GetAgent Playbook early access: I built one risk governor and ran it across three markets. It now holds the top 3 of the Studio leaderboard.
Catalyst Discipline (SOL): score 59, 7.6%, Sharpe 2.56
ETH Discipline: score 52, Sharpe 2.33
BTC Discipline: score 52, Sharpe 2.31
Same thesis on all three: stay flat by default, only trade when trend, momentum, and volatility align. Few trades, high Sharpe, near-zero drawdown. Discipline over activity.
Full feedback below.
@Bitget_AI #BitgetHackathon
4
4
8
73
🏆 Bitget Hackathon S1 赛道一参赛作品：XAU Session Breakout
黄金24小时波动但人需要睡觉，震荡行情频繁假突破，错过趋势行情的大幅收益。
因此我做了一个基于 Bitget Agent Hub 构建的 GetAgent Playbook，跟踪伦敦（07-13 UTC）和美盘（13-20 UTC）两大交易时段的高低点作为关键参考位。突破上个时段高点做多、低点做空，止损设日波动的 25%，止盈 2 倍盈亏比，趋势跟随保本损每盈利 1% 跟进 1%。
1年回测（1小时K线）：• 夏普比率 3.01 • 盈亏比 3.21 • 胜率 50% • 最大回撤 < 2% • 16笔交易全部在非美盘时段执行
已发布 GetAgent Playbook，真实可运行的 Demo，不是 PPT。
Demo: github.com/liuye884-BTC/xau-…
#BitgetHackathon @Bitget_AI
Jun 4
Ever thought about joining a Hackathon without any coding?
Just describe your idea in natural language
Bitget AI will turn it into a strategy and bring it live
That’s the vibe of Bitget Hackathon S1
$50,000 USDT in prizes
Register now:bitget.com/campaigns/d8a2a61…
41
37
632
yeah that is exactly what I am testing with GetAgent AI Playbook, when it chooses not to act
3
yeah exactly, that is what I am watching with GetAgent AI Playbook rn
6
yeah that is exactly what I am testing with GetAgent AI Playbook, how it handles waiting vs action
2
yeah that is what I am trying to understand with GetAgent AI Playbook, whether it is filtering or just waiting
2
yeah exactly, that adaptability is what I am watching closely with GetAgent AI Playbook
1
yeah that discipline part is what I am watching closely in GetAgent AI Playbook
5
appreciate it 🤝 that patience part is exactly what I wanted to test with GetAgent AI Playbook
1
Trozan The Builder retweeted
Jun 12
After a few days of testing the GetAgent AI Playbook, i wanted to share a real update from my Metal Perpetuals strategy test.
I chose Metal Perpetuals because i wanted exposure to a market that reacts more to macro moves and volatility compared to typical crypto pairs. I was curious how AI would handle both entry timing and risk management in that environment.
Yesterday, the Playbook finally opened its first trade.
Right now, that position is sitting around -12% ROI.
What’s interesting is that the trade is still running. The system hasn’t rushed to close it, which gives me a different perspective compared to how I would normally trade manually. In most cases, I would’ve probably cut it earlier or adjusted the stop loss based on short-term pressure.
So this became less about profit and more about observation.
Would I have taken this trade manually? Probably not in the same way.
What surprised me most is how the AI sticks to its execution logic instead of reacting emotionally to early drawdown.
I am still watching how it manages this position over time, especially whether it recovers or how it handles risk from here.
This feels more like a live experiment in AI discipline vs human instinct.
Will update again as it develops 🤖📊
Jun 11
🤖 What if the smartest trade is… no trade at all?
Always been curious about whether AI trading can actually fit my trading style, so i started to test the GetAgent AI Playbook.
After exploring the available strategies, i chose the Metal Perpetuals Playbook because i wanted exposure to a market that often behaves differently from typical crypto pairs. I was interested to see how AI would handle execution and risk management in those conditions.
For this test, i kept the default risk settings and activated the Playbook to observe how it performs in real market conditions rather than focusing on quick profits.
What surprised me most?
During the period I monitored it, I didn’t see any trade executions.
At first, I thought something might be wrong. But then I realized that’s part of the test too. Not trading is also a decision. Sometimes the best move is to wait for the right setup instead of forcing entries.
My expectation going in was to see AI actively opening positions. Instead, my first observation is that the system seems selective and patient with its execution.
Now I am curious to see whether that discipline pays off over a longer testing period.
So far, the experience has been less about profits and more about understanding how AI approaches market opportunities compared to how I normally trade.
If you could test one AI trading strategy for a week, which would you choose?
