Skip to main content

2 posts tagged with "market-data"

View All Tags

Introducing AI Orchestrator — An Agent That Coordinates Your Workers

· 6 min read
ApudFlow OS
Platform Updates

We are introducing the AI Orchestrator — a new worker that runs an AI agent inside your workflow. Instead of wiring every step by hand, you select the workers the agent may use and describe the task. The orchestrator chooses the parameters, calls the workers, adapts when data is missing, and writes the final answer.

It is the difference between a fixed pipeline and a delegation.

Why we built it​

Financial workflows rarely follow the same path twice. A market brief may need price data, news, and the economic calendar — but sometimes the news feed is empty, the calendar needs a wider window, or a symbol has no recent candles. A fixed workflow has to anticipate every branch. The AI Orchestrator can decide at runtime.

Common examples:

  • prepare a morning market brief from several sources,
  • compare price action with news and macro events,
  • monitor a setup and alert only when a score is high enough,
  • research a symbol with multiple data providers,
  • remember preferences and lessons between scheduled runs.

How it works​

The orchestrator is a ReAct-style tool-calling agent:

  1. It receives your prompt, the selected workers, and the run context.
  2. Each selected worker is exposed as a tool with its parameter schema.
  3. The model reasons, calls a worker, observes the result, and decides the next step.
  4. It can retry with different parameters or choose another worker.
  5. When it has enough information, it writes the final answer.

Every tool call is a real worker execution. That means API credits, rate limits, credentials, and side effects apply exactly as they would for a normal node. The trace is returned in the calls field so you can audit what happened.

What you get​

The node returns more than a text answer:

FieldWhat it contains
answerThe final written response.
planThe agent's plan when planning mode is enabled.
callsWorker name, parameters, and result preview for every call.
workers_usedThe unique workers that were actually invoked.
statusfinished when the run completed normally.
stepsNumber of reasoning/tool steps used.
usagePrompt, completion, total, cached tokens, and LLM call count.
scoreOptional numeric score for conditional branching.

The output panel shows answer as its own group next to the calls and workers_used tables, so you can inspect both the result and the path that produced it.

Quick start​

1. Add the node​

Place AI Orchestrator after a trigger and before whatever consumes the result:

[Schedule] -> [AI Orchestrator] -> [Telegram]

2. Select the workers it may use​

Keep the set small and focused. For a market brief:

fetch_price
fetch_news
browse_calendar

Triggers and visualization/widget nodes are hidden automatically — they cannot be executed as tools. The orchestrator itself and parameter_loop are also excluded.

3. Write the prompt​

State the goal, output format, time range, and what to do when data is missing:

Prepare a concise EURUSD market brief for the London session.

Use the last 24 hours of price action, the most relevant news, and the
high-impact events in the next 48 hours. Compare the technical picture with
the news flow and call out disagreements.

Return three bullet points of evidence, a directional bias, and a confidence
score from 1 to 5 on a final line exactly like: SCORE: 4

If news is unavailable, say so explicitly and continue with price and calendar
data. Do not invent headlines.

4. Run it​

Run the workflow from the editor or wait for the trigger. Open the calls trace to see which workers were used and with which parameters.

Memory that lasts between runs​

Set memoryScope to control persistence:

  • run — memory only inside the current run (default),
  • workflow — session history and long-term facts persist for this workflow/node/owner,
  • none — no memory is loaded or saved.

With workflow scope, the agent can use remember and recall tools. Save stable knowledge, not market snapshots:

  • good: "Use the London timezone and report prices in EUR for this workflow."
  • good: "The CoinGlass funding-rate endpoint is the preferred BTC derivatives source."
  • not useful: "BTC is 86,500 right now."

Guardrails for production​

Long-running agents need limits. Open advancedSettings to tune:

  • maxSteps — maximum reasoning/tool steps (default 15),
  • maxRuntimeSeconds — wall-clock budget for the node (default 180),
  • toolTimeout — maximum time for one delegated worker,
  • tokenBudget — total token budget, 0 for unlimited,
  • maxToolCalls — hard cap on worker invocations, 0 for unlimited,
  • planningMode — react to act immediately, plan to write a plan first.

Identical worker calls with identical parameters are cached within a run. A retry with different parameters is a new call and counts against maxToolCalls.

Conditional alerts with a score​

The orchestrator does not decide which downstream nodes run. For deterministic branching, ask for a score and use a Condition node.

Prompt ending:

End with a line exactly like: SCORE: 4

Condition expression:

vars['Orchestrator']['score'] >= 4

Then send Telegram only on the true branch. You get the agent's reasoning plus a hard threshold you can audit.

Choosing between the orchestrator and a fixed pipeline​

Use the AI Orchestrator when the sequence of steps depends on what the data says. Use ordinary workers or Run Workflow when the sequence is known in advance.

