2 posts tagged with "orchestration"

Markets move fast, and making sense of them requires not just data but context — what happened yesterday, what decisions you made, how conditions have changed. The AI Makler worker brings that context to life: an intelligent financial agent that remembers past sessions, makes decisions, manages positions, and can even trigger other workflows.

Think of it as a tireless trading assistant that keeps notes on every session and gets smarter the more you use it.

What Is AI Makler?​

AI Makler (Polish for "broker") is an AI-powered financial agent that lives in the AI category of the left sidebar. Unlike stateless AI workers that process one request at a time, AI Makler remembers its past analyses, decisions, and market observations across multiple runs within the same workflow.

This makes it ideal for:

• Continuous market monitoring — the agent knows what it saw yesterday
• Trading signal generation — it tracks its own accuracy over time
• Portfolio management — it remembers open positions and reviews them
• Multi-step workflows — it can trigger other workflows based on analysis

Key Features​

🧠 Persistent Memory​

• One MongoDB document per workflow — all runs share the same memory
• Remembers: market state, analysis, orders, triggered workflows
• Configurable history (1–100 iterations, default 20)
• No raw prompts saved — just the meaningful context and decisions

📊 Two Processing Modes​

📈 Structured Orders​

When the agent decides to trade, it returns proper order objects:

{
  "action": "buy",
  "symbol": "BTCUSD",
  "entry_price": 86500.00,
  "target_price": 92000.00,
  "stop_loss": 84000.00,
  "position_size": 0.5,
  "order_type": "market",
  "reason": "Bullish flag breakout on above-average volume",
  "certainty_pct": 82
}

The agent only generates orders when certainty > 60%. If it's not confident, it just returns analysis — no false signals.

🔗 Workflow Orchestration​

AI Makler can trigger other workflows to perform complex tasks. List the allowed workflow IDs in the configuration, and the agent will decide when to run them, passing data along. Triggered runs are fire-and-forget via the same Redis queue as manual runs.

💼 Position Management​

Pass your current open positions as a JSON array, and the agent will review each one — deciding whether to close, hold, or modify based on current market conditions.

How to Use It​

Adding the Worker​

1. Drag AI Makler from the AI category onto your canvas
2. Connect it after your data sources (or trigger it on a schedule)
3. Configure the parameters

Configuration​

Output Fields​

Use Cases​

1. Market Monitor With Memory​

[Schedule Trigger] → [Fetch Market Data] → [AI Makler: analysis] → [Condition: alert?] → [Telegram Notify]

AI Makler runs every hour, sees how conditions evolved, and sends alerts when patterns change.

2. Signal Generator With Position Tracking​

[Schedule] → [Fetch Data + News] → [AI Makler: decision] → [Save Orders to User List]

Agent analyses market data and news, returns buy/sell signals with targets and stop-losses.

3. Portfolio Manager​

[Trigger] → [Fetch Positions + Market Data] → [AI Makler: decision] → [Run Workflow "Execute Orders"]

Agent receives current open positions, reviews each one, and decides what to do. The execution workflow handles the actual order placement.

4. Multi-Strategy Coordinator​

[Trigger] → [AI Makler: analysis]
         → [Trigger: Run Backtest Workflow]
         → [Trigger: Run Risk Analysis Workflow]

Agent decides which analysis workflows to run based on market conditions, passing relevant data to each.

Memory in Action​

When AI Makler runs for the first time, it has clean memory. After each session, it saves:

• What the market looked like
• What analysis it produced
• What orders it generated
• What workflows it triggered

On the next run, it gets a summary of previous sessions:

PREVIOUS SESSIONS (most recent first):
  [1] 2026-06-21T08:00:00 | BTCUSD: Bullish, ETHUSD: Neutral | Orders: 2
  [2] 2026-06-20T20:00:00 | BTCUSD: Ranging, high volume | Orders: 1 | Triggered: 1
  [3] 2026-06-20T12:00:00 | BTCUSD: Bearish rejection at 88k

This context lets the agent spot trends in its own decision-making and adapt.

Legal Disclaimer​

This is not financial advice. Trading involves substantial risk of financial loss. The AI Makler worker is a tool for analysis and automation — all trading decisions should be reviewed by a qualified professional. Past performance in memory does not guarantee future results.

You've built a library of workflows — data pipelines, signal generators, backtesters, alert senders. Until now, each one ran in isolation. The new Run Workflow worker changes that: trigger any workflow from inside another workflow, pass variables between them, and (optionally) wait for results.

