See the workspace, start to finish
A narrated tour of the one-market loop — research the edge, write the playbook, backtest it on real history, then go live — with every AI call and every guardrail on screen.
Prepare → Decide → Execute → Review
Most tools hand you a signal and walk away. Cortiq runs the entire cycle — and every session, backtest and research run compounds in one per-instrument knowledge base.
Prepare a single-instrument workspace with D1→M15 MT5 context, structured research, train-only hypotheses, out-of-sample validation and a written report you can inspect.
Turn findings into explicit rules: setup, entry, risk, management and invalidation. Attach preparation packages, sentiment reports and an instrument profile so every session starts from real context.
Replay the playbook over historical M1 with real AI decision cycles — strictly no-lookahead, with as-of prep and sentiment. Measure expectancy before a cent of capital is at risk.
Use the prepared context to make and execute your decision in MT5, with approval gates and external risk guardrails. Review the result so the next session starts with evidence rather than a blank slate.
Every session and backtest distills what it saw into the instrument's knowledge ledger — where observations become trusted learnings only once enough evidence confirms them. Live reads rank below backtested ones, and the ★ mastery rating rises only when a strategy reaches production. The market compounds instead of resetting.
One instrument. Two hands on it.
Trade it yourself on the chart, or let the agent trade it and approve what it proposes. Both run inside the same session, on the same instrument, under the same risk limits — and everything either of you does lands in the same journal.
The chart and ticket you place orders from. Screenshots use demo data.
Discretionary, with the prep already done
Start a manual session and the agent never places an order. It still prepares the market, keeps the research, and writes up what happened — you make the calls.
- A live chart in the session — timeframes, drawing tools, indicators, scroll-back through history.
- A guided ticket: set the stop first, pick 0.5%, 1% or 2% risk, and the lot size is calculated for you.
- ATR presets for stops and targets, or click the price straight off the chart.
- Close, part-close and move stops on any open position without leaving the chart.
Autonomous, with the reasoning on the record
Start an autonomous session and the loop runs: wake, read, decide, act. You stay above it — reading the cycles, approving the trades, stopping it when you want.
- The agent wakes on your triggers, reads the data package you approved, and decides.
- Every wake is logged as a cycle you can open — what it saw, what it decided, what it did.
- Its decisions are drawn on the same chart, so you can see where it acted.
- Trades wait for your approval unless you have explicitly handed over that gate.
One workspace for the work around every trade
Prep, data, indicators, risk and the full trade record live as inspectable artifacts. The AI proposes; your rules decide what trades. Nothing happens that you can't read back later.
Open any trade and see exactly why it happened
Cortiq stitches the full record from MT5: the entry, stop and target, the agent's reasoning at the moment of the call, every modification, and the chart at exit. The journal is the source of truth — not a summary you have to take on faith.
Everything you’ve learned about a market, in one place
Every playbook, session, backtest and research run for one symbol, aggregated into a single command center — headed by an honest ★ mastery rating that counts only the strategies you've promoted to production. Underneath runs a knowledge pipeline: observations mature into learnings only once enough evidence confirms them, learnings become hypotheses, hypotheses become validated edges, and edges become playbooks. Live reads are always weighted below backtested ones — so a market's edges and traps compound with honest provenance instead of resetting each session.
Prep is already done when you sit down
Preparation packages (higher-timeframe regime, key levels, structure, directional skew, session map), sentiment reports and an instrument profile are auto-generated before the session and refreshed on a schedule.
You decide what it sees
Pick the timeframes (M1→D1), indicators (MACD, RSI, Bollinger, MA, ATR, Stochastic, CCI…) and news the agent reads each cycle. Bundle them into reusable packages the agent receives on every wake.
It sees exactly what you see
Indicator values are read live from your MetaTrader 5 terminal each cycle — the same numbers your charts show, handed to the agent as structured data instead of a screenshot.
The model can't touch your risk limits
Hard limits — not the model — enforce daily and weekly drawdown, profit targets, max trades, per-symbol caps and loss-streak stops, checked outside the model on every cycle. A breach triggers an emergency stop that cancels pending orders across every account and pauses sessions — then auto-resumes when limits clear.
Know exactly where the day stands
The dashboard reads how far the day is from its profit target and how much buffer is left before the daily stop — across all accounts, or for a single account you select — the same limits the guardrails enforce, updating as trades close.
