Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    LatAm Synth — Synthetic Fintech Test Data

    1

    Generate statistically realistic, privacy-safe synthetic LatAm fintech data for testing and ML.

    Free

    1 useSecurity scanned
    LatAm Synth — Synthetic Fintech Test Data

    LatAm Synth — Synthetic Fintech Test Data

    Example session with this skill installed

    Generate a test fixture for 50 users in Mexico and Colombia for a savings app demo. I need reproducible JSON data for 2024.

    • Read your context and instructions
    • Compiled the latam synth

    I have generated a synthetic dataset for 50 users across Mexico and Colombia using the latam-synth actor. The generation used seed 42 to ensure these results can be reproduced in your test suite. The data includes linked user profiles, savings goals (e.g., "Emergency Fund", "Travel"), and a full transaction history for the 2024 calendar year.

    Synthetic Dataset Summary

    TableRecordsFormatPrimary Key
    users50JSONuser_id
    goals84JSONgoal_id
    transactions612JSONtransaction_id
    // Sample of generated users.json
    [
      {
        "user_id": "u_88291",
        "country": "Mexico",
        "gamification_score": 740,
        "savings_discipline_score": 0.82,
        "goals_completed_ratio": 0.66
      },
      {
        "user_id": "u_10293",
        "country": "Colombia",
        "gamification_score": 410,
        "savings_discipline_score": 0.45,
        "goals_completed_ratio": 0.25
      }
    ]
    
    // Sample of generated goals.json
    [
      {
        "goal_id": "g_551",
        "user_id": "u_88291",
        "category": "Education",
        "name": "Master's Degree",
        "required_amount": 5000.00,
        "created_at": "2024-01-15",
        "deadline": "2024-12-30",
        "goal_status": "in_progress",
        "is_shared": false
      }
    ]
    

    Next steps

    • Save the full OUTPUT_DATA to your tests/fixtures/ directory.
    • Use seed 42 in your CI configuration to maintain consistent test state.
    • Verify that your dashboard frontend correctly calculates the goals_completed_ratio from the synthetic user records.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Give your agent realistic financial test data for Latin America instead of Faker output.

    This skill teaches your agent when and how to call the LatAm Synth generator on Apify. It produces three linked tables (users, savings goals, deposit/withdrawal transactions) that are 100% synthetic, contain zero personal data, and are statistically calibrated on 506,311 real records from Coinch, a savings app I built and ran across Latin America from 2015 to 2024.

    What makes the data realistic

    • Multimodal deposit amounts, including the round-number deposits real users make
    • Real monthly seasonality (January peak, December dip)
    • 8 goal categories with realistic amounts, horizons and abandonment rates
    • Coherent per-goal histories: achieved goals actually reach their target
    • Reproducible by seed, so your test fixtures stay identical across runs

    Use it for Test fixtures and seed data, integration and QA testing, realistic demo dashboards, and bootstrap data for churn or segmentation models.

    Requirements An Apify account. Your agent runs the generator through the Apify MCP server or the Apify API with your own token. Generation is billed by Apify at about $0.25 per 1,000 synthetic users; the agent estimates and confirms the cost before large runs.

    Not for Card authorizations, merchant acquiring, fraud labels or lending data. The generator models savings behavior only.

    Limited to savings goals, deposits, and withdrawals. No support for credit, lending, fraud labels, or card auths. Requires an Apify account and API token.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike generic libraries, this skill uses statistical distributions from 500,000+ real records to replicate authentic user behaviors, such as "round-number" deposits and realistic goal abandonment rates, which are crucial for valid fintech testing.

    The skill is compatible with any AI agent or environment that supports the Model Context Protocol (MCP) or REST APIs, including popular tools like Claude Desktop, Cursor, and custom Node.js/Python scripts.

    Yes, by using the seed-based generation feature, you can produce the exact same dataset across different environments, ensuring consistent test fixtures for your CI/CD pipelines.

    While the data is statistically modeled after real-world trends, it contains no PII (Personally Identifiable Information) and is 100% synthetic, making it safe for use in staging environments and compliant with privacy regulations.

    The skill focuses specifically on the savings lifecycle, including user profiles, goal-setting, and transaction histories (deposits/withdrawals); it does not currently support lending, payroll, or credit card authorization data.

    New in APIs & Backend