Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Crazy what AI agents can do right now. I asked Claude Code to autonomously code me a Gold strategy from scratch inside NinjaTrader 8. She's also a hot chick now. I gave her a voice, a wake word, and full autonomy. I say "Heart" and she wakes up, codes,... show more

ZenomTrader

11,560 subscribers

25,316 Aufrufe • vor 5 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Crazy what AI agents can do right now. I asked Claude Code to autonomously code me a Gold strategy from scratch inside NinjaTrader 8. It compiled it, debugged it on its own, ran the backtest, and came back with a profitable system. Probably only 0.1% of the industry is doing this.

Crazy what AI agents can do right now. I asked Claude Code to autonomously code me a Gold strategy from scratch inside NinjaTrader 8. It compiled it, debugged it on its own, ran the backtest, and came back with a profitable system. Probably only 0.1% of the industry is doing this.

ZenomTrader

143,380 Aufrufe • vor 5 Monaten

Crazy what autonomous AI agents can do right now. Claude Code researched academic papers, coded a multi symbol strategy from scratch, compiled it, debugged it, backtested it across 4 timeframes and 3 instruments, and came back with validated results. I built the pipeline. It did everything else. Jim Simons built the Medallion Fund, the most successful trading fund in history, by automating systematic research. 66% average annual returns for decades. The key was never any single strategy. It was the pipeline that could find, test, and validate edges faster than anyone else. First time i did this it was on NinjaTrader 8, now i have both an MT5 and NT8 bridge running. It tested across M30, H1, H2, H4 and also across multiple symbols simultaneously: USTEC, XAUUSD, USDJPY. If the edge is real, it should survive all of them. The results: 4/4 timeframes profitable. M30: profit factor 1.33, Sharpe 2.91 H1: profit factor 1.37, Sharpe 2.34 H2: profit factor 1.54, Sharpe 2.07 H4: profit factor 1.38, Sharpe 1.29 This is what 0.1% of the industry is actually doing right now.

Crazy what autonomous AI agents can do right now. Claude Code researched academic papers, coded a multi symbol strategy from scratch, compiled it, debugged it, backtested it across 4 timeframes and 3 instruments, and came back with validated results. I built the pipeline. It did everything else. Jim Simons built the Medallion Fund, the most successful trading fund in history, by automating systematic research. 66% average annual returns for decades. The key was never any single strategy. It was the pipeline that could find, test, and validate edges faster than anyone else. First time i did this it was on NinjaTrader 8, now i have both an MT5 and NT8 bridge running. It tested across M30, H1, H2, H4 and also across multiple symbols simultaneously: USTEC, XAUUSD, USDJPY. If the edge is real, it should survive all of them. The results: 4/4 timeframes profitable. M30: profit factor 1.33, Sharpe 2.91 H1: profit factor 1.37, Sharpe 2.34 H2: profit factor 1.54, Sharpe 2.07 H4: profit factor 1.38, Sharpe 1.29 This is what 0.1% of the industry is actually doing right now.

ZenomTrader

54,747 Aufrufe • vor 5 Monaten

Jim Simons’ fund was trading tens of thousands of strategies. I realized I’d been thinking about this the wrong way the whole time. I was focusing too much on individual strategies instead of on how fast I could test and discard them. I asked Claude Code to autonomously code strategies for me from scratch. It compiled them, debugged them on its own, ran the backtests, and came back with results. I did that over 500 times in 2 months. Most were garbage. Twelve survived. A full hedge fund in a single file. A normal trader tests maybe one idea per week, 50 per year if they’re serious. I do 50 in a day. Jim Simons didn’t win by having the best single strategy. He won because his team could test and discard faster than anyone else. As he put it: “If everyone is trying to solve the same problem, don’t do that.” I don’t need a team of PhDs. Just Claude Code on a laptop. The rest are still watching courses from scam gurus with no verified track record. Probably only 0.1% of the industry is doing this.

Jim Simons’ fund was trading tens of thousands of strategies. I realized I’d been thinking about this the wrong way the whole time. I was focusing too much on individual strategies instead of on how fast I could test and discard them. I asked Claude Code to autonomously code strategies for me from scratch. It compiled them, debugged them on its own, ran the backtests, and came back with results. I did that over 500 times in 2 months. Most were garbage. Twelve survived. A full hedge fund in a single file. A normal trader tests maybe one idea per week, 50 per year if they’re serious. I do 50 in a day. Jim Simons didn’t win by having the best single strategy. He won because his team could test and discard faster than anyone else. As he put it: “If everyone is trying to solve the same problem, don’t do that.” I don’t need a team of PhDs. Just Claude Code on a laptop. The rest are still watching courses from scam gurus with no verified track record. Probably only 0.1% of the industry is doing this.

ZenomTrader

27,722 Aufrufe • vor 3 Monaten

Crazy that Claude can now autonomously code strategies and validate them on TradingView and it’s actually faster than my pipeline. Time to expand to a third platform for our code TradingView is next. 15+ strategies are waiting to be coded. And a full Meta EA TV version is coming. Probably only 0.001% of the industry is doing this. Huge thanks to Andrew and The Daily Profiler for this pipeline idea.

