agentic-pipeline

Structured, multi-agent development pipeline

An AI-powered technical interview and assessment platform that conducts real-time coding interviews using speech-to-text and large language models. Built on a scalable microservices architecture with Redis and PostgreSQL, enabling automated candidate evaluation, code assessment, skill scoring, and personalized interview experiences at scale.

Document Intelligence Refinery — agentic extraction pipeline with multi-strategy routing and confidence-gated escalation.

Commando AI: AI-powered project management using Monte Carlo simulation to predict delivery dates with confidence intervals. Multi-agent AI optimizes resource allocation. Automates workflows across Slack, Discord, Google Drive, Notion. Features real-time meeting transcription and intelligent task automation.

Six-agent agentic pipeline for legacy modernization via business logic extraction and greenfield rebuild

⚠️ Consolidated into athlete-profiler → github.com/anil-gorti/athlete-profiler

HeadMaster — open-source ADLC (AI-Driven Delivery Lifecycle) built on Claude Code. Turns a single conversation into PRD, TDD, Jira stories, code, tests, and a reviewed PR.

Pre-flight checks for AI agents — Claude Code plugin with adversary verification, atomic budgets, and tournament-gated prompt promotion.

Agentic job search pipeline: LangGraph + HiTL review + Claude scoring + resume tailoring + MCP server

Agentic Pipeline for course creation. Mechanical verification, diagrams and house style. Highly parallel with guardrails and UI included. VSCode and Mastra Editions.