Meridian Engine, by Horizon AI · directional analyses
Direction, levels and invalidation recorded before the move. Outcome checked on public price series.
Meridian Engine, by Horizon AI, analyses market structure and liquidity across timeframes and publishes the The side on which the analysis expects the move: long (up), short (down) or neutral, meaning no directional edge. with The level from which risk and result are measured., stop and The T1 and T2 levels at which the analysis counts the move as complete., timestamped in UTC, before the move. Every outcome stays public in R, losses included.
Get the next analysis View the full record
With the waitlist: one analysis a week by email, with the complete card, in the same format as the public record.
01 — Structure
Structure of an analysis: bias, entry, stop, targets, invalidation, rationale and outcome, recorded before the move
Bias
Long, short or neutral. Neutral means no directional edge and is published with the reference band and the two closes that would invalidate it.
Entry
The level from which risk, targets and result are measured.
Stop
The price that invalidates the analysis. The distance between entry and stop defines The reference unit of risk: the distance between entry and stop. A +1R result equals the stated risk., shown in price on the card.
Targets
T1 and T2, in price and in multiples of R. A T2 at +1.08R means a move slightly larger than the stated risk.
Invalidation
The closing conditions, on the analysis timeframe, that void it before the stop: for example an H1 bar closing above 4,318.9.
Rationale and opposite scenario
The evidence, each item with bar and timestamp, and the strongest opposite scenario the engine assessed and rejected, with the reason.
Outcome
The first event within the horizon (target, stop or invalidation), with MFE: the maximum favourable excursion after entry. MAE: the maximum adverse excursion. Both in R., checked on public price series independent of the engine’s feed.
No field is optional: an analysis without a stop, an invalidation or an issue time is not published. No field changes after issue: every card is recorded with a UTC timestamp and the run ID before the move, and the section 03 record carries its outcome.
02 — Method
Method: structure breaks graded by quality, sweeps measured in ATR, every piece of evidence tied to its bar
- Structure
- Higher or lower highs and lows (HH, HL, LH, LL); structure breaks (Break of structure: a break of a high or low in the direction of the trend. and Change of character: the first break against the trend.) graded by quality: displacement (a break with momentum) or drift (a slow break). A drift break alone is not sufficient for a decision.
- Liquidity
- Clusters of equal highs and lows, where orders concentrate. Sweeps, that is price pushing past those levels, measured in multiples of the average bar range (Average true range: the average range of a bar, a measure of volatility.).
- Zones
- Supply and demand zones, and the price gaps left by momentum bars (Fair value gap: the gap left by a momentum bar, between the high of the previous bar and the low of the next, or the reverse. and Balanced price range: the overlap of two fair value gaps in opposite directions.).
- Context
- Market session, ATR percentile (volatility against its average) and the macro calendar when available. A missing or stale input is stated on the card.
- Decision
- Two agents: one reads the chart structure, the other decides whether there is a trade. Every statement names the bar it comes from: in the BTCUSD reading of 2026-10-01, the H1 sweep of 30/09 at 13:00 UTC, 1.28 times the ATR deep. Without confluence the outcome is “no trade”, with the band and both scenarios.
The full report lists the evidence item by item: the BTCUSD report of 2026-10-01 lists ten, each with timeframe, bar and timestamp, together with the rejected opposite scenario and its reason.
03 — Record
Public record: the outcome of every analysis in R, losses included, under exit rule v1
| Date UTC | Instrument | TF | Bias | Entry | Stop | T1 / T2 | Outcome | Net R | Sample |
|---|---|---|---|---|---|---|---|---|---|
| 2026-10-03 23:31 | XAUUSD | D1 · H4 · H1 | Conditional short | 4,187.44 | 4,231.00 | 4,133.72 / 4,098.04 / 4,018.84 | Open, horizon until 2026-10-30 21:00 UTC | — | out |
| 2026-10-03 22:41 | EURUSD | D1 · H4 · H1 | Short | 1.12522 | 1.13180 | 1.12147 / 1.11450 | Open, horizon until 2026-10-30 21:00 UTC | — | out |
| 2026-10-01 00:25 | BTCUSD | H1 | Neutral | — | — | Band 83,304.1 – 84,443.6 | Upside break of the band, 18:00 UTC H1 close | — | out |
| 2026-09-24 00:28 | XAUUSD | H1 | Short | 4,288.43 | 4,321.00 | 4,273.76 / 4,253.37 | T1 at 02:00 · T2 at 10:00 UTC | +1.07 | in |
| 2026-08-09 00:09 | BTCUSD | H1 | Conditional short | 64,886.5 | 65,017.9 | 64,689.4 | Not activated: invalidated at 02:00 UTC, before the trigger | — | in |
Source: the record of published analyses, with the run ID and issue time of every row. Each outcome is checked on the public price series named on its card.
- R
- The result divided by the initial risk: +1R equals a gain matching the stated risk, −1R a stop reached.
- Exit rule
- Fixed on 2026-09-26, before the analyses it measures, and not changeable afterwards: any change opens a new version. Full text of the rule.
- Sample
- Out of sample: analyses recorded before any event. In sample: analyses published with the outcome known, which stay in sample.
- Costs
- Deducted from every outcome before net R is calculated: $0.30 per trade on gold, $50 on BTC.