Crazy that Claude can now autonomously code strategies and validate them on TradingView and it’s actually faster than my pipeline. Time to expand to a third platform for our code TradingView is next. 15+ strategies are waiting to be coded. And a full Meta EA TV version is coming. Probably only 0.001% of the industry is doing this. Huge thanks to Andrew and The Daily Profiler for this pipeline idea.

ZenomTrader

98,205 Aufrufe • vor 3 Monaten

The most insane thing i built with AI agents: A full hedge fund in a single file. 7 independent strategies. 2,000 lines of code. 5 symbols. One Expert Advisor. Each strategy has its own trade engine, its own risk parameters, its own magic numbers. They never touch each other. Why one file? Because that's how you control what actually matters: max drawdown across all strategies, overlap prevention so two algos don't stack the same directional bet, and anti-hedging logic for prop firm compliance. Nobody does this. Sharpe ratio above 2. Eight years of data. $100k starting balance. Claude Code launched MetaTrader, configured the parameters, ran the backtest, and switched to the equity curve. I didn't touch anything. Fully autonomous. I shared the exact logic and code structure inside the Discord. This is one of the most ambitious projects i've built so far:not just a strategy, a portfolio engine.

The most insane thing i built with AI agents: A full hedge fund in a single file. 7 independent strategies. 2,000 lines of code. 5 symbols. One Expert Advisor. Each strategy has its own trade engine, its own risk parameters, its own magic numbers. They never touch each other. Why one file? Because that's how you control what actually matters: max drawdown across all strategies, overlap prevention so two algos don't stack the same directional bet, and anti-hedging logic for prop firm compliance. Nobody does this. Sharpe ratio above 2. Eight years of data. $100k starting balance. Claude Code launched MetaTrader, configured the parameters, ran the backtest, and switched to the equity curve. I didn't touch anything. Fully autonomous. I shared the exact logic and code structure inside the Discord. This is one of the most ambitious projects i've built so far:not just a strategy, a portfolio engine.

ZenomTrader

37,856 Aufrufe • vor 4 Monaten

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below

Anatoli Kopadze

16,858 Aufrufe • vor 1 Monat

I asked Claude Fable 5 to reverse engineer a 1993 DOS game with no source code. It read the raw machine code, rewrote the engine in C, and gave me a fully editable port for every platform. 30 min from EXE to iPhone. Sharing it all so you can revive your own childhood games!

I asked Claude Fable 5 to reverse engineer a 1993 DOS game with no source code. It read the raw machine code, rewrote the engine in C, and gave me a fully editable port for every platform. 30 min from EXE to iPhone. Sharing it all so you can revive your own childhood games!

Ammaar Reshi

150,104 Aufrufe • vor 1 Monat

THIS IS THE ENTIRE STRATEGY I WOULD USE IF I WAS LEARNING TO CODE TODAY! Roadmap suggestions and all. This is a LONG video but a detailed one. Drop a like and BOOKMARK IT because you are probably going to want to reference this one later. Tag someone who can benefit from this.

THIS IS THE ENTIRE STRATEGY I WOULD USE IF I WAS LEARNING TO CODE TODAY! Roadmap suggestions and all. This is a LONG video but a detailed one. Drop a like and BOOKMARK IT because you are probably going to want to reference this one later. Tag someone who can benefit from this.

Danny Thompson

90,926 Aufrufe • vor 2 Jahren

Nobody in the history of prop firm trading has built what i built in 6 weeks with autonomous agents. Over 1,000,000 lines of code across 17 projects. Zero lines written manually. Claude Code and Codex did everything. I described what i wanted and the agents coded, compiled, debugged and deployed it while i was sleeping, eating, running, buying an apartment. The full list is insane and i still can't believe it. A trading dashboard that destroys every commercial tool in the industry. Prop firm simulator, hedge detection engine, correlation matrices, multi-portfolio simulation across firms, payout certificates. Built by one person from Romania in his apartment. Two autonomous backtesting bridges. NinjaTrader 8 and MetaTrader 5 running in parallel. They compile, debug, and backtest without me touching a single button. i wake up to new equity curves. A Meta EA with 12 strategies. Gold, Nasdaq, USDJPY, Bitcoin. Mean reversion, trend following, breakout.All running simultaneously in one script. Sharpe 2.17. a full hedge fund in a single file. An AI clone of myself answering support tickets on my premium community 24/7 in my exact voice. Trained on everything i ever said. it speaks every language and never sleeps. Voice control from anywhere in my apartment. Screenshot automation in 0.1ms. A phone bridge so i control my entire infrastructure from my pocket. A tweet engine scoring virality. 5 custom AI tools i designed from scratch. 9,000 in prop firm fees turned into 130,000+ in payouts in the last 6 months. 41% CAGR verified with private investor capital. 74 premium members at 80/month. Show me one person who did more in 6 weeks. I will wait.

