Skip to main content
Back to challenges
Challenge

Build a Smart Nation Public Citizen Service Copilot with AutoGen and Vercel v0

Build a multi-agent citizen inquiry system for Singapore Smart Nation digital services. Using Microsoft AutoGen for multi-turn collaboration and Vercel v0 for dynamic frontend response generation, your copilot will resolve civic service queries and process form submissions with high compliance.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop an AutoGen multi-agent system styled with Vercel v0 interfaces to handle Singapore GovTech Smart Nation resident service requests.

Delivery guide

How work is evaluated

Evaluation

Evaluate multi-agent dialogue trajectory and proper routing of citizen requests to appropriate government service handlers.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

correct_agency_routing

Assigned agency matches Singapore government jurisdiction

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

intent_accuracy

Correct identification of civic workflow step • target: 0.9 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Orchestrate multi-agent interactions using AutoGen AssistantAgent and UserProxyAgent

  • Design citizen intent classification for Singapore Smart Nation service portals

  • Integrate Vercel v0 code generation for UI card rendering

  • Ensure adherence to GovTech digital service policy guidelines

Resources and assets

Reference links and supporting material

Dataset notes

Synthesized Singapore resident queries spanning public housing, identity management, and municipal services.

Challenge setup

Evaluate multi-agent dialogue trajectory and proper routing of citizen requests to appropriate government service handlers.

Challenge input

JSON containing resident query string

AutoGen

Microsoft framework for multi-agent delegation.

Vercel v0

Generates dynamic React/Tailwind frontend cards.

Evaluated output

JSON containing assigned_agency, workflow_step, and dynamic_ui_type

Evaluation checks
  • Assigned agency matches Singapore government jurisdiction
  • Correct identification of civic workflow step • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: GovTech_Citizen_QA_v1
  • Intent Accuracy target: 0.9
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • AutoGen · Required
  • Vercel v0 · Optional
Observation
  • Galileo · Optional
Reward / Eval
  • Galileo · Optional

Evaluation contract

  • correct_agency_routing · Weight 1
  • intent_accuracy · Weight 1

Metrics

  • intent_accuracy · Target 0.9

Benchmarks

  • GovTech_Citizen_QA_v1
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing resident query string

    Output: JSON containing assigned_agency, workflow_step, and dynamic_ui_type

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework
  • Vercel v0 · UI Generator

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Smart Nation Public Citizen Service Copilot with AutoGen and Vercel v0