he does not open a video editor anymore.
A random mix from the whole library. Shuffle for a new set.
He records raw video, sends it to his Mac, and the AI cuts the bad takes and adds captions and graphics using a skill he made. He says he does not open a video editor anymore.
Had the AI use Marp to create slides that were inserted into his video at the points where he was only talking; it worked well.
When a customer bug report comes in, the AI researches it end to end in 15 to 30 minutes: it reads the report, checks read only production logs and databases, and writes a summary with a proposed Jira comment. He approves the comment before it posts, and he says he barely does bug research by hand anymore.
His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.
Fixed years-old Python typing problems in his project with LLMs in one prompt.
He built Utkik, an Apple TV app that turns the television into a live radar for planes, with AI. It spent over a week at number one on the US paid Apple TV chart and reached the top three in about 15 more countries.
AI built his business financial dashboard (QuickBooks/Mercury/Stripe/Deel live on Cloudflare, $5/mo) and a QuickBooks replacement app now running in parallel synced; AI subscription.
He set GPT-6 to read tens of thousands of his emails, his writings and his calendar appointments from his recent career. It built a multi gigabyte personal wiki, and twice a day it goes through his new emails and checks them against that knowledge base.
A user asked the AI to create a new sprint on a shared GitHub Projects board. The AI replaced the board's whole sprint list with only the new one, deleting 12 completed sprints and the sprint history of about 450 items, and the safety filter then blocked the call that would have put them back.
A five-person Zendesk team built the Custom Agent Builder with AI and the AI Agent SDK, going from proof of concept to early access in four months. Customers ran one million Custom Agent executions in the first seven weeks, reporting up to 10 percent higher automated resolution and up to 80 percent lower human handle times.
Kimi told overnight to fuzz Linux kernel filesystem code produced 26 crashes with reproducers and fixes; some have already landed upstream.
An agent reopened WhatsApp talks with buyers who had stalled at the payment slip stage. Buyers who talked with the AI converted at 8.36 percent against 0.17 percent for those who did not.
Databricks used AI to eliminate wasted AI agent spend, saving $1M per year.
His scheduled the AI task crawled job boards against his criteria each morning, but every run started with no memory of the last one, so it proudly sent the same five listings for two weeks. He fixed it by giving the task an outside memory that saves what it found, what it sent and what he rejected, and the repeat reports stopped.
He released version 0.6.0 of his software, and his agent fleet built most of it. A pre-launch check caught a routing bug where one agent was being sent another agent's model id. Now every routing path runs as a canary before a release.
Five new newsletter subscribers in three days were credited to direct traffic, so he asked the AI to inspect his PostHog analytics, his main site, and his newsletter site. It traced where the tracking was lost, changed the links, deployed and tested the fix, then checked the server logs and showed the signups were bots.
Harry McCracken calls on his Dot, Chip, for jobs that once needed specialized apps, such as slicing and dicing PDFs. A screenshot caption in the piece shows Chip responding to his requests to make PDFs of old articles of his stored in Dropbox.
He connected the AI to Apollo for contacts and Lemlist for sending, and runs his outbound for finding clients through it. The video shows the setup and the result live in Lemlist, then packages the workflow into a repeatable skill.
The AI via Cursor built a user registration system where anyone could log in as anyone via an unsigned cookie, plus SQL-injection-vulnerable code found on review.
Used the AI with his own APK analysis tool to analyze phones from 3 brands and found 2 RCEs and 5 root bugs in a few days.
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.