A useful rule:

  • Fixed steps -> normal workflow nodes.
  • Deterministic workflow-to-workflow orchestration -> Run Workflow.
  • Adaptive research across several workers -> AI Orchestrator.
  • Trading analysis with structured orders -> AI Makler.

Learn more​

The full worker reference — parameters, output fields, memory details, examples, and troubleshooting — is available in the AI Orchestrator documentation.

The deep dive article covers the agent loop, tool selection, prompt engineering, and production patterns in more detail.

Availability​

AI Orchestrator is available now in the public worker library under the AI category. Add it to a workflow, select a few workers, and give it a task.

As always, validate automated outputs before acting on them. The orchestrator is a reasoning layer, not a guarantee of accuracy, and it should sit behind your risk controls.


This post is for educational purposes only and does not constitute investment advice. Financial markets involve risk. Always test workflows and use appropriate risk management.

Twelve Data Market Data Connector - Comprehensive Financial Data Access

· 7 min read
ApudFlow OS
Platform Updates

In today's fast-paced financial markets, access to reliable and comprehensive market data is essential for informed trading and investment decisions. Introducing the Twelve Data Market Data Connector - a powerful worker that provides seamless access to one of the most comprehensive financial data APIs available.

What is Twelve Data Market Data Connector?​

The Twelve Data Market Data Connector integrates with the Twelve Data API to provide access to real-time and historical financial data across multiple asset classes including stocks, forex, cryptocurrencies, ETFs, and mutual funds. Whether you're building trading strategies, conducting fundamental analysis, or developing financial applications, this connector offers everything you need in one unified interface.

With support for over 40 different operations ranging from historical price data to technical indicators and fundamental company information, the Twelve Data connector eliminates the need for multiple data sources and complex API integrations.

Key Features​

  • 40+ Operations: From basic price data to advanced technical indicators and fundamental analysis
  • Multi-Asset Support: Stocks, forex, crypto, ETFs, mutual funds, and more
  • Real-time & Historical Data: Access both live market data and extensive historical datasets
  • Global Coverage: Data from exchanges worldwide with automatic timezone handling
  • Flexible Parameters: Customizable intervals, date ranges, and output sizes
  • Rate Limiting: Built-in per-user rate limiting when using shared API keys
  • Error Handling: Robust error handling with clear error messages
  • API Key Management: Support for personal API keys or shared environment keys

Core Operations Overview​

1. Market Data Operations - The Foundation​

time_series: Historical and intraday OHLCV data for any symbol quote: Real-time quote snapshots with full market information price: Simple real-time price data for quick checks

2. Technical Analysis Operations​

indicator: 20+ technical indicators including SMA, EMA, RSI, MACD, Bollinger Bands

3. Discovery Operations​

symbol_search: Find symbols by name, exchange, or country exchanges: List all available exchanges and markets

4. Fundamental Operations​

profile: Company overview and basic information fundamentals: Detailed financial statements and metrics dividends, splits, earnings: Historical corporate actions logo: Company logo URLs for branding

5. Financial Statements​

income_statement: Revenue, expenses, and profitability data balance_sheet: Assets, liabilities, and equity information cash_flow: Operating, investing, and financing cash flows

6. ETFs & Mutual Funds​

etfs_list, etfs_world: ETF discovery and global listings mutual_funds_list, mutual_funds_world: Mutual fund data and analysis

7. Calendar & Events​

dividends_calendar, earnings_calendar: Upcoming corporate events ipo_calendar: New public offerings and listings

8. Analyst & Market Data​

earnings_estimate, revenue_estimate: Analyst forecasts recommendations, price_target: Analyst opinions and targets analyst_ratings: Comprehensive analyst coverage

Getting Started - Interface Configuration​

Basic Setup​

  1. Select Worker Type: Choose "twelve_data" from the worker selection dropdown
  2. Choose Operation: Select your desired operation from the operation dropdown
  3. API Key (Optional): Enter your personal Twelve Data API key, or leave blank to use the shared key
  4. Configure Parameters: Fill in operation-specific parameters based on your needs

Common Parameters​

  • api_key: Your Twelve Data API key (optional if shared key is configured)
  • operation: The specific operation you want to perform
  • symbol: Stock ticker, forex pair, or crypto symbol (required for most operations)

Operation-Specific Parameters​

Time Series Configuration:

  • interval: Data interval (1min, 5min, 15min, 30min, 45min, 1h, 2h, 4h, 1day, 1week, 1month)
  • outputsize: Number of data points to return (max 5000)
  • start_date/end_date: Date range for historical data
  • timezone: Target timezone for timestamps

Technical Indicators:

  • indicator: Indicator type (sma, ema, rsi, macd, bbands, etc.)
  • time_period: Lookback period for calculation
  • series_type: Price series to use (open, high, low, close)

Search & Discovery:

  • symbol: Search query for symbol lookup
  • exchange: Filter by specific exchange
  • country: Filter by country

Advanced Configuration Options​

Rate Limiting Awareness​

When using the shared API key, the system enforces per-user rate limits (5 calls per minute). Make sure your userId is properly configured in the context for accurate limiting.