Every trade, rebuilt for you
Entry, stop, target, the agent’s reasoning, the action timeline and the chart at exit — stitched together from MT5. Tag and annotate, generate session summaries, and tie into Open Market Journal.
See every decision, cycle by cycle
Each wake is logged as a cycle: what the agent saw, what it decided and what it did. Open any cycle to read the reasoning, the parsed decision and the execution result — the timeline is the audit trail, not a summary you take on faith.
Study one market deeply
Prepare reusable data files, then run Behaviour, Edge or watch-and-learn Exploration passes over the history. Grounded results come back as a plain-language answer — verdict, confidence and chart examples — ready to hand off into a playbook, profile or prep notes.
Learn from history before you trade it again
A no-positions replay steps the agent through historical candles of one instrument and writes what it notices — observations and durable learnings — straight into the knowledge ledger. The instance-finder runs in a network-denied sandbox: it can read the data but never touch your account.
Every claim pinned to the candle it happened on
A learning is only as good as the instances behind it. Each one opens onto its own chart with a marker per moment the AI described — the level forming, the sweep, the reclaim, the outcome — and the matching sentence beside it. Instances that argue against the pattern are kept and marked, not quietly dropped.
The chart is in the session
Candles stream from your MT5 terminal into the session itself — timeframes from M1 to D1, drawing tools, indicators calculated by Cortiq, and scroll-back through history. Your open positions draw their entry, stop and target on it; so do the agent’s decisions.
Place the trade yourself, sized properly
Manual sessions have no AI decision loop — you trade. Set the stop first, choose 0.5%, 1% or 2% account risk, and the lot size follows. ATR presets for stops and targets, prices picked straight off the chart, and close or part-close any position from the same panel.
Replay it by hand, or let the agent run it
Both kinds of backtest open straight into a chart. Step a manual replay forward candle by candle and place orders as the bar prints — the cursor is a hard cutoff, so you can never see past it. Or run the autonomous replay: real decision cycles over historical M1 with as-of prep, sentiment and profile context.
Nothing moves without your yes
Every change the AI wants to make — memory, triggers, trades — waits for your yes. Mutating actions stay gated until you approve, inside the session windows you set.
Practice the real process, risk-free
Run the identical loop with no real orders. When a virtual trade earns it, promote it to a real MT5 order — same logic, same guardrails, one click.
Your keys, your cost — can be €0.
Bring whatever AI you already use or pay for. Cortiq never resells inference and never sits between you and your provider — switch anytime without losing your session. Run a local model on your own GPU and your ongoing AI cost is €0.
One key, hundreds of models. Route to whatever is best for the job and change your mind whenever you like.
Run the AI fully private on your own GPU — nothing leaves your machine, and every session after setup costs you nothing.
Drive the agent through your existing ChatGPT or Claude subscription via the official CLI / agent — no extra API bill on top of the plan you already pay for.
Paste a key from your provider and pay their rate directly — no middleman, no markup.
Compatible today: OpenRouter · Ollama, LM Studio, llama.cpp · ChatGPT and Claude via their official CLI · direct OpenAI, Anthropic and Gemini APIs.
Built like infrastructure, not a bot.
Cortiq wires the agent into MetaTrader 5 through a local bridge, then wraps every action in hard limits that live outside the model. The reasoning is the AI's; the rules are yours.
The agent talks to MetaTrader 5 through a bridge that runs on your computer. No broker plugin, no cloud relay — nothing about your orders touches our servers.
Run multiple MT5 terminals and accounts simultaneously, each on its own port. Every session binds to one chosen account.
Market and pending orders (limit/stop), SL/TP modification, partial close, full close and cancel — with a pre-trade broker margin check before anything is sent.
By design, each session is locked to a single market. No basket scanning — the agent builds deep, measurable expertise on the instrument in front of it.
Global and per-account rules enforce daily and weekly drawdown, profit targets, max trades, per-symbol caps and loss-streak stops — checked outside the model on every cycle.
A breach cancels pending orders across every account and pauses sessions, then auto-resumes once the limits clear. Unrealized P/L is monitored continuously.
Position size is computed from equity × your risk% and overrides whatever lot the agent proposed. The model can suggest; it cannot oversize.
A human-in-the-loop Copilot dock gates mutating actions until you approve, with time-of-day session windows that keep the agent inside the hours you trade.
The AI proposes. Your rules dispose.
Context gets stronger when you review it
Single-market focus isn't a Cortiq invention. Some of the most respected traders alive built their careers on it — going deep on one thing instead of wide on everything.