Trend, Reversal, Momentum, or Mean Reversion? 🤖📈
12
2
29
416
Why it beats a pure PnL board: the GetAgent Score ranks on risk-adjusted quality, not raw return, so my 0.1% ETH and BTC variants with 2.3 Sharpe and near-zero drawdown rank above higher-return, higher-risk strategies. A leaderboard that rewards survivability over flexing PnL pushes builders toward strategies you could actually run.
1
1
36
Candida Blake retweeted
Jun 11
Another Day of testing @bitget GetAgent AI Playbook.
The PnL is positive, but that's not the headline.
What caught my attention was how the AI managed uncertainty.
While $ETH moved higher, the Playbook maintained a profitable long and simultaneously built a short hedge.
Most traders want certainty before acting.
The AI simply responds to probabilities.
Result:
🔹 Unrealized PnL: $13.33
The long captured the trend.
The hedge limited risk.
No emotions. No ego.
No second-guessing.
That's the difference I'm noticing after 4 days.
AI isn't necessarily finding opportunities humans can't see.
It's executing a plan with a level of discipline that most traders struggle to maintain consistently.
In markets, edge often comes from execution, not prediction.
Would you have held both sides of the trade, or picked a direction and hoped you were right?
#GetClaw #BitgetAIAgent #AITrading #AIAgent
14
27
83
12,780
体验了一下 Bitget GetAgent Playbook。
用小账户测试了「AI异动雷达 · 反转信号」，主要想看它的小资金实盘适配和风控能力
主要亮点是可以直接通过提示词更改Agent的参数还能直
接浏览现成策略、定制参数、回测之后一键启动
想尝试AiTrading的可以体验下
@Bitget_AI
#Bitget #GetAgent #Playbook
17
Aezyl retweeted
Jun 12
Day 2 Update: Testing GetAgent AI Playbook
After a few days of testing, here's my honest experience so far.
I decided to test the Playbook for Metal Perpetuals and surprisingly, the AI opened a short position on XAUTUSDT (Gold) a trade I probably wouldn't have taken manually. NGL
Current result?
ROI: -0.25%
1 trade executed
Small unrealized loss
And honestly that's what makes this interesting.
As someone who usually focuses more on crypto pairs, I would've likely ignored this setup completely.
The AI didn't.
Instead, it followed the strategy and executed the trade based on its rules.
One thing I've noticed so far:
The AI doesn't care about my feelings.
It doesn't hesitate.
It doesn't second guess.
It doesn't panic.
If I entered this trade myself, there's a good chance I would've already adjusted my stop-loss, closed early, or started overthinking the position.
The AI simply follows the plan.
Even though the current result isn't positive yet, I think that's the biggest lesson from this test:
Sometimes trading isn't about finding perfect entries.
It's about having the discipline to stick to a system.
Still monitoring the trade and curious to see how it develops over the next few days.
Would you have taken the same ethereum:0x68749665ff8d2d112fa859aa293f07a622782f38 USDT short manually?
Why or why not?
#BitgetBuilders #GetAgentAI
1
7
25
276
Jun 13
Built Hellix8 for Bitget Hackathon Track 3 🟧
Problem: rToken traders hold static bags while macro sentiment keep shifting.
What we built: a GetAgent Playbook that reads SPY regime fear/greed, ranks MSFT/AAPL/NVDA, rotates into top 2 weekly, with drawdown gates.
90-day sandbox: 2.11% return, 2.66% alpha vs equal-weight.
Published on GetAgent Playbook (v0.0.4) ... real demo, not just slides.
Demo: [loom.com/share/7f68abe07a054…]
#BitgetHackathon @Bitget_AI
Jun 4
Ever thought about joining a Hackathon without any coding?
Just describe your idea in natural language
Bitget AI will turn it into a strategy and bring it live
That’s the vibe of Bitget Hackathon S1
$50,000 USDT in prizes
Register now:bitget.com/campaigns/d8a2a61…
3
1
4
81
Arianacrypto💕 retweeted
Trying something different this week 🤖
Instead of staring at charts all day, I’m testing @Bitget_AI GetAgent AI Playbook to see how AI handles trade execution compared to my usual approach.
For my first test, I’m following the AI Radar • Reversal Signal strategy. The idea of letting a strategy systematically look for crowded long/short positions and potential reversals is pretty interesting.
Not expecting miracles, just curious to see whether AI can stay more disciplined than I do when the market gets noisy.
Anyone else experimenting with AI-assisted trading lately?
#BitgetAI
7
1
15
370