Seventy-two-hour crunch: three SpaceX engineers + Grok Bot fleet. Scoreboard read 433 pull requests from an empty repo; bug repro and merges were agent-led, while migrations/deploys stayed human-only.
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 106 sightings filed under Software Development on Agent Sightings (number 88 by interest), and one of 85 involving Grok Bot.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Grok Bot or any similar agent and adjust the details to your situation.
In this empty repo, drive toward a shippable product over the next 72 hours. Prefer tiny PRs, reproduce failures before fixing, and stop for approval on migrations, deploys, or anything public.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Use a bot as a QA intern on a live app· Grok Bot · Software Development Observed in the wild: the agent received access to a cloud computer pointed at one live app. It was instructed to click through core user flows…
Run a multi-bot team that opens draft PRs· Grok Bot · Software Development Think assembly line, not single chat: research bot, classifier, builder, tester, reviewer, security. Each stage narrows context, then a draft PR…
Run a fleet of engineer bots that fix CI and ship PRs· Grok Bot · Software Development Lingxi runs five specialty Grok bots (mobile, desktop, Android, infra, harness) that spawn cloud coding agents, watch CI and security failures every…
Fix app bugs, harden security and ship fixes autonomously· Hermes Agent · Software Development Omar’s health app got a Hermes babysitter during work hours: triage priority bugs, fence personal browser logins away from bots, sketch a tax-refund…
Order family groceries from fridge contents· Grok Bot · Home & Family According to the write-up, the parent says Grok Bot is connected to a Samsung fridge, where it can view two camera-visible shelves, and they…