Teserax - Graph-Based Research Agent
Solo-built production TypeScript SaaS research agent that turns linear LLM chat into a graph-based exploration space with branching, synthesis, tool calling, RAG over live web sources, async orchestration, typed API contracts, and graceful failure recovery.
What this project proves
Solo-built graph-based research agent
Live TypeScript SaaS research agent with graph-based exploration, tool calling, live-source RAG, async orchestration, typed contracts, and graceful failure recovery.
Core challenge
Turn linear LLM chat into a non-linear research workflow that can branch, synthesize, and recover from long-running AI task failures.
Evaluation lens
Graph UX, tool-calling orchestration, live-source retrieval, typed APIs, and production deployment.
A live public SaaS product that combines research-agent behavior with a visual graph workflow.
Overview
Teserax is a solo-built production SaaS research agent and graph-based thinking tool. The live product turns linear LLM chat into a visual, non-linear exploration space where users can branch into parallel lines of inquiry, merge or summarize findings, and synthesize insights on an interactive canvas.
The current resume describes Teserax as a TypeScript SaaS research agent with multi-step orchestration, tool calling, RAG over live web sources, typed API contracts, async workflows, retry behavior, and failure recovery. The live site metadata reinforces the graph-based interaction model: the product is not just an API wrapper, but a workflow surface for non-linear research and analysis.
What I Owned
- Designed and shipped the product end to end as a solo project.
- Built the graph-based UX for branching, merging, summarizing, and cross-linking AI responses.
- Implemented multi-step agent orchestration with tool calling and retrieval over live web sources.
- Used Zod-typed API contracts to keep frontend/backend behavior explicit and testable.
- Added async workflow handling, retries, and graceful degradation for long-running AI tasks.
- Deployed and operated the live product at teserax.vercel.app.
Hard Problems Solved
- Research is non-linear: long-form analysis often branches and recombines. Teserax models that directly as a graph instead of forcing every interaction into a single chat transcript.
- Agent steps need structure: tool calling, RAG, retries, and async work require typed boundaries so failures are recoverable rather than confusing.
- Live-source context changes: retrieval over web sources needs graceful degradation when sources are unavailable, slow, or incomplete.
- Solo product ownership: the project required product design, frontend engineering, backend orchestration, deployment, and operational judgment in one system.
Key Features
- Graph-Based Exploration: Branch, merge, summarize, cross-link, and rewrite research paths on an interactive canvas.
- Agentic Research Flow: Multi-step orchestration with tool calling and RAG over live web sources.
- Typed API Contracts: Zod schemas keep request/response behavior explicit across the stack.
- Async Orchestration: Long-running research flows use retries and failure-recovery behavior for graceful degradation.
- Production Deployment: Live SaaS surface deployed publicly and linked from the current resume.
Why It Matters
Teserax is the clearest current proof of solo AI product engineering in the portfolio. It connects an interaction design idea, a graph-based product model, and agentic backend infrastructure into a live system that users can actually try.
Tech Stack
- Frontend: TypeScript, React, graph-based interaction UI
- Backend / AI: FastAPI, tool calling, RAG, async agent orchestration
- Contracts: Zod typed schemas
- Infrastructure: EC2, Cloudflare, Vercel deployment surface