Skip to content
View imtiazx's full-sized avatar
1 follower · 1 following

Block or report imtiazx

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
imtiazx/README.md

// what I'm building

Project What
✅ RAGScope Benchmarks 5 RAG strategies side by side. Faithfulness, latency, context precision.
🟠 DocuAgent Multi-agent document intelligence with supervisor routing and Redis-backed memory.
⚪ SafeScore Red-teaming toolkit for deployed GenAI apps. System prompts, RAG pipelines, tool configs.
⚪ LLM Observatory Drop-in SDK for token cost, latency, and output quality monitoring.
⚪ GraphRAG Lite Entity extraction + graph traversal + vector search with visible reasoning paths.
⚪ PromptOps Version control and A/B testing for prompts with Claude-as-judge evaluation.

✅ completed    🟠 building    ⚪ planned

// numbers

  • 5 years at Accenture Industry X
  • 25+ enterprise GenAI studies delivered
  • 4 disciplines: statistics, data science, responsible AI, forward deployed engineering

Profile Views

Pinned Loading

  1. ragscope ragscope Public

    Public RAG benchmarking harness. Compare retrieval strategies (Naive, HyDE, Multi-query, Hybrid) on your own corpus with RAGAS evaluation scores.

    Python