How the NextScalp AI Co-Pilot Works (/ai, /review and RR @ market)

Most "AI trading" tools point a language model at a chart and let it narrate. NextScalp does the opposite. The automated alert stream is 100% deterministic - real price action, measured levels, real volume, no model in the live path. The AI co-pilot is a separate, on-demand layer you summon yourself when you want a second opinion on a specific pair. This guide explains exactly what that co-pilot does: the /ai analysis, the /review chart-vision read, and the one-tap 📐 RR @ market button - and, just as importantly, the guardrails that stop it from lying to you.

Why the AI is on-demand, never automatic

The hard line in NextScalp is simple: a deterministic alert carries only facts, and an LLM does not produce facts - it produces interpretation. So the model is never wired into the automated delivery path. It runs only when you ask for it: when you type /ai, upload a chart to /review, or tap one of the inline analysis buttons on a signal. Nothing the model says is broadcast to anyone else, and nothing it says can fire an alert.

That separation is the whole point. The screener tells you what is happening with math you can verify. The co-pilot helps you decide whether to act - a structured opinion, clearly labelled as an opinion, summoned on demand.

Every AI answer is grounded against the live book

A model left to free-associate will happily invent a clean-looking entry that does not exist. NextScalp closes that gap by grounding every response against live market data and validating it server-side before it reaches you.

Concretely: each price, level and stop the model proposes is checked against the actual order book within a timeframe-appropriate tolerance - tighter on fast timeframes, looser on slow ones, because a number that is "close enough" on the 4h is nonsense on the 1m. And any setup that contradicts a kill-scenario the deterministic engine has already flagged is rejected outright or stripped of its trade plan before you ever see it. The model does not get the last word; the live book does.

You ask, the bot grounds the model on a live order-book snapshot and validates every number against the real book and the engine's kill-scenarios. A clean setup returns as a labelled second opinion; a setup that fails the check comes back as an explicit no-trade or has its plan stripped - never an invented entry.

The three ways you summon it

`/ai` - on-demand symbol analysis

/ai <TICKER> [TF] runs a full scalp-oriented breakdown of a pair on a timeframe you choose (1m / 5m / 15m / 1h / 4h): the reasoning steps, setup quality, confidence, direction, and concrete Entry / SL / TP1 / TP2 - or an explicit "no trade" with the reason when nothing is there. The 1m read is the pre-entry special case: RSI and ATR are deliberately suppressed because they are noise-dominated on that timeframe, while higher-timeframe context flows in from prior analyses of the same symbol so the 1m read stays anchored to the bigger picture.

Two conveniences make it cheap to lean on:

One-tap analysis on every signal. Each delivered alert carries inline 5m / 15m / 1h buttons that run the analysis straight from the message - no retyping the ticker.
Multi-timeframe revision. Re-run on another timeframe and the bot accumulates the prior-TF summaries for that symbol and feeds them in as context, so the new read is not blind to what you have already seen. Repeat analysis of the same symbol is free and does not cost quota.

The exact syntax, default timeframe and per-run token cost live in the /ai command reference.

`/review` - chart vision on your own screenshot

/review <TICKER> [TF] is the same engine pointed at an image. You upload your own chart screenshot on any supported timeframe (1m / 5m / 15m / 1h / 4h); Claude reads the picture, combines it with live data, and returns the same structured analysis. It is the bridge between the chart you are already staring at and NextScalp's live book - useful when you have drawn your own levels and want a grounded second read on them. The /review command reference covers how to attach the screenshot and which timeframes it accepts.

📐 RR @ market - "can I still take this?"

The most-used button in the product answers the question every scalper asks when they open the bot 30 seconds (or 3 minutes) after the ping: is this setup still tradeable, or is it dead? Every signal that ships a Trade Plan carries a 📐 RR @ market button - one tap, about a second, and a popup tells you:

Current price versus the planned entry (and whether the entry has already been touched).
The live reward-to-risk achievable right now at market, versus the original planned R:R.
For a setup that already resolved: the final verdict - TP1 hit, SL hit, trailed to break-even, or expired.
Time elapsed since the alert.

The alert planned a 3:1 setup from the entry. By the time you tap, live price has run toward the target: the reward left shrank and the risk to the unchanged stop grew, so the honest RR @ market is closer to 1.6 - chasing is no longer the same trade.

It is deliberately on-demand, not live-updating: each tap is a fresh snapshot, with no message edits, no Telegram flood and no visual noise in the chat. It also pairs naturally with reward-to-risk discipline - the button is just R:R recomputed at the live price instead of at the planned entry.

What it deliberately does not do

Honest framing means being clear about the limits, too:

It is a second opinion, not a verdict. Every AI output is labelled as interpretation. It does not override the deterministic gate, and it cannot promote a setup the engine killed.
It will tell you "no trade." When the grounded read does not find a setup, it says so with the reason rather than manufacturing an entry to look useful. A blank is information.
It never updates silently. /ai, /review and RR @ market all run only when you trigger them. There is no background model quietly changing its mind in your chat.
It degrades gracefully instead of refusing. Each reply shows which model answered and how much quota remains; when the premium budget runs low the bot steps down to a faster model rather than blocking - you always get an answer.

How it fits the rest of NextScalp

The co-pilot sits on top of the deterministic machinery, not instead of it. The alert you are analysing already passed the scoring gate - scored against higher-timeframe alignment and volume - and only carried a Trade Plan if the geometry was actually tradeable. The AI layer then lets you interrogate that specific setup: read it on three timeframes, point it at your own screenshot, or check whether the R:R still stands at the current price. For a deterministic pre-entry view of the same symbol - levels, walls and value area with no model involved - the Focus dashboard is the companion tool.

/ai and /review are Premium commands, and the RR @ market button is Premium by virtue of how alerts are built - Free users still see the full alert text, just without the inline buttons. All of it is available during the 7-day free trial.

The discipline is the same one that runs through the whole product: the screener never lies about what is happening, and the co-pilot never pretends its interpretation is a fact. Together they let you watch the whole market and still make the final call yourself - with a grounded second opinion one tap away.

Want a grounded AI second opinion on every signal, plus 16 other deterministic alerts screened for you in real time? Try NextScalp free for 7 days.