Data Formatting​

All timestamp data is automatically formatted in ISO format for consistency. You can customize this behavior through additional parameters if needed.

Multi-Symbol Support​

Operations like time_series support comma-separated symbol lists for batch requests, allowing you to fetch data for multiple assets in a single call.

Practical Implementation Examples​

Intraday Trading Strategy​

Create a complete intraday analysis workflow:

  1. Fetch Real-time Quotes using the quote operation
  2. Calculate Technical Indicators using the indicator operation
  3. Monitor Multiple Symbols with batch time_series requests
  4. Set Alerts based on price levels and indicator signals

Complete Workflow Example:

  • workers[0]: Twelve Data Connector
    • type: twelve_data
    • operation: time_series
    • symbol: AAPL,MSFT,GOOGL
    • interval: 5min
    • outputsize: 100
  • workers[1]: Technical Analysis
    • type: technical_analysis
    • indicators: rsi,macd
    • data_source: workers[0].result

Fundamental Analysis System​

Build comprehensive company analysis:

  • workers[0]: Company Profile
    • type: twelve_data
    • operation: profile
    • symbol: TSLA
  • workers[1]: Financial Statements
    • type: twelve_data
    • operation: income_statement
    • symbol: TSLA
    • period: annual
  • workers[2]: Analyst Estimates
    • type: twelve_data
    • operation: earnings_estimate
    • symbol: TSLA

ETF Portfolio Analysis​

Analyze ETF performance and holdings:

  • workers[0]: ETF Discovery
    • type: twelve_data
    • operation: etfs_world
    • country: US
  • workers[1]: ETF Performance
    • type: twelve_data
    • operation: etfs_world_performance
    • currency: USD

Operations Comparison Table​

Operation CategoryBest ForKey ParametersOutput Format
Market DataPrice analysis, chartingsymbol, interval, datesOHLCV arrays
Technical IndicatorsSignal generationindicator, symbol, periodIndicator values
FundamentalsCompany analysissymbolJSON objects
FinancialsRatio analysissymbol, periodFinancial statements
ETFs/Mutual FundsPortfolio constructionfilters, limitsAsset listings
CalendarsEvent timingdate rangesEvent arrays
Analyst DataInvestment decisionssymbolEstimates and ratings

Best Practices and Tips​

API Key Management​

  • Use personal API keys for higher rate limits and dedicated quotas
  • The shared key enforces per-user limits (5/min) to ensure fair usage
  • Monitor your API usage through the Twelve Data dashboard

Data Optimization​

  • Use appropriate intervals for your analysis timeframe
  • Limit outputsize to reduce response times and API costs
  • Cache frequently accessed data to minimize API calls

Error Handling​

  • Check for API key validity before complex workflows
  • Handle rate limit errors gracefully with retry logic
  • Validate symbol existence before requesting detailed data

Performance Considerations​

  • Batch requests for multiple symbols when possible
  • Use historical data endpoints for backtesting
  • Implement caching layers for real-time applications

Integration with Other Workers​

Trading Strategy Integration​

Combine with technical analysis workers:

  • Support & Resistance Calculator: Use price data for level identification
  • Pattern Recognition: Feed historical data for pattern detection
  • Risk Management: Incorporate volatility data from indicators

Portfolio Management​

Build comprehensive portfolios:

  • Asset Allocation: Use ETF and mutual fund data
  • Performance Tracking: Monitor returns with price data
  • Rebalancing: Trigger based on fundamental changes

Alert Systems​

Create intelligent notifications:

  • Price Alerts: Monitor specific levels with real-time data
  • Technical Signals: Generate alerts from indicator crossovers
  • Event Notifications: Track earnings and dividend calendars

Conclusion​

The Twelve Data Market Data Connector represents a comprehensive solution for financial data access, providing everything from basic price information to advanced fundamental analysis in a single, easy-to-use interface. Whether you're a retail trader, institutional investor, or financial application developer, this connector offers the flexibility and reliability you need to build sophisticated financial workflows.

With support for global markets, multiple asset classes, and extensive historical data, the Twelve Data connector eliminates data silos and simplifies the development of financial applications. Start exploring the power of comprehensive market data today and unlock new possibilities for your trading and investment strategies.

For detailed guides on specific operations, check out our dedicated articles covering each major operation category with step-by-step interface instructions and practical examples.