Skip to content
View surpradhan's full-sized avatar
🎯
AI Engineer → Founder
🎯
AI Engineer → Founder
83 followers · 37 following
  • Bangalore

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Block or report surpradhan

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
surpradhan/README.md

Banner

AI Engineer · Builder · Bangalore

LinkedIn  ·  GitHub

I build systems at the intersection of language models and real-world utility - from evaluation frameworks and agent pipelines to tools that make AI actually work in production. Currently exploring agent memory, multi-agent orchestration, and the infra that makes large systems reliable.

Work

personal-mobile-orchestrator   ·   Python
AI-powered orchestration layer for autonomous mobile automation. 146 commits and counting.

claude-code-for-ai-engineers   ·   Python
A methodology-first skill pack for AI engineers - covering RAG evaluation, agent debugging, MCP servers, paper reproduction, and benchmark reporting.

agent-workflow-comparison   ·   Python
A controlled benchmark of 10 AI agent workflow patterns - single-step through human-in-the-loop - evaluated across 25 tasks on success rate, answer quality, tool accuracy, latency, and token cost. Results are directly comparable.

cartograph   ·   Python
Intelligent mapping and data visualization.

Stack

Python · TypeScript · JavaScript

LangChain · OpenAI · Anthropic Claude · Hugging Face

FastAPI · PostgreSQL · Docker

Background

I work at the edge of what language models can reliably do - building the scaffolding, the evals, and the debugging tools that make the difference between a demo and a system. My interest is both in the models themselves and but more in the engineering discipline around them.

Bangalore, India

Popular repositories Loading

  1. agent-event-protocol agent-event-protocol Public

    AEP is an open observability protocol for AI agent systems - giving you structured event capture, real-time session tracing, and multi-agent workflow visibility in a single self-hosted deployment.

    JavaScript 3 5

  2. forecasting-showdown forecasting-showdown Public

    A rigorous benchmark of 11 time-series forecasting models on hourly energy demand data — from a seasonal naive baseline to gradient-boosted trees, deep recurrent networks, and a stacking ensemble.

    Python 3

  3. agent-workflow-comparison agent-workflow-comparison Public

    A controlled benchmark comparing 10 AI agent workflow patterns on a shared structured business dataset. Every pattern runs the same 25 tasks against the same data using the same LLM — results are d…

    Python 3

  4. spendwise-ai spendwise-ai Public

    A Local, open-source personal finance analyser — no cloud, no API keys, no data leaves your machine.

    Python 2

  5. claude-code-for-ai-engineers claude-code-for-ai-engineers Public

    Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Full pack (6 skills, …

    2

  6. orionpulse-data-agent orionpulse-data-agent Public

    A sales analytics agent that combines deterministic data tooling with optional LLM orchestration.

    Python 1