AI News

Luo Yonghao tries TRAE in Double 11 livestream: you can build software in minutes without knowing how to code

Phoenix TechnologyUpdated Nov 11 16:37

AI summary

In his Double 11 livestream, Luo Yonghao demonstrated TRAE, a full-chain AI development platform. Claiming he cannot write a single line of code, he generated in minutes a short-drama research report with charts, turned more than 50,000 characters of material into two sets of PPTs, and even built a voice input method app from a hand-drawn sketch. TRAE's first-month trial price is 9.9 yuan; as of June this year, it had more than 10 million registered users worldwide and 1.6 million monthly active users. A GitHub report shows that more than 40% of PRs on the platform are initiated by AI Agents.

Body · AI translation

During the Double 11 livestream, the studio was transformed into an AI showroom. Luo Yonghao got hands-on with TRAE and instantly became the voice of the masses for AI Coding. QbitAI Download the client for exclusive early access. November 11, 2026, 13:53:00, from Beijing.

Wen Le, reporting from the Non-Mainstream Lab.

Truly, one lives long enough to see everything. This year, the most technically sophisticated thing about Double 11 turned out not to be figuring out how to stack discounts.

First, the top livestreamer was enthusiastically selling two trillion Tokens, and right after that, I scrolled into Old Luo's livestream—

TRAE, the full-chain AI development platform, which Luo Yonghao calls "Cui Laosan," was offering a first-month experience at the irresistible price of just 9.9 yuan.

A fifty-something man who claims he "can't write a single line of code" set up a computer and projected the screen on the spot, and in front of tens of thousands of viewers, he directly showed off his moves:

In a few minutes, he generated a short-drama research report with data charts;

He transformed more than 50,000 words of dense material into two sets of launch-event-grade PPTs;

And from a single rough hand-drawn sketch, he somehow built a genuine, fully functional voice input software.

Amazing. AI Coding, which is usually repeatedly tested by programmers in tech forums and scrutinized over performance metrics, was overnight pushed onto a mass-market sales stage.

So? Why are the big livestreamers collectively selling deep and mysterious technical products this year?

A huge shift this Double 11

In previous years' Double 11, what we grabbed was nothing more than toilet paper stockpiled by the box, skincare products whose discounts we couldn't figure out, and digital hardware with all sorts of specs...

This year the style is different.

Li Jiaqi's livestream and its two trillion Tokens let everyone see for the first time that AI, too, can be "stockpiled by weight."

But lively as it was, many ordinary people who followed the trend and placed orders instantly had a row of question marks over their heads:

I bought a bunch of cold Tokens—what exactly can I do with them in daily life? Use them to chat with a large model and play word-chain games to kill time? Or casually search for material and churn out a document?

The public has become desensitized to pure technical parameters and abstract numbers very quickly. Once the novelty-seeking curiosity of onlookers passes, the only thing everyone really cares about is:

Can this thing become something I can actually use in my hands?

These two livestreams have actually hit a cross-section of the industry.

Gartner's 2026 Generative AI Hype Cycle from the authoritative research firm shows:

The market has already passed the early concept-inflation phase and is accelerating toward a pragmatic stage that values real-world results.

Growth in large models that simply chat and answer questions has peaked, while capabilities closely tied to business scenarios, such as code generation and application building, are receiving more attention.

The industry directly calls 2026 the first year of agents, and even the Cyberspace Administration of China has specifically laid down rules for agents.

Anthropic's coding trends report earlier this year also mentioned that software development is undergoing its biggest paradigm shift since the invention of the graphical interface:

Anyone can become a developer is no longer a slogan on a PPT, and the programmer's role is slowly shifting from "writing code by hand" to "directing AI to do the work."

Beyond selling raw materials like underlying compute power and chat windows, the industry has also begun to output finished-product capability that can directly deliver usable tools.

So look again at these two livestreams: what Li Jiaqi sells is raw material, compute quota; what Old Luo sells is a finished product, a tool you can use right away.

