Kafka Fraud Detector

Overview

Consumes transactions from a Kafka topic and scores each for fraud risk using velocity analysis, geo-anomaly detection, and retrieval pattern matching. Conditional tools restrict admin_override access based on context. Concurrency control queues transactions by customer_id to prevent race conditions. High-risk alerts are formatted by a tool agent and published to a Kafka outbound topic.

Use cases

Architecture

Main template files

Install these files with connic init my-project --templates=kafka-fraud-detector. The CLI places agent definitions in a folder named after the template under agents/.

kafka-fraud-detector/
  agents/
    fraud-scorer.yaml
    fraud-escalator.yaml
  tools/
    fraud_tools.py
  middleware/
    fraud-scorer.py
  schemas/
    fraud-assessment.json
  requirements.txt
  README.md

Get started

Install the template, create a Connic project, and deploy through a connected Git repository or the CLI.

1. 1

   Install and scaffold

   Install the SDK and create a project from this template.

   terminal

   Copy

   pip install connic-composer-sdk
   connic init my-project --templates=kafka-fraud-detector

   Then cd my-project

2. 2

   Deploy

   Choose a deployment method. A connected Git repository deploys on push; use the CLI for projects without a connected Git repository.

   Git integration

   1. 1

      In Connic: Project Settings → Git & Environments, connect the GitHub repository

   2. 2

      On the same page, map a branch (e.g. main) to the Production environment

   3. 3

      Push the scaffolded project to that repository

   terminal

   Copy

   git add .
   git commit -m "Add Kafka Fraud Detector template"
   git push origin main

   CLI deploy

   1. 1

      In Connic: Project Settings → API Keys & MCP Auth, create an API key and copy project ID

   2. 2

      Run connic login in the project folder

   3. 3

      Use connic dev to try with hot-reload, connic test to run suites, or connic deploy for production

   terminal

   Copy

   connic login
   connic dev     # Ephemeral dev env with hot-reload
   connic test    # Run declarative test suites
   connic deploy  # Deploy to production

3. 3

   Connect and configure

   Add a Kafka inbound connector for the transactions topic and a Kafka outbound connector for fraud alerts. Configure bootstrap servers and optional SASL authentication. Use a connic/* model, or add BYOK credentials under Project Settings → LLM Provider.

   Full connector setup guideQuickstart guideConnector docs