Agent orchestrationQualGent (YC X25)Software Engineer Intern2025Shipped

QualGent AI Assistant

One chat box for a QA team, with 45+ tools and sub-agents behind it.

45+ tools and sub-agents unified

Problem

QA teams had capability scattered across a dozen surfaces: test history in one place, tickets in another, app knowledge in a third.

Every question meant stitching them together by hand.

I built QualGent’s flagship assistant.

The interesting engineering was in routing, not generation: with that many tools available, picking the right three is the whole problem.

An enterprise QA copilot: one orchestrator in front of everything a QA engineer needs to ask about.

One orchestrator, forty-five tools, three routes taken

01
Gemini 2.5 Pro orchestrator on Google ADK, routing across 45+ tools and sub-agents with shared state management.
02
Tool surface spanning RAG retrieval, an MCP Postgres/pgvector Toolbox, and Jira and Linear through OAuth.
03
Deployed to Vertex AI Agent Engine via gated Cloud Build, so agent changes ship through the same review gate as code.

Gemini 2.5 Pro orchestrator on Google ADK

Became the primary way QA engineers at QualGent queried app knowledge, test history and issue trackers.

Google ADK · Gemini 2.5 Pro · Vertex AI · MCP · pgvector · Cloud Build

Built inside a company codebase, so there’s no public source to link. Happy to talk through the design.