This turns your workflows into reusable building blocks — your data-processing workflow becomes a function call, your backtest runner becomes a sub-process, your entire analysis chain becomes a single parent workflow.

What Is the Run Workflow Worker?​

The Run Workflow worker lives in the Flow category of the left sidebar. Drag it onto your canvas, select a target workflow (via autocomplete), optionally pass variables, and choose a mode. That's it.

It's a flow-control node — it orchestrates other workflows rather than processing data itself.

Key Features​

• Autocomplete target selection — search and pick any of your workflows by name
• Variable passing — send key-value data that becomes available in the target workflow as {{ variable }}
• Two execution modes — fire-and-forget for parallel execution, wait-for-result for sequential chaining
• Timeout control — in wait mode, configure how long to wait (10–600 seconds)
• Full result capture — wait mode returns every node's output from the target workflow

How to Use It​

Finding the Worker​

Look in the Flow category in the left sidebar, or search for "run workflow". The node shows a play-arrow icon with a gear.

Adding to Your Workflow​

1. Drag the Run Workflow node from the left sidebar onto your canvas
2. Connect it to preceding nodes (e.g., a trigger or data source)
3. Click the node — the right panel opens with configuration fields
4. Select target workflow — the autocomplete field lets you search by name

Configuration​

Passing Variables​

Any variables you pass become available in the target workflow's context. For example, if you pass:

{
  "symbol": "BTCUSD",
  "timeframe": "1h",
  "limit": 200
}

The target workflow can reference them as {{ symbol }}, {{ timeframe }}, and {{ limit }} in any downstream node — just like webhook trigger variables.

Mode Comparison​

Workflow Chaining Patterns​

1. Simple Trigger Chain (Fire-and-Forget)​

[Manual Trigger] → [Run Workflow "Fetch Data"] → [Run Workflow "Send Alert"]

The parent workflow triggers "Fetch Data" and "Send Alert" — both run independently.

2. Data Pipeline (Wait-for-Result)​

[Schedule Trigger] → [Run Workflow "Fetch & Clean Data" (wait)] → [Run Workflow "Generate Signals" (wait)] → [Run Workflow "Store Results"]

Each step waits for the previous one to finish. The parent orchestrates a multi-stage pipeline.

3. Fan-Out / Parallel Processing​

[Trigger] → [Run Workflow "Analyze BTC" (fire-and-forget)]
         → [Run Workflow "Analyze ETH" (fire-and-forget)]
         → [Run Workflow "Analyze SOL" (fire-and-forget)]

All three analysis workflows launch simultaneously — great for multi-symbol scans.

4. Reusable Report Generator​

[Webhook Trigger] → [Fetch Data] → [Process Signals] → [Run Workflow "Generate Report" (wait)] → [Telegram Notify]

The "Generate Report" workflow is shared across many parent workflows — write once, reuse everywhere.

Financial Markets Applications​

Strategy Pipeline​

[Schedule Trigger] → [Run Workflow "Fetch OHLCV Data" (wait)]
                   → [Run Workflow "Compute Indicators" (wait)]
                   → [Run Workflow "Run Backtest" (wait)]
                   → [Telegram Send Results]

Chain your data-fetching, indicator, and backtest workflows together. Each is independently testable and reusable.

Multi-Symbol Analysis​

[Trigger] → [Parameter Loop] → [Run Workflow "Analyze Symbol"]

Use a Parameter Loop to iterate over symbols, passing each one to a shared analysis workflow via variables. Collect results in a final aggregation step.

Output​

Fire-and-Forget​

• run_id — the ID of the triggered run (use to track progress)
• targetWorkflowName — name of the triggered workflow
• passedVariables — the variables that were passed along

Wait-for-Result (all of the above, plus)​

• targetStatus — finished, failed, error, or cancelled
• targetResults — object mapping each node name to its output
• targetFinishedAt — timestamp of completion

Tips​

• Name your workflows clearly — the autocomplete shows workflow names. Descriptive names make selection faster.
• Use wait mode for dependencies — if step B needs step A's output, use wait-for-result.
• Use fire-and-forget for independence — if steps don't depend on each other, let them run in parallel.
• Watch timeouts — complex target workflows may need more than 300s. Adjust the timeout parameter in expert settings.
• Variable names matter — pass variables with names that match what the target workflow expects.

Legal Disclaimer​

This is not financial advice. Trading involves risk of financial loss. The Run Workflow worker is a tool for automation — you are responsible for the logic and outcomes of your workflows.