Noetfield Runway · Stock & Crypto

A trading system that will not trade

It reads the market, writes a falsifiable plan, checks that plan with arithmetic the model never touches, and hands it to a person. There is no order path in it to abuse.

Last cycle

decisions produced

Approved

0

Watchlist

0

Cycles recorded

9

Total spend

$0.0391

Mode

RESEARCH_ONLY

Next brief

Sun 07:00 PDT

Live — what the agent last did

LTCUSDT LONG · Trend Continuation REJECTED

Entry

45.66

Stop

45.5

Target

46

R : R

2.13

Score

78

Conf.

70%

Max size

312.50

LTCUSDT is in an uptrend (trend=UP) with price above both EMA20 and EMA50, RSI neutral but above 50, suggesting momentum is bullish. A long entry at current close with stop below recent support (EMA50) offers a favorable risk-reward ratio above the minimum 2:1, targeting a move to a round number resistance.

Invalidated if: Price closes below EMA50 (45.50) on 1h candle; RSI drops below 40; Trend indicator flips to DOWN

EXPOSURE_LIMIT

Cycle gha-31262411554-1-ai-trader — DECISIONS_PRODUCED, finished 12 h ago at Aug 8, 2026, 07:40 PDT. Screened 12, analysed 3, spent $0.0069 (estimated). Value class: risk_reduction.

Today’s scan — every symbol considered

SymbolScoreReadWhy
ATOMUSDT 49 LONG Base and higher timeframe both up. MACD histogram agrees with the trend direction.
POLUSDT 45 LONG Base and higher timeframe both up. MACD histogram agrees with the trend direction.
LTCUSDT 44 LONG Base and higher timeframe both up. MACD histogram agrees with the trend direction.
SOLUSDT 37 LONG Base and higher timeframe both up. MACD histogram agrees with the trend direction.
XRPUSDT 36 SHORT Base and higher timeframe both down. Volume is 1.02x its 20-bar average.
BNBUSDT 33 NO_DIRECTIONAL_EDGE Base and higher timeframe both up. MACD histogram agrees with the trend direction.
AVAXUSDT 30 NO_DIRECTIONAL_EDGE MACD histogram agrees with the trend direction. Volume is 1.54x its 20-bar average.
DOTUSDT 29 NO_DIRECTIONAL_EDGE -0.97% over the momentum lookback. Volume is 1.42x its 20-bar average.
ETHUSDT 27 THIN_VOLUME Base and higher timeframe both up. MACD histogram agrees with the trend direction.
ADAUSDT 24 THIN_VOLUME Base and higher timeframe both up. Volume is 0.68x its 20-bar average — no confirmation.
LINKUSDT 16 THIN_VOLUME Base and higher timeframe both up. MACD histogram agrees with the trend direction.
BTCUSDT 15 THIN_VOLUME Base and higher timeframe both up. Volume is 0.77x its 20-bar average — no confirmation.

Scored in plain arithmetic before any model is called, so this part costs nothing and exists for every cycle. Only symbols with a directional read are worth paying to analyse.

How a cycle runs

01Scanplain code

Recent candles for a short watchlist, from a public read-only feed that has no trading surface on it.

02Screenplain code

Trend, momentum, volatility and volume computed in ordinary arithmetic. Anything stale, thin or too volatile is dropped here, for free.

03Analyse

Only the survivors reach a model, routed cheapest-first through the shared dispatcher. It returns a thesis with levels, invalidation conditions, the evidence each claim rests on, and what data it lacked. This is the only paid step.

04Riskplain code

A pure function returns approved, watchlist or rejected. The model has no vote and cannot size a position.

05Receiptplain code

Written for every cycle including the empty ones, with what it spent and what class of value it produced.

Approved does not mean take this trade. It means every machine check passed and a person should now look.

What the risk gate refuses

ConditionWhy it stops thereCode
Data older than the freshness limitA plan built on a stale bar is a plan for a market that has moved.STALE_DATA
Stop on the wrong side of entryAbsolute distances hide an inverted plan — it reports a healthy ratio while being structurally backwards.LONG_STOP_NOT_BELOW_ENTRY
Reward-to-risk below the floorA thesis that needs to be right most of the time is not an edge.LOW_REWARD_RISK
Position would breach exposureTight stops buy large notionals; the cap binds regardless of conviction.EXPOSURE_LIMIT
Daily loss or drawdown reachedThe system stops for the session rather than trading its way back.DAILY_LOSS_LIMIT
Position cannot be sizedNo stop distance means no risk unit, so there is nothing to size against.INVALID_SIZE
Anything other than research modeFixed in code, not configuration. Approval is unreachable under any other mode.MODE_NOT_ALLOWED

Boundaries

No order placement, no wallet connection, no exchange credential exists anywhere in this service. Market data comes from a public read-only host. The research-only mode is fixed in code rather than configuration, so changing it takes a code change and a review.

No fallback ever invents a trade. When the budget runs out, a provider declines, or fixtures are in use, the answer is no setup with the reason attached — never a fabricated entry, stop and target. A made-up plan is indistinguishable downstream from a real one.

It owns no model provider, no API key and no pricing table of its own. Routing, caching, budget and cost evidence all come from the shared dispatcher.

This agent has never run against a live provider. The wiring is verified end to end including its failure paths; its judgement is not. Nothing here is financial advice.