The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Your trading bot isn't losing money because the strategy is bad. Here is the real reason.
I see the same post in trading forums every week: "My bot works in backtest, but it bleeds money live."
The developer assumes the strategy is wrong. They tweak the RSI. They add a moving average. It bleeds again.
The real problem is almost never the strategy. It is that the bot is trading on headlines that were never about oil in the first place—or it is trading on stale news because it fired on the first tweet it saw instead of the newest one.
When I built my autonomous oil trading system, I did not trust a keyword matcher to decide when real money moved. I put a reasoning model in front of every headline. It returns four things before a trade is allowed to fire:
Is this actually about oil? (Most aren't. They get filtered.)
Impact: BULLISH / BEARISH / NEUTRAL
Strength: 1–5, where 5 is "war, embargo, major supply shock"
Confidence: 0.0–1.0
A trade only executes if confidence passes a hard threshold. And if the reasoning API ever fails, a circuit breaker falls back to a deterministic engine—the system gets dumber for one cycle, it does not go dark.
The monitor polls every 20 seconds and primes on the first poll. It records the baseline tweet ID and does not trade on old news. That single design choice killed more false signals than any strategy tweak ever did.
This is not a script. It is a pipeline that reads the world, reasons through the noise, and executes with precision. All for $0 to run.
If your bot is bleeding in live markets and you cannot find the root cause, that is the exact problem I solve. I read the architecture, I find where the signal is leaking, and I ship a fix.
If you are stuck on an execution or signal problem, my inbox is open. Tell me the symptom, and I will tell you if it is fixable.
🔗 Full architecture: github.com/S-7-D-2023/OIL-NEWS-SYSTEM
#AITrading #Python #LLM #BuildInPublic #QuantDev
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
The fix for an agent that keeps getting your design system wrong isn't a better prompt.
It's putting the rules where the agent reads them.
In the repo. In skills. In checks it can run itself.
Writing a course about exactly this.
What sells it for me is the refusal telling the agent exactly where the token should go. A bare "no hex" error usually just sends it looping. Does guard.mjs run only as an agent hook, or in pre-commit too so it catches humans as well?
End-to-end retail analytics pipeline that turns raw, messy CSV exports into business decisions, built in Python and SQL and runnable with one command.
What it does:
Cleans and validates 6 relational tables, fixes 585 data-quality issues and logs every action
Loads a SQLite warehouse with keys, constraints and window-function SQL
Customer analytics: RFM segmentation, cohort retention, CAC / LTV by channel, product Pareto, market-basket analysis
Churn prediction model validated on future data (ROC-AUC 0.71, no data leakage)
6-month revenue forecast, best of 3 models by backtest (4.2% MAPE)
Auto-generated Excel report (live formulas, native charts) and an interactive Streamlit dashboard
18 automated tests
An AI customer support chatbot for a fictional Nigerian food delivery business, Lagos Fresh Kitchen. It runs on n8n Cloud and uses Claude Haiku 5.5 as the AI model. The workflow is three nodes: a chat trigger receives the customer’s message, an AI Agent processes it, and the Anthropic Chat Model writes the answer.
How it behaves
The AI Agent has a system message that sets the rules. It must answer only from the business information, never invent prices, areas, hours or policies, and use a fixed fallback line when the answer isn’t there: “I don’t have enough information to answer that accurately. Please contact our support team.”
The business information it knows
Open Monday to Saturday, 9 AM to 8 PM, closed Sundays
Delivers to Lagos Mainland (Ikeja, Yaba, Surulere, Maryland, Ojota, Gbagada) and Island areas (Victoria Island, Ikoyi, Lekki), not outside Lagos
Delivery takes 30 to 60 minutes, with fees from ₦1,000
Menu of jollof rice, fried rice, rice and stew, pounded yam with egusi, grilled chicken, suya and soft drinks
Payments by card, transfer and cash on delivery
Cancellation allowed before cooking starts
No Sunday orders or Sunday delivery, and no event catering
Refunds, complaints and order status go to support
good work