Monkey Science / Rich Mitchell

AI with
a pulse.

AI creator and consultant. Building useful systems, content and strategy for brands and businesses that want the new tools without losing the human story.

↓

AI creator / consultant
Technologist since the early web

01 / Stance

Not self-driving.
Needs a driver.

Think Formula 1. You have the whole team behind the car — engineers, strategy, telemetry — but you still need a skilled driver to get the most out of it.

AI is that machine and pit wall. Monkey Science is the operator in the seat: judgment, taste and accountability working with the AI crew so brands and businesses get speed without handing the steering wheel to a system that is not ready to race alone.

Formula 1 car with pit crew and telemetry — AI as the team, you as the driver

Driver over autopilot

02 / About

Creator.
Consultant.

Monkey Science is Rich Mitchell — an AI creator and consultant helping people and businesses put artificial intelligence to work in the real world.

Not theory theatre. Practical builds, clear thinking, and the judgment that comes from decades of adopting new technology early — from the first professional SEO practices, through pioneering digital production practices and technique, to today’s AI tools.

More efficiency. More productivity. More creativity.
Early+ adopter across
web · film · AI

Hyperlink · Virgin Media · digital production · AI

Case studies

Trading Intelligence

03 / UltraScalp

UltraScalp

Built to trade.

UltraScalp annotated short-timeframe chart with entry, target, stop and news callouts
Annotated chart · clear pickLIVE TRADES

Live trades · day / retail

Short timeframe.
Your call.

UltraScalp is a Monkey Science system built to make trades — and to assist making them — for day and retail short-timeframe trading.

Its knowledge graph, symbol bibles, and self-learning loop dig into history and live UltraScalp data — including order book and depth of market (DoM) where timing needs more than a candle. Pattern recognition, news-aware AI, and evolving playbooks (such as the 15-minute Playbook) surface clear picks, so you can enter, manage, and exit with clearer evidence.

RoleAI creator / systems thinking StanceLive trades & assistance FocusDay / retail · short timeframe EngineKnowledge graph · self-learning
Ask about this work The core loop Full-page core loop

Purpose-built for live trades

UltraScalp · Core loop

The core is DATA. Theories. Execute. Adapt.

Dangerous for data
Guarded for live
Intelligence stays local
Demo only · live capital blocked
Engineering spine → data→ RunPack→ decision trace→ MFE / MAE→ construction audit→ stress gate→ promotion
THE CORE DATA protect integrity THEORIES from data only EXECUTE guarded · paper first ADAPT writes new data INGEST normalise · isolate RunPack · traces · KG cBot · paper MFE/MAE · gate · promote DOM · news

UltraScalp is an explainable, evidence-driven system for short-lived opportunities. Data is not an input. Data is the product. Theories are assembled from it. Execution is allowed only after cost, sizing, and invalidation survive a gate. Adaptation does not mutate live logic — it writes new data.

Do not ask: was the signal right?
Ask: was the trade constructible after cost, sizing, timing, and invalidation?
01   AI is never an untracked oracle. Analyst proposes. Gates promote.
02   Deterministic code owns risk and order permission. LLMs cannot override a hard gate.
03   No strategy passes on gross P&L. After-cost or it does not exist.
04   Fail closed. Missing data reduces authority. It never manufactures confidence.
05   Learn offline. Reviewed proposal — never an automatic live mutation.
01 · The core

DATA

Ingest, normalise, isolate. Two lanes stay labelled. Dirty data never enters a primary verdict.

  • Databento DBN/CSV — DOM, MBP-10, orderflow, replay
  • cTrader journals, trade logs, Open API context
  • News / calendar feeds v3
  • Candles, indicators, symbol relationships
  • Capture bus → incoming → RunPack archive
  • Metals / non-normalised trades isolated
02 · From data only

THEORIES

A theory is a RunPack plus an experiment id. Never inferred after the fact. Never promoted by the model that proposed it.

  • RunPack: features · decisions · ai_traces · trades · verdict
  • Deterministic spine + AI selector / veto / chooser
  • Sequence AI Labeler V3.1 · Orderflow V3
  • Edge Probe · Signal Diagnostic · Timebox Scalp
  • Research Workbench · Evidence Board · Knowledge Graph
  • Clear picks ranked by evidence, not vibes
03 · Guarded

EXECUTE

Paper first. Broker adapters only. Intelligence stays local. Live capital is blocked.

  • Cost preflight before any size
  • Risk-normalised sizing · symbol risk caps
  • Armed entry: Market / Pullback / Confirm — or expire
  • Fail-fast: adverse-first · no-follow · giveback
  • cBot · paper executor · broker router
  • AI veto / exec shadow-first · live adjust = false
04 · Writes new data

ADAPT

Measure the path, not the story. Survivors promote. Failures become labels. That is why data stays the core.

