Pinned Tweet
Every crypto trading bot I've used had the same flaw:
it couldn't tell me why.
Entry at $67,240. Exit at $66,100. A red number. No explanation.
So I'm building the opposite — a bot where an LLM (Claude, DeepSeek, Gemini) makes every call and writes out its full reasoning before risking a cent.
It's running live in paper-trading mode right now.
Every week I'll post the numbers here. Wins, losses, and what the AI was thinking. No cherry-picking.
Follow along.
Ever thought how cool it would be if Claude could trade for you?
That's exactly why I built KAI Terminal.
You pick Claude or any of the other built-in models and tell it how you trade: what you enter on, where your stop goes, how much you risk. From there it watches the market around the clock, takes the setups that match your rules, manages open positions and writes down why it made every move.
You set the limits it can't cross, and you decide whether trades go out automatically or wait for your approval.
No API keys to connect, the models are built in. Start on paper money, then connect your exchange when you're ready.
Setting up a trading strategy for an AI model used to mean staring at an empty prompt and a wall of settings.
In KAI Terminal it's one button. The setup assistant generates a first version of your settings in a few seconds, and from there you just chat with it.
"Tighter stops." "Only trade BTC and ETH." "Skip weekends." "Don't enter against the 4h trend." It adjusts as you talk.
The first version is only a starting point. The strategy becomes yours in the conversation, one tweak at a time, on whichever model you picked: Claude, Gemini, DeepSeek or MiniMax.
Still looking for beta testers. If setup is what stopped you before, it's one click now.
kailabs.cc
We're looking for people to test KAI Terminal, and you don't need to know anything about crypto to help.
My favorite feature right now is Chart Lab. You open a chart and just ask the model about it. It answers in text and draws on the chart itself: support and resistance levels, channels, patterns. If it sees a setup, it lays out a trade card with entry, stop and targets. You can drag the lines where you want them, and nothing is placed until you confirm.
You pick the model from the ones built in: Claude, Gemini, DeepSeek or MiniMax.
If you trade, run your own strategy on paper money and try to break it. If you've never touched crypto, that's useful too. Click around for ten minutes and tell me what felt confusing, slow or ugly. Fresh eyes catch things I stopped noticing months ago.
Signing up is free, no card and no exchange account needed. Anyone who sticks around and gives real feedback gets a paid plan from me for free.
Reply here or DM me with whatever you find.
kailabs.cc
looking for a few people to help me test kai terminal properly.
if you trade crypto and want to run your own strategy through a model (claude, deepseek, gemini or minimax), i'll give you a paid plan for free while we test.
that unlocks what the free plan doesn't have: auto-execution inside limits you set, a post-mortem on every closed trade, and enough credits to actually run the bigger models.
what i'm asking back: use it for real over the next few weeks, write your own strategy, and tell me what's broken, confusing or missing.
10 spots
sign up at kailabs.cc with the email you want upgraded, then reply or dm me and i'll switch your plan on.
if you've tried the beta, you probably noticed the strategy prompt is empty.
that's on purpose.
kai doesn't ship a default strategy. you can't even activate one until you've written your own entry rules. if i had a strategy that reliably worked, i'd be running a fund, not building a tool.
the terminal handles the heavy part: market data, execution, stops, a review of every open position each candle, a post-mortem after every close. what to trade and why stays yours.
not sure what to write? reply with the setup you trade by hand and i'll help you turn it into a prompt.
kai terminal is in beta.
for the past few months it was just me building this in public. now you can actually use it.
you pick a model (claude, deepseek, gemini or minimax), write your own strategy, set your own risk limits, and it runs on its own. every trade comes with a written thesis you can read and argue with.
three ways to run it: built-in paper money, your exchange's demo account, or your real account. you only give it trade-only keys, so your funds never leave your exchange.
it's rough in places and i'm fixing things daily. if something breaks or feels off, tell me. that's what a beta is for.
kailabs.cc
serious question for anyone who's automated their trading: can you actually leave it alone? like properly walk away for two weeks without opening the app.
weird thing about stepping away for two weeks: the terminal kept running the whole time.
my strategy, the model i picked, the risk limits i set, all of it just doing its thing at 3am while i was fixing other parts of the product and not looking at a single chart.
came back and read the journals like someone else's trading log. some entries i'd defend, some i'd argue with. but every single one had a written reason i could actually check.
that's the bit i keep coming back to. i don't have to trust it. i can read exactly what it thought and decide for myself.
KAI retweeted
🚨 THE STOCK MARKET MADE A NEW ATH
Kalshi traders forecast a 73% chance the S&P500 will trade at 8,000 or above this year.
What is your prediction?
🤝 Paid partnership
been quiet for two weeks. not because the thing died, because i was heads down building instead of posting about building.
turns out you can't do both well when it's just you. every hour i spend writing a post is an hour the actual product doesn't move. so i picked the product for a while.
back now. the terminal is in better shape than it was when i went quiet
nobody asked but i'm quietly proud of this: kai is one kotlin codebase that compiles to the backend, the desktop app, and the browser terminal at once.
same language running the trading engine, the background workers, and the ui you click. the whole thing ships as a single file.
everyone told me not to do the web target in kotlin. it broke the build three separate times in ways that only showed up in production and nowhere in testing. kept it anyway.
solo dev tax: every weird stack decision is yours to defend at 2am.










