Skip to content
Jawad Nisar
AI & AutomationLLM compliance scoring / insurance call centers

IntelligenceX

Call recordings in, LLM-scored compliance scorecards out.

Role
Full-stack engineer at Igknight Tech

Overview

A multi-tenant platform for insurance call centers. Recordings arrive from SFTP, S3 and partner APIs, get transcribed, then scored by configurable LLM scorecards for required disclaimers and agent performance. I worked across the ingestion pipeline, the background job stack and the React front end.

What I built

  1. Shipped features and production fixes across ingestion from SFTP, S3 and partner APIs
  2. Hardened concurrent ingestion with race-safe writes backed by unique indexes
  3. Added per-item isolation to scheduled job loops, so one bad record cannot stall the rest
  4. Improved the prompt runner behind the LLM scorecards
  5. Tightened the protocol for destructive production scripts, with read-only pre-flights that print the blast radius

Stack

  • Ruby on Rails
  • React
  • PostgreSQL
  • LLM APIs
  • Solid Queue
  • TypeScript
  • Deepgram
  • AWS

Related

Other projects that share this one's domain or its stack.

  • AI & Automation2025

    CHIIRP

    Legacy AJAX to Rails Turbo, with the server bill cut on the way.

    • Ruby on Rails
    • React
    • Sidekiq
    • PostgreSQL
    • +1
  • AI & Automation

    Moemate

    AI agent platforms with real personalities behind them.

    • Node.js
    • TypeScript
    • MongoDB
    • Redis
    • +4
  • AI & Automation

    Eliza Agent

    A social media AI agent that can take on any character.

    • Node.js
    • LLM APIs
    • NoSQL