Skip to content
Adarsh Dwivedi.AI & Product Engineer
02Work

Travel Planner Agent

Five Generations of a Multi-Agent Planner

Travel Planner Agent running: Five Generations of a Multi-Agent Planner.

Captured from the live deployment, not a mockup

01 · The problem

Built five successive generations of the same planner, linear, parallel, orchestrator, human-in-the-loop and an MCP factory graph, keeping every generation runnable so the architectural trade-offs can be compared rather than argued about.

02 · How it works

  • 01

    Served all five concurrently through Aegra on AWS Bedrock with a standalone MCP server exposing 10 travel tools, and covered the backend with 630 tests against a real Postgres.

03 · What it cost, and what it returned

Wired live Playwright browser automation the user can take over mid-run, so the agent hands control back at exactly the point where a human should decide.