Skip to content

Reviewer Guide

Campus RAG Assistant is a source-reviewable AI platform for governed campus knowledge. It combines a cited-answer RAG path with a HITL-gated helpdesk escalation loop: when the knowledge base cannot resolve a question, the system can retry retrieval, use controlled web research, search GitHub issues for duplicates, draft a ticket, and file to GitHub only after human confirmation. The system runs behind one FastAPI backend and Vue 3 SPA with AWS / Azure / mock providers, RAGAS evaluation, LangSmith and Prometheus observability, CI/security gates, redaction, and responsible-AI guardrails.

Review it as an engineering artifact: source code, architecture, screenshots, evaluation results, observability, CI/CD, security posture, and release hygiene. It is not presented as a hosted public product.

What this shows

Capability What it shows Evidence
Cited RAG path LangGraph retrieval stages, KB-first answers, multi-query retrieval, rerank hooks, source contracts, and opt-in web research DESIGN.md · EVALUATION.md · ADR-001 · ADR-003
Helpdesk escalation loop Bounded multi-turn escalation with KB retry, web research, GitHub duplicate search, GitHub ticket drafting/filing, clarifying turns, redaction, HITL confirmation, and four explicit outcomes; ADR-006 tracks the LangGraph supervisor migration Helpdesk overview · ADR-005 · ADR-006
AI platform architecture One FastAPI + Vue product surface over AWS / Azure / mock providers, tenant configuration, feature flags, migrations, and CI-safe local mode ARCHITECTURE.md · ADR-001
Evaluation, observability, and responsible AI RAGAS baseline, LangSmith traces, Prometheus metrics, k6 load profiles, gitleaks, protected branches, redaction, and human approval before side effects eval_baseline_v2.md · operations-manual/index.md · ADR-004

Suggested review paths

Reviewer Start here
Hiring manager Case Study
Staff / principal engineer Architecture, Design Notes, ADRs
AI engineer Evaluation, LangGraph KB path, Provider registry ADR
Platform / DevOps reviewer Operations Manual, CI/CD, Security
Product reviewer Screenshots, Case Study, Product Roadmap
Agent / orchestration reviewer Helpdesk overview, Conversation Flow, Engineering Spec, Agentic Rebuild plan

What this repository implements

  • Vue 3 product UI with sessions, streaming chat, cited sources, feedback, OAuth handoff, Ask/Agent mode.
  • FastAPI backend with JWT cookies, SSE endpoints, Alembic migrations, request IDs, Prometheus metrics.
  • Provider registry for AWS, Azure, and mock execution modes.
  • LangGraph RAG pipeline (condense → multi_query → retrieve → rerank → generate → format) plus chain path for true token streaming.
  • Tenant-hydrated prompt and topic configuration in Postgres.
  • RAGAS evaluation harness with a documented v2 retrieval baseline.
  • LangSmith trace capture for KB and web-research paths.
  • Opt-in web research with disclaimer UI and source_kind=web metadata.
  • Helpdesk escalation: ASK-mode one-shot endpoints plus multi-turn AGENT-mode endpoints with HITL ticket filing.
  • CI/CD, gitleaks, dependency review, no tool attribution guard, k6 load testing, release docs, and production hardening backlog.

What this is not

  • Not an official UC Berkeley or UC product.
  • Not a public hosted SaaS product.
  • Not a production deployment claim.
  • Not a generic chatbot demo.
  • Not a claim that the current evaluation set is production-sufficient.
  • Not a claim that the current helpdesk supervisor is LLM-driven; that migration is tracked in ADR-006.

See Notice and License for attribution and licensing details.