What these two livestreams hit is exactly this watershed from selling conversations to selling results.

As a Coding Agent that takes in compute power and directly produces applications, it fills the gap from raw material to finished product.

Software development used to be regarded as an incomprehensible mystery, but under the whole-network scrutiny of a livestream, it was compressed into a process as natural as typing and chatting.

Viewers understood too:

What was put on the shelf this time was not conversation quota that gets consumed at any moment, but a set of digital productivity that can turn ideas into real tools at any time.

The public's guard against technology also loosened on the spot.

Luo Yonghao builds things live

TRAE has multi-file awareness, automatic environment configuration, and underlying local code orchestration capabilities.

In the past, the most off-putting, tedious steps in software engineering for laypeople—

configuring environments, installing dependency packages, setting up project frameworks, fixing configuration file errors... this whole pile of dirty, exhausting work that makes one's scalp tingle—are all encapsulated in the system's underlying layer and run silently.

To put it more plainly, it can let you build software purely from an idea.

And what kind of person is Old Luo?

Everyone online knows his nitpicking persona. With him on stage, the whole sales session became a high-pressure test.

As a result, this earnest layman openly stated:

I can't write a single line of code. In the past, making software required recruiting designers, product managers, and a bunch of engineers, and communicating with them was like being a subordinate; now with Cui Laosan, I can revise it a hundred times and it won't even roll its eyes.

In the livestream, Old Luo projected the three major results he had built in a few hours, each hitting the daily pain points of working people.

Facing the short-drama boom, Old Luo directly gave TRAE instructions, requiring an analysis of the short-drama market from January to October this year.

AI took less than 4 minutes to spit out a plain-text report. Old Luo immediately turned into a picky boss and started finding fault:

Text alone won't do. Import it directly into Feishu. Use pie charts where pie charts can be used, and bar charts where bar charts can be used. It has to look serious enough to fool the boss, but it must not deceive the boss—the data must be solid and reliable!

Old Luo's computer unexpectedly froze once midway through. After restarting, he told the AI, "It just crashed, continue completing the task." TRAE not only did not mock Old Luo with "long live understanding," but steadily picked up the progress and within a few minutes generated a Feishu document rich in both text and images.

Even better were the subsequent workplace-survival combo moves.

Old Luo had it stand in management's shoes to run a stress test, and in reverse pulled out a response checklist, laying out all the predictions in a three-tier structure of "one-sentence core answer + detailed data support + follow-up Q&A."

At this Monday's regular meeting, wasn't he just directly confident?

Faced with cutting-edge industry materials, Old Luo fed a deep document of more than 50,000 characters straight into TRAE to read through and digest, asking it to organize it into a PPT, split into two sets: a "speaker version" and a "self-service reading version."

The speaker version kept only core viewpoints, flowcharts and cases on each page, with all the detailed reasoning stuffed into the speaker notes below; the reading version was complete in text and images and logically self-contained, convenient for others to take and read silently.

Old Luo also specifically made a request:

Do it quietly in the background for a while, don't grab the foreground graphical interface and delay me from doing other things; change the format to our company's widescreen 21:9, and use a blue theme.

TRAE obediently took the whole order, and in a short while two neatly delivered files with careful layout arrived.

Of course, the most fun was a tool Old Luo came up with himself: Mantou Voice.

Because the Microsoft mouse in his hand is jokingly called the Mantou mouse, he wanted to make use of that idle middle scroll wheel:

In any software, long-press the middle scroll wheel and a small floating window pops up at the cursor to start speech-to-text; drag and release onto a punctuation mark or the send button, and input is completed in one go.

Old Luo first stuffed an extremely scribbled hand-drawn wireframe sketch at TRAE. TRAE understood immediately, not only reproducing the interaction concept in the sketch, but also proactively breaking down the button functions, failure fallback plans and cross-application coverage.

