THE CLAUDE CODE TEAM JUST KILLED PROMPT ENGINEERING
They stopped typing prompts and put the agent inside loops that run, verify and stop on their own while they sleep.
Runs on 4 loop types. No hand-holding. No next prompt.
Everything you used to do by hand, you now hand off:
- The check → a SKILL.md the agent verifies its own work against
- The stop → /goal, stops when the goal is hit or the tries run out
- The trigger → /loop, fires on an interval and reacts to what changed
- The prompt itself → a schedule that starts the work without you
Most people prompt harder and get a chatbot.
This one runs /goal until Lighthouse hits 90 and stops itself. And it checks your PR every 5 minutes to fix failing CI.
The catch: an agent is no judge of its own work. So /goal runs a separate evaluator, and code review goes to a second agent with fresh context.
You + a goal + a loop = an agent that ships while you sleep.
Save this before you write another prompt.
显示更多
NOTEBOOKLM + A BROWSER AGENT JUST KILLED THE $60K SALES REP
One person wired Google's NotebookLM into a browser agent that finds leads and closes deals on the live web while they sleep.
Runs on NotebookLM + an agentic browser. No calls. No team.
The numbers are insane:
- Sales rep: $60K/year + commission
- Lead-gen agency: $2K to $5K/month
- A closer: 20% of every deal
- This setup: a free Google tool + one browser agent
- Skill required: feed it your offer
The opportunity is even wilder:
Most people use AI agents wrong and get a chatbot. This one ran overnight and closed a $497 sale, then copies itself the moment it works.
One person + NotebookLM + a browser agent = a sales team that runs while you sleep.
Save and watch the clip.
显示更多
speed camera company CEO right after signing a $2M city contract, watching a college kid run the same radar off a balcony webcam and $20 of Claude
A 20-year-old student from China, Li Hao, built an AI speed radar with Claude alone and sold it to a city district for $317,000
He wrote the whole thing in 9 days, spending about $20 on Claude API calls
He set an old camera on his balcony, pointed it at the intersection below, and let Claude watch the road
Claude tags every car, motorbike and pedestrian in real time, 653 in five minutes, and flags anyone over the limit
The moment a car speeds, Claude clips the video, reads the license plate, matches the owner, and emails the fine on its own
A normal radar takes one photo and misses half the time. Claude records full video, so there is nothing to dispute, and the fines go out with no operator
He walked into the district office with a flash drive and asked for 10 minutes. he left with a contract
Every Claude config he used is in the article
显示更多
A HARDWARE MODDER BOLTED A BATTERY PACK ONTO A $599 MAC MINI M4 AND TURNED A DESK SERVER INTO A BACKPACK AI RIG THAT RUNS FOR EIGHT HOURS WITHOUT A WALL OUTLET
he posts a video of the mac mini with a slim battery module clamped to the side, USB-C plugged into the back. no power brick, no outlet, just the 10 to 30W draw of the M4 chip pulling from a 20,000mAh bank. a full work day on one charge. this is not a portable laptop trick. it is a desk-class AI server that fits in a sling bag
the same $599 mac mini i recommended in last week's article as the silent default, now untethered. pair it with a mobile hotspot or a Starlink mini and you have a fully off-grid LLM stack that answers questions in a forest, on a plane, in a power outage. the model lives in the box, the battery powers the box, that is the whole stack
this is not a gadget. it is the first time the words "AI server" and "fits in your bag" belong in the same sentence
显示更多
Anthropic CEO:
"If my revenue is not $1 trillion, even $800 billion,
there's no force on earth, no hedge on earth,
that could stop me from going bankrupt."
In a 3-hour podcast, Dario Amodei does the math on his own bankruptcy.
Revenue 10x a year.
90% of code written by the model.
A country of geniuses by 2028.
He can't tell you if it ends in trillions or zero.
The most honest voice in AI, or the biggest bubble admitting it?
显示更多
Creator of Claude Code:
"Right now you still need to know how to code. In a year or two, it won't matter. I haven't edited a single line by hand since November."
In a 90-minute podcast, Boris Cherny breaks down the exact setup behind the tool now writing 4% of every public commit on GitHub.
More value than a $500 vibe-coding course.
Save this. In a year we'll know if he was right.
显示更多
Creator of Claude Code:
"Right now you still need to know how to code. In a year or two, it won't matter. I haven't edited a single line by hand since November."
In a 90-minute podcast, Boris Cherny breaks down the exact setup behind the tool now writing 4% of every public commit on GitHub.
More value than a $500 vibe-coding course.
Save this. In a year we'll know if he was right.
显示更多
NVIDIA just made paying for AI feel optional.
Open model, a million tokens of context, free tier with no per-token cost, runs on your own hardware.
Entire codebases, whole data rooms, a year of chat logs, all swallowed in one prompt. No chunking, no RAG, no rate limit theater.
The closed-AI premium has 90 days to defend itself.
Bookmark this and come back.
Open beat closed. Again.
显示更多
Someone built THIS using 460k tokens on Opus 4.8.
No degree. No team. No game dev background.
And you're still telling yourself you 'can't make apps.'
The distance between an idea and a real product just hit zero.
Stop scrolling. Start building.
显示更多