  • MFE / MAE · endpoint · SL/TP sim · cost model
  • Construction audit — early? cost-positive? sized? MFE first?
  • Stress gate: OOS · placebo · after-cost · stability
  • Promotion ladder → next logic profile
  • Evidence Board: dominant failure + next experiment
  • Promote / reject overnight into the graph

Lane A · Futures / Databento

DBN / MBP-10 → ingest → normalised features → RunPack → order-flow research → verdict (hit-rate, OOS, placebo, after-cost)

Lane B · CFD / cTrader

cBot logs → trade_log → construction / Achilles audit → verdict (sizing, cost, late entry, no-MFE, exits)
Both lanes produce evidence. They are not the same lane. Proxy flow is never labelled as genuine order flow.
UltraScalp · research / demo · Full-page core loop ↗
  • 01

    AI Market Analysis with Playbooks

    AI market analysis and playbooks work as a pair — a concrete case is the 15-minute Market Open. The system reads early tape, structure, and context against the open playbook so the first quarter-hour is planned, not improvised: clear entries, filters, and exits before the session stretches out.

  • 02

    Intelligent Candidate Search

    Finds and ranks trade candidates intelligently — scanning names, setups, and evidence so the strongest opportunities rise first. Instead of hunting the board by hand, you get a short list ordered by how well each candidate fits the rules, the tape, and the playbook you’re running.

  • 03

    Playbooks that evolve

    Trading playbooks that learn from what worked — and what didn’t. A concrete example is the 15-minute Playbook: entries, exits, and filters keep refining as live results come in. Plans stay current as markets change, instead of freezing a static rulebook.

  • 04

    Rules and AI together

    Hard rules and AI side by side. Clear filters decide what’s allowed before anything reaches the tape; AI adds judgment where judgment helps — reading context, ranking setups, and explaining why a pick looks strong without overriding the rails you set.

  • 05

    AI that reads the news

    Headlines aren’t noise. AI reads the news against the tape so context lands with the trade, not after it — linking catalysts, symbols, and timing so you see whether a story supports or undercuts the setup you’re about to take.

  • 06

    Patterns and market read

    Spots structure and momentum on short timeframes, with order book and depth of market (DoM) when the chart alone isn’t enough. That layered read helps separate real pressure from noise before you commit size.

  • 07

    Trading heatmaps

    See where activity and interest are clustering — across names, times, and pressure — so hot zones stand out at a glance. Heatmaps turn scattered signals into a map you can scan while the session is still moving.

  • 08

    Automation with guardrails

    Automation that can enter and manage trades — with hard limits you set. Gate, confirm, or stop anything that steps outside the rails, so speed never outruns the risk rules you chose.

  • 09

    Symbol bible and knowledge graphs

    Each symbol carries a living “bible” of how it behaves — typical ranges, quirks, and linked names. Knowledge graphs connect those symbols, news, and patterns so related moves and context surface together instead of living in separate silos.

  • 10

    Determinism and AI-created setups

    Deterministic rules lock what is allowed: filters, risk, and pass/fail checks that run the same way every time. Alongside that, AI creates and proposes setups — assembling entries, targets, and context — so you get inventive picks that still clear a fixed gate.

Annotated short-timeframe chart

1 / 7

A Monkey Science case study in AI for live trades.

04 / iMagellan

iMagellan

Live map · wind + streamsEARLY STAGE

02 — iMagellan Early stage

Built to
brief.

An early stage Monkey Science project — global live passage briefing for sailors and skippers. Wind, streams and currents, tides and GPS context, planned in natural language and read on the phone.

Prompt-driven route planning that turns a short ask into leave/arrive windows, gate notes and map intelligence — so the skipper keeps professional judgment while the brief stays close at hand.

RoleAI creator / early product build StanceEarly stage · live briefing ReachGlobal passages LayerWind · streams · tides · GPS
Ask about this work

Early stage · live briefing

1 / 4

An early stage Monkey Science project in live passage briefing.

05 / What I do

Useful AI.
Clear heads.

I help founders, marketers and operators create with AI, choose the right tools, and build workflows that actually stick — informed by a career of shipping new technology before it was comfortable.

Book a conversation
  • 01 AI creation & content systems
  • 02 Consulting & strategy
  • 03 Workflow design
  • 04 Hands-on implementation

06 / Contact

Building with AI?

Let's make
something useful.

Monkey Science
by Rich Mitchell

UK / available worldwide

Tap anywhere or press Esc to close