02 · ACTIVE TRADERAn active trader who wants to improve
Turn the way you work into a process you can test and improve
You already open and manage trades, use charts or analysis tools, and make your own decisions. Maybe you're not profitable yet, maybe your results are inconsistent, and maybe you're doing well and want to improve performance and save time.
Reactor is a trading operating system that brings together market data, AI and your trading accounts. It lets you research ideas, test decisions, execute and manage trades — and go back to the results to understand what's worth improving.
You can start wherever you need help: use the chat for analysis, set up an Agent with a specific role, or connect several Agents into a workflow. Your instructions decide the way of analyzing, the room for judgment and the authority to execute.
The examples below show a few ways to use the system.
01
EXAMPLE 1
"I have an idea for a trade. I want to check what I'm missing."
You can ask Reactor to test the idea against market data: trend across several timeframes, momentum, volatility and other information available for that market.
You can set the approach you care about — for example, look for confirmation of a breakout, or check whether the entry is too late. You can also compare the analysis of several models on the same opportunity.
Your idea
→
Market data
→
Act · wait · avoid
WHAT YOU'LL SEE
A trade idea, the data that was gathered, and an analysis that lays out the reasons to act, wait or stay out.
Questions that may come up
Does the system just confirm what I already think?
You can instruct it to look for weaknesses, evidence against the idea, and conditions where it's better not to act.
What happens when information is missing?
We'll look at what was received, what's missing, and how that affects the conclusion. Missing information should stay visible in the analysis.
What does comparing models give me?
It shows differences in the analysis and the decision. To know which approach is more useful, you need to track its results.
✓ HOW WILL I KNOW I GOT IT?
You can identify which information strengthened or weakened the idea, and what would make you change the decision.
02
EXAMPLE 2
"I spend a lot of time searching before I even get to the analysis."
You can describe what you're looking for and use Reactor to scan the market. For example: assets that fell within a certain range, a defined price pattern, or a combination of conditions.
The results become a list you can keep analyzing. When the search fits your need, you can save the instructions and run them again, or pass the results to another Agent.
Your conditions
→
Market scan
→
Candidate list
→
Further analysis
WHAT YOU'LL SEE
A scan based on your idea, how many assets were checked, the ones that matched, and a follow-up analysis of one candidate.
Questions that may come up
Is every result a trade worth taking?
A result means the asset met the search conditions. You can add an analysis and decision step before buying.
How do I know what was actually scanned?
We'll show the market that was checked, the timeframe, the scope of the check and any missing data.
Can I make the search permanent?
You can save the instructions and set up an Agent to run the task at the times you choose.
✓ HOW WILL I KNOW I GOT IT?
You can separate the conditions that put an asset on the candidate list from the conditions that justify entering a trade.
03
EXAMPLE 3
"I spot opportunities, but I don't know if they really work over a series of trades."
Reactor lets you break the research into stages. You start by defining the opportunity and collecting its occurrences. With the candle tools you can replay price movement after each occurrence and check how far it moved in the trade's favor, how far against it, and how long it took.
That way you can research the opportunity before adding an Agent that picks which trades to take. Later you test the quality of the decisions and the trade management separately.
In a real example, we scanned for a Bullish Engulfing pattern every four hours. We researched the movement after the signals and, based on the findings, chose a 3% stop-loss and a 4.5% profit target. Then we ran a Buyer that buys the signals.
As of preparing this example, by the measurement provided, 800 trades closed with a 65% win rate. In this case the Buyer doesn't filter with judgment; that lets us collect results before testing an extra decision layer.
4h
Bullish Engulfing scan every four hours
3%
Stop-loss target
4.5%
Profit target
800
Closed trades
65%
Win rate
As of preparing this example, by the measurement provided.
WHAT YOU'LL SEE
The signals that were collected, a replay of the movement after them, and how the findings led to choosing the targets.
Questions that may come up
How does this research help beyond an overall result?
It lets you check where the opportunity works, where it weakens, and which part of the process affects the result.
Can I also check opportunities we didn't buy?
You can research the movement after collected signals, including cases you decided to skip, depending on the data available.
Is success in research enough to go live?
You also need to look at costs, actual execution and behavior in other periods. You keep measuring after going live.
✓ HOW WILL I KNOW I GOT IT?
You can define what you want to test in your idea, and which data would let you evaluate it.
04
EXAMPLE 4
"I have good trades, but I don't know what really works and what hurts the result."
