Fable and GPT-5.6 at max effort did a task that would have been a near 6-month project in a week, building a data capture pipeline, a synthetic data baseline, and building and testing 100 classification model variants with near-SOTA results.
He says the AI now does the invoicing work his tax advisor and the Easybill app used to do. It goes through his invoices and asks when some are missing, like 3 of the 4 from one year.
He is a consultant, and the free apps he and his team used to track time for the official timesheet all annoyed him. So he made his own time tracker, ConClock, with AI, and it is already at version 0.7.2.
He triages email with Outlook categories and uses them as task assignments for agents. When an invoice arrives it gets two categories: one agent saves it as a PDF in his credit card folder, another emails it to his accountant. Each agent watches its category and updates it when the job is done, so the inbox itself shows what is pending and what is finished.
He runs product marketing at a SaaS company. The AI audited where old icons appear across 12 products, sites, decks and emails and produced a tracker of about 200 rows to assign out. It built the URL redirect map for a site restructure, runs a browser routine that pastes page text into a sheet, and writes quarterly status updates in 20 minutes instead of most of an afternoon.
Ryan Mercer spent a weekend building a SaaS with AI and Next.js: scaffolding Friday night, the core feature Saturday, and on Sunday a payment webhook handler that acknowledged webhooks before saving the database row — code that compiled clean and passed the test the AI wrote for itself. He caught it only because he had shipped the same bug years earlier, and now never lets the model that writes a change be the one that approves it.
This only partly worked. Worth knowing before you try it.