"Gambit team on IBM Bob 2.0 hackathon Hackathon"

Team Idea

RepoPilot Onboarding is an agentic AI platform that turns any codebase into a guided, interactive onboarding experience for new developers. Problem: New engineers take 8-10 weeks to become productive, costing enterprises over $300K annually per 50-engineer team. Solution: Submit a GitHub URL. RepoPilot clones the repo, parses it with Tree-sitter, and spawns two IBM Bob 2.0 subagents in parallel — one analyzing architecture, one extracting business logic. Bob's full-repository context powers evidence-backed reasoning; every claim cites exact file paths and line ranges. A synthesis agent merges the findings into an 8-step interactive code tour, a visual architecture summary, and a grounded Q&A interface with inline citations. Built with IBM Bob 2.0 Agent Mode, custom .bob rules, LangGraph, FastAPI, and Next.js. Read-only, deterministic, and scalable to any repository — from open-source projects to enterprise monorepos.

Team Members

Muraghesh Balachandra Shirakol

Muraghesh_B_S

Ashwin TVS

User_with_problems

Prajwal Gunagi

prajwal_gunagi18

Shruthan T M

shruthan650779

SATHWIK AS

SathwikAS

Keval R Jain

kevalxd728

Submission

RepoPilot : Agentic AI Onboarding

RepoPilot is an agentic AI onboarding platform powered by IBM Bob 2.0. By simply pasting a GitHub URL, a new developer receives an autonomous architecture analysis, an interactive 8-step code tour with line-level citations, and a grounded Q&A interface.