Not only did it produce a finished product in one go, TRAE could also export the project package for secondary development at any time.

Old Luo realized he had chosen the wrong model at the start, so he falsely claimed he was going to change computers (which was not actually the case...), and had it package up the source code and project description to make switching devices convenient.

Fortunately, TRAE preserved all the project progress, saving this veteran product manager's dignity...

The local software that finally ran successfully could be used in browsers, chat windows and even Feishu. Hold the scroll wheel and speak, and the text would appear on screen accurately in real time; casually swipe to the right-side button and release, and commas and question marks would be automatically filled in, and it could even directly trigger Enter to send.

I have to say, an excellent product concept—we are all fans of Brother Long's tech (doge)

Imagination is free, creation is free

After watching the livestream, many people's first reaction must have been to see something new, and right after that their hearts itch:

I'm not a programmer—can I really use it to do something?

Yes, and the threshold is much lower than you think.

In the past, making a small piece of software meant either teaching yourself syntax for years and staying up until you went bald, or finding a technical team to outsource it, with starting costs often tens of thousands of yuan.

Now, underlying code writing is deeply managed by TRAE, and the cost for ordinary people to validate an idea keeps dropping. At most a few hours of spare time, and you can shape the idea in your head into a clickable, interactive prototype.

As of June this year, TRAE's global registered users have exceeded 10 million, with 1.6 million monthly active users, and a considerable portion of users open it to work nearly 5 days a week.

So what do ordinary people use it for?

Two high school students who love playing badminton spoke from experience!

Because hiring professional coaches long-term was too expensive, and they usually could not see the details of their own movements clearly, they—who knew nothing about programming—used TRAE and, by calling sensor data from phones, watches and earphones, made an app that can analyze swing movements and give guidance, and it has even been officially listed on app stores;

There was also a young man torn about whether to install surveillance cameras in his grandmother's home.

If installed, he could know promptly when the elderly person fell, but at the thought of Grandma being watched by a camera all day, he really could not bear it.

In the end, he used TRAE to build the Fanglian Guardian Assistant, which did not rely on cameras or microphones to record audio or video, but only used a pillbox and door sensor to judge the situation, pushing reminders only when medication was missed or there was an abnormal outing, preserving the dignity and privacy of the elderly in their later years.

The global developer community GitHub mentioned in its annual report "State of Octoverse":

AI is lowering the development threshold, and a large number of citizen developers without traditional programming backgrounds are beginning to participate in building applications; more than 40% of PRs (pull requests) on the platform are initiated by AI Agents, and open-source contributions from non-professionals are increasing rapidly.

△

Source: "State of Octoverse" 2026

Although TRAE has not smashed the rice bowl of senior system architects, nor will it make you rich out of thin air, it has genuinely filled in the development shortcomings for independent creators who lack technical partners.

The thing blocking ideas from landing is no longer incomprehensible terminal errors. As long as you keenly capture the real pain points around you and express them clearly, you have a chance to land them painlessly.

Administrative and operations staff sitting in offices, tortured daily by all kinds of bizarrely formatted spreadsheets, can absolutely use it to whip up an exclusive batch data-cleaning script;

Independent photographers and illustrators no longer need to buy expensive website templates; a few natural-language interactions can build a portfolio display page with a unique style;

Small e-commerce sellers can casually customize a small automated accounting plugin tailored to their own store's special commission rules.

...

One person, with a clear business concept plus the seamless execution of the tool, can support a process that used to require a small team to run.

Don't say it—I really spotted a need while watching the livestream, and immediately TRAE'd it!

I built a cliff cabin with my bare hands, ready to drag my "enemy" over to talk through our issues (doge).

What does everyone want to whip up?

"Special statement: The content of the above works (including videos, pictures or audio) is uploaded and published by users of Dafeng Hao, a self-media platform under Phoenix Net. This platform only provides information storage space services.

Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."

Source

Phoenix Technology