The wizards specialize
Read through Jack Schwager's Market Wizards interviews with the world's best traders and the same lesson keeps surfacing: depth beats breadth. The edge comes from knowing one arena cold — its behaviour, its tells, its traps — not from watching everything at once. Concentrate, then compound.
Tom Hougaard trades one thing — the index open
The high-stakes day trader and author of Best Loser Wins has built his career on a tiny, fixed set of index markets — primarily the German DAX — traded live on YouTube nearly every day for years. Not a scanner, not a basket. A focused practice, reviewed over time.
What working traders keep saying on the podcasts
Short clips from trader interviews. Different guests, different markets — the same conclusion, reached independently: narrow down, then go deep. Every quote is transcribed from the video's own captions.
Tom Hougaard, the traders in Market Wizards, and everyone in the clips above are independent of Cortiq and do not endorse it. Quotes are transcribed from each video's public captions and lightly trimmed for length, with wording unchanged. They're shown here because concentrated, single-market focus is a long-proven approach — and Cortiq is built to make that focus practical. Nothing here is trading advice.
The journal writes itself, then teaches the next session
Never write a journal entry again — and never lose the lesson. Cortiq rebuilds every trade the moment it closes: entry, reasoning, timeline, all of it. Then it feeds that memory into your next session, so you stop relearning the same thing every month.
Entry, stop, target, the reasoning, the full timeline — reconstructed the moment the trade closes. No spreadsheet, nothing to abandon by Wednesday.
The reasoning behind every decision is saved as plain text you can re-read, tag and annotate — not just a P/L number that tells you nothing about why.
What happens today feeds straight into tomorrow’s research and prep, so you stop starting from zero every session.
Cortiq’s real daily preparations publish every day on Open Market Journal — the same reasoning, the same journal, in public. See what a prepared session actually looks like before you buy.
Read today’s prep on Open Market JournalThe questions a skeptic asks first
You should be wary of opaque trading software. Here is exactly where Cortiq assists your process and where your decisions and rules remain in control.
No. Every AI call is plain text you can read, edit and reject before it acts. The agent’s reasoning, the market read and each decision are logged in full — nothing executes that you can’t inspect, before, during and after the trade.
Good. The risk limits live outside the model and the model cannot override them — position size, drawdown and trade caps are enforced by validators, not the AI. Mutating actions wait for your approval, and you can paper-trade the exact loop first.
Cortiq is a trader-led workspace, not an autonomous bot. Your approval gates, daily and weekly drawdown limits, trade caps and emergency stop keep execution inside the rules you set.
It is a guided Windows install and an activation key you paste on first launch. Connect your MT5 account, point it at an AI you already have — OpenRouter, a local model, or your existing ChatGPT or Claude — and run.
Depth over breadth. A session stays on one instrument so preparation, decision criteria and journal review share the same context. Multi-symbol scanning is deliberately outside the workflow.
It will be, sometimes — it is a tool, not a promise. That is why your playbook carries explicit invalidation rules, the guardrails cut losers on their own, and you stay in the loop on every mutating action. Cortiq does not predict markets or offer signals.
Built for me. Now for you.
I’ve spent close to a decade as a software engineer, architecting systems at one of the world’s largest tech companies. Trading has been my other decade, a hobby I never stopped taking seriously.
My own prep used to eat two or three hours before I’d even opened a chart. I kept losing the lesson from a trade I’d made a month before, buried in a folder of screenshots I never reopened.
Along the way, I built my own trading tools, just for me. Cortiq is one of them, the one that turned out beautiful, refined over years until it worked exactly the way I needed.
Now I want other serious traders to have it too. I think you’ll get real use out of it.
One key. One price. Yours to keep.
Cortiq is a one-time purchase — not a subscription, no auto-renewal. The only ongoing cost is your own AI usage, and with a local model that can be €0.
Cortiq is an execution and research environment, not a signals service and not financial advice. Trading is risky and you can lose money. Read the refund policy and risk disclosure before you buy.
Straight answers before you buy
What Cortiq is, what it needs, and what it deliberately does not do. No overpromises.
How to Master One Market
The five-stage loop I run on a single instrument — and how to wire it to an AI and your own MT5. Works with Cortiq or the tools already on your desk.
- Why committing your read before you see the outcome is the whole game
- How to write heuristics that carry their context, instead of trigger rules that trap you
- Where an AI genuinely helps a discretionary trader — and where it will confidently wreck you