Every analysis received by email appears in this table with the same issue time. Get the next analysis
04 — Comparison
Comparison on seven checkable criteria: UTC issue time, cited evidence, published losses, fixed exit rule, public check series
| Meridian Engine | Paid signal channels (typical) | AI analysis tools (typical) | |
|---|---|---|---|
| Direction stated before the move | Yes, with a UTC timestamp | Yes, often without a checkable timestamp | Partly, as scores |
| Rationale with cited evidence | Yes, bar by bar | No | Partly |
| Losses published | Yes, all of them | Rarely, self-reported | Partly, often backtests only |
| Exit rule fixed in advance | Yes, version 1 of 2026-09-26 | No | No |
| Checked on public series | Yes, up to two series | No | No |
| Forex, metals, indices, crypto | All four classes | Yes | Zero to three classes out of four |
| Reader’s decisions | Position size and risk | Often not even these | All |
Source: internal review of 19 operators, updated on 2026-09-19. Every Meridian Engine row can be checked in the section 03 record.
05 — What you get
What you get: a weekly card with bias, entry, stop and invalidation, identical to those in the public record
- Weekly analysis
- One complete card by email every week: bias, entry, stop, T1 and T2 in price and R, invalidation conditions, timeframe, UTC issue time and horizon.
- Outcome
- The outcome of the same analysis once the horizon closes: net R, MFE and MAE, check series.
- Record
- The full record, losses included, always public, under exit rule v1 of 2026-09-26.
- At launch
- Terms announced at launch: subscribers receive all the information they need by email.
Every analysis sent by email enters the section 03 record with the same issue time and run ID: picking analyses after the outcome is ruled out by construction, because the record holds every row, losses included. Each row links to its card and to the public price series used for the check.
The analyses contain no position sizes and come with no urgency messages or return promises: they are the same for everyone, and position size and risk stay with the reader.
Sample analysis: XAUUSD, 2026-09-24, full card and outcome (+1.07R net)
06 — Technical questions
Technical questions: timeframe, price feed, the 1R risk unit, conditional analyses and the exit rule
Which timeframe does the engine use?
Several: the timeframe of each analysis is written on its card, together with the horizon of validity. The first published analyses are on H1; analyses on other timeframes will follow. Horizons and exit rule.
Which feed do the prices come from?
The engine reads the bid of the feed named on the card. The outcome is checked on independent public series, for gold Binance PAXGUSDT and COMEX GC=F, with a stated tolerance. Check series on the gold card.
What is 1R and why is it used?
The distance between entry and stop. Measuring in R makes instruments with different stop sizes comparable. On the gold card 1R equals $32.57. Gold card.
What is a conditional analysis?
An analysis that applies only if a trigger fires, for example an H1 close below a level. Without the trigger the outcome is “not activated, 0R”, and the row stays in the record. BTCUSD, 2026-08-09.
Why “no trade” in some cases?
Without confluence there is no directional edge. The analysis publishes the band and the two closes that would invalidate it, and that outcome also enters the record. BTCUSD, 2026-10-01.
What determines the outcome?
The first event within the horizon: target, stop or a closing invalidation condition. If stop and target fall in the same bar, the stop prevails. Exit rule of 2026-09-26.
Does the analysis say how many lots to open?
No. The analyses are the same for everyone and do not take the reader’s account into account: position size and risk stay with the reader. Scope of the analyses.
Are the analyses personalised?
No. No information on capital, experience or goals is collected, which is why the analyses are not investment advice. Scope of the analyses.
For a question not listed here: contact@usemeridianai.com. The answer is added to this list.
07 — Scope and founders
Scope of the analyses: bias, levels and invalidation published; position sizing and trading decisions with the reader
- Nature
- General market analyses, identical for every reader and published to the public. They do not take the reader’s situation into account and are not investment advice.
- Published content
- Bias, entry, stop, T1 and T2, invalidation conditions, timeframe, UTC issue time and horizon. Never position sizing, never execution on the reader’s behalf.
- Trading decisions
- Actual entry, lot size, exposure and trade management stay with the reader.
- Verifiability
- Every published analysis enters the record with run ID, issue time and exit rule v1 of 2026-09-26; losses stay public alongside gains.
- Risk
- Leveraged trading can lose more than the capital invested; leveraged products carry a high risk of losing money rapidly.
- Conflicts of interest
- The founders trade personally, including instruments that the analyses may cover.
- Publication and corrections
- Analyses produced by Meridian Engine and published by Horizon AI, S.r.l. in formation, Italy. An error in text or data is fixed on the page and logged with its date in the corrections log.
| Founders | Role | Background |
|---|---|---|
| Fabio SalvanLinkedInX | Company direction · CEO | Trades the markets on his own account, with institutional concepts and Smart Money Concepts (SMC); detail on the LinkedIn profile |
| Salvatore ContinoLinkedInX | Technology · CTO | Designed and built Meridian Engine. Stated roles: Cursor Ambassador, Microsoft Insider Developer, startup mentor for Startup Geeks; detail on the LinkedIn profile |
Backgrounds as stated by the founders; the linked profiles give the detail.
Method, horizons and exit rule: methodology.
08 — Waitlist
Waitlist: a weekly card with bias, entry, stop, targets and invalidation, in the same format as the public record
Your personal code arrives by email on sign-up. With the «The weekly reading» box ticked, a complete card arrives every week: bias, entry, stop, T1 and T2 in price and R, invalidation conditions, timeframe and UTC issue time. Once the horizon closes, the recorded outcome of the same analysis follows, in net R, checked on public price series.
The same card enters the section 03 record with the same timestamp. Terms and use of the code are announced at launch. Unsubscribing takes one click.
The analyses are the same for everyone and do not consider the capital, experience or goals of whoever receives them: position size and risk stay with the reader. Contact: contact@usemeridianai.com.
Form not showing? Open it in a new window.
The form is run by Tally (Belgium, EU); data is stored in Europe. Privacy notice.