PROJECT / 2025
SynGraph
Deep Research Agent
LangGraph + Next.js workflow that orchestrates supervisor/worker agents for deep research with dual search engines and human clarifications.
- stack
- TypeScript · Next.js · LangGraph · Google Gemini · Tavily · Exa · MDX
How it works
question
you askclarify
asks back if it's vaguesupervisor
workers search Tavily and Exareport
Gemini Pro writes it
01 / Overview
Course project (TNM114) that builds an agentic research stack: a router detects follow-ups vs new requests, a supervisor delegates to parallel researcher agents, and reports are synthesized with citations. Uses Gemini 3 Pro for reasoning, Gemini 2.5 Flash for routing/summarization, and Tavily + Exa for web/semantic search.
02 / Key features
- –Supervisor-worker LangGraph with typed state and parallel researchers
- –Clarification interrupts for ambiguous requests before planning
- –Dual search (Tavily + Exa) with compression and source tracking
- –Follow-up handling to merge prior context with new queries
- –Report generation pipeline producing cited research briefs
03 / Challenges
- –Routing between new research and follow-up answers reliably
- –Keeping research loops transparent with cited sources
- –Balancing depth vs speed across Gemini Pro and Flash roles
04 / Solution
Implements typed graph nodes for route/clarify/brief/supervisor/report, integrates Tavily and Exa connectors, and separates model roles so heavy reasoning stays on Gemini Pro while fast routing/summarization uses Flash.
05 / Outcome
Demonstrates reliable deep-research UX with human-in-the-loop clarifications, parallel subtopic exploration, and cited reports suitable for coursework assessment.