You can start from the trade report and look at the overall picture: profit and loss, win rate, average win versus average loss, and how trades were closed.
When there's also a record of the signals and the Agent runs, you can connect the opportunity, the decision, the entry and the management. The candle tool lets you check what happened to price afterwards.
That way you can test questions like: was the entry late? Was the target too far relative to the move? Was profit taken too early? Did the filter skip good opportunities?
Opportunity
→
Decision
→
Entry
→
Management
WHAT YOU'LL SEE
A cumulative result, one winning trade and one losing trade, and then a check of one specific part of the process.
Questions that may come up
Does a high win rate mean the method is good?
You also need to look at the size of wins and losses and at costs. Win rate alone doesn't explain the money result.
Can I tell why a trade lost?
You can check the data and the decisions and form explanations to test on more cases. One trade isn't enough to decide what to change.
Can I compare versions of the method?
You can build a comparison, while separating a change in the instructions from a change in trade size, leverage or market conditions.
✓ HOW WILL I KNOW I GOT IT?
You can point to one change worth testing, and explain which findings support testing it.
05
EXAMPLE 5
"I want the system to analyze my way, even when I'm not available."
An Agent can get a role, gather data and apply judgment according to your instructions. You can define what matters in the analysis, how to weigh conflicting information, and when to wait or stay out of a trade.
You can start from a ready-made prompt example and adapt it to your approach. Then you run it, review its decisions and improve the instructions.
The level of independence is chosen separately: the Agent can present an analysis, make a decision that waits for approval, or go on to automatic execution within defined limits.
Analysis only
Decision waiting for approval
Automatic execution within limits
WHAT YOU'LL SEE
An Agent's instructions, a case where it decided to act, and a case where it decided to wait or skip.
Questions that may come up
Do I have to turn every decision into a hard rule?
You can define principles, priorities and limits, and leave the Agent room for analysis and judgment.
How do I know if the instructions are good?
Check how the Agent interpreted them, which decisions it made, and what the results were over a series of cases.
Does one Agent have to do everything?
You can separate detection, the buy decision, risk management and reporting, and give each role its own instructions and permissions.
✓ HOW WILL I KNOW I GOT IT?
You can explain what judgment you're handing to the Agent, and which limits or decisions stay with you.
06
EXAMPLE 6
"I want to connect my decision to its execution and management."
Reactor lets you turn a plan into trading orders. You can set the entry, allocation, protection and profit targets, and also build a staged entry or several linked orders.
After entry, you can give a management Agent a separate task: check the position, keep the protection in place, take partial profit, or consider an exit when conditions change.
Trade plan
→
Order preview
→
Execution
→
Management Agent
WHAT YOU'LL SEE
A trade plan, a preview of the orders, and an Agent that handles the position after execution.
Questions that may come up
Can I check the orders before they're sent?
We'll show the preview in the relevant execution path, including quantities, prices and protections.
Can trade management include judgment?
Yes. The instructions can combine defined rules with analysis of market conditions, according to the authority given to the Agent.
How do I know what was executed and why?
You can go through the runs, the tool results and the actions, and check the actual state of the account.
✓ HOW WILL I KNOW I GOT IT?
You can connect the trade plan, the orders that were sent, and the authority given to the management Agent.
07
EXAMPLE 7
"I want search, analysis, execution and tracking to work together."
You can connect several Agents so the output of one feeds the next: a scanner finds candidates, a decision Agent reviews them, an execution step handles orders, and management and reporting Agents keep tracking.
You can also bring in signals from other systems. The process can run at set times or in response to an event, with the level of involvement you chose.
Scanner
→
Decision Agent
→
Execution
→
Management & reporting
WHAT YOU'LL SEE
One opportunity moving through the process, including the points where it can stop, ask for approval or continue.
Questions that may come up
Do I have to start with a full process?
You can start with a single task and expand once you've checked its behavior and results.
How do you test a process with several Agents?
Check each role separately, and the hand-off of information between them. You can review the data, failures, run durations and usage cost.
Can I bring in the tools I already use?
Reactor supports connections and external signals. We'll look at the right connection for your tools and process.
✓ HOW WILL I KNOW I GOT IT?
You can identify which part of your work is worth connecting first, what it will pass to the next step, and how you'll test whether it helps.
SEE IT LIVE
Want to go through these examples with us?
In a live demo we'll open the system and walk through the examples that fit you, at your pace.
ANOTHER TYPE?
Not quite you?
Go back and pick the description closest to where you are today.