Nobody in the history of prop firm trading has built what i built in 6 weeks with autonomous agents. Over 1,000,000 lines of code across 17 projects. Zero lines written manually. Claude Code and Codex did everything. I described what i wanted and the agents coded, compiled, debugged and deployed it while i was sleeping, eating, running, buying an apartment. The full list is insane and i still can't believe it. A trading dashboard that destroys every commercial tool in the industry. Prop firm simulator, hedge detection engine, correlation matrices, multi-portfolio simulation across firms, payout certificates. Built by one person from Romania in his apartment. Two autonomous backtesting bridges. NinjaTrader 8 and MetaTrader 5 running in parallel. They compile, debug, and backtest without me touching a single button. i wake up to new equity curves. A Meta EA with 12 strategies. Gold, Nasdaq, USDJPY, Bitcoin. Mean reversion, trend following, breakout.All running simultaneously in one script. Sharpe 2.17. a full hedge fund in a single file. An AI clone of myself answering support tickets on my premium community 24/7 in my exact voice. Trained on everything i ever said. it speaks every language and never sleeps. Voice control from anywhere in my apartment. Screenshot automation in 0.1ms. A phone bridge so i control my entire infrastructure from my pocket. A tweet engine scoring virality. 5 custom AI tools i designed from scratch. 9,000 in prop firm fees turned into 130,000+ in payouts in the last 6 months. 41% CAGR verified with private investor capital. 74 premium members at 80/month. Show me one person who did more in 6 weeks. I will wait.

ZenomTrader

29,573 Aufrufe • vor 4 Monaten

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Nityesh

41,143 Aufrufe • vor 4 Monaten

This is why you want an execution layer share your tools, auth and approvals across all agents you use Check out me adding the Axiom MCP server, authing to it, and calling it from Claude Code and OpenCode in under a minute - all locally on my computer `npm i -g executor`

This is why you want an execution layer share your tools, auth and approvals across all agents you use Check out me adding the Axiom MCP server, authing to it, and calling it from Claude Code and OpenCode in under a minute - all locally on my computer `npm i -g executor`

Rhys

29,977 Aufrufe • vor 4 Monaten

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

Riley Brown

73,418 Aufrufe • vor 7 Monaten

i needed a *nice-looking* qr code for a recent project and wasn't happy with any of the results i found, so i made an app to do it for me and shipped it. this is qewie - make beautiful qr codes (qews?) with a few taps. save or share them wherever you want. live and free on the app store (link below)

i needed a nice-looking qr code for a recent project and wasn't happy with any of the results i found, so i made an app to do it for me and shipped it. this is qewie - make beautiful qr codes (qews?) with a few taps. save or share them wherever you want. live and free on the app store (link below)

jpa

540,586 Aufrufe • vor 1 Jahr

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Ethan Mollick

162,293 Aufrufe • vor 2 Jahren

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

Diego

12,588 Aufrufe • vor 2 Monaten

Claude Code creator, Boris Cherny: "Going from agents to loops is as big a jump as going from code to agents." 40 minutes of the head of Claude Code showing exactly how he works now. Loops running his code reviews, his maintenance, his fixes, on their own. Watch it, then read the full breakdown of loops below.

Claude Code creator, Boris Cherny: "Going from agents to loops is as big a jump as going from code to agents." 40 minutes of the head of Claude Code showing exactly how he works now. Loops running his code reviews, his maintenance, his fixes, on their own. Watch it, then read the full breakdown of loops below.

Anatoli Kopadze

374,751 Aufrufe • vor 1 Monat

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.

Sudo su

65,570 Aufrufe • vor 4 Monaten

I just ran a full research project without doing any research. Lemma by Analemma did everything: 1. Explore I typed a question. It mapped the entire field. Concepts, references, key papers. Done. 2. Survey I asked for a literature review. It gave me 50+ pages with real citations. Not a summary. A publication-grade draft. 3. Code I described an experiment. It wrote the code, ran it, showed results. 4. FARS I gave it a research direction. It generated hypotheses, planned experiments, ran them, and wrote the full paper. Zero input from me after that. This is the first tool I've used that actually runs research instead of just helping you do it. FARS already ran live and produced 100 papers in 10 days. One every 2 hours. Watch it here: This is what "Vibe Research" looks like.

I just ran a full research project without doing any research. Lemma by Analemma did everything: 1. Explore I typed a question. It mapped the entire field. Concepts, references, key papers. Done. 2. Survey I asked for a literature review. It gave me 50+ pages with real citations. Not a summary. A publication-grade draft. 3. Code I described an experiment. It wrote the code, ran it, showed results. 4. FARS I gave it a research direction. It generated hypotheses, planned experiments, ran them, and wrote the full paper. Zero input from me after that. This is the first tool I've used that actually runs research instead of just helping you do it. FARS already ran live and produced 100 papers in 10 days. One every 2 hours. Watch it here: This is what "Vibe Research" looks like.

Muhammad Ayan

39,960 Aufrufe • vor 1 Monat

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

Kyle Walker

13,669 Aufrufe • vor 16 Tagen