Skip to main content
Back to challenges
Challenge

Deploy a Life Event Proactive Service Dispatcher with Mastra AI

Smart nation initiatives require seamless proactive service delivery when citizens reach major life milestones. Build a Mastra AI workflow that monitors life event triggers, checks eligibility across government agency APIs, and dispatches unified LifeSG support packages with 100% workflow execution reliability.

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.

Build a proactive public service delivery workflow using Mastra AI memory, agent tools, and step functions for LifeSG citizen milestones.

Delivery guide

How work is evaluated

Evaluation

Evaluates workflow step execution reliability and eligibility matching accuracy for citizen life events.

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

all_benefits_included

Checks that mandatory government grants are present in dispatch payload.

Binary check

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

Dimension 2

execution_reliability

Percentage of workflow steps completing without unhandled failures. • target: 1 • 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

  • Master Mastra AI TypeScript agent definitions and agent workflow steps

  • Utilize Mastra built-in memory and context persistence for long-running user milestones

  • Build proactive notification and eligibility verification tools

  • Ensure robust error handling and step retries in government service dispatch

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic citizen life event dataset containing birth, senior support, and housing milestone triggers.

Challenge setup

Evaluates workflow step execution reliability and eligibility matching accuracy for citizen life events.

Challenge input

JSON life event trigger (e.g., newborn registration)

Mastra AI

TypeScript-first AI framework with built-in memory, workflows, and tools.

Evaluated output

JSON dispatched support package summary with activated agency services

Evaluation checks
  • Checks that mandatory government grants are present in dispatch payload.
  • Percentage of workflow steps completing without unhandled failures. • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: GovServiceWorkflowBench
  • Execution Reliability target: 1
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Mastra AI · Required
  • Langchain · Optional
  • Sacred · Optional
Orchestration
  • Mastra AI · Required
  • Langchain · Optional

Evaluation contract

  • all_benefits_included · Weight 1
  • execution_reliability · Weight 1

Metrics

  • execution_reliability · Target 1

Benchmarks

  • GovServiceWorkflowBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON life event trigger (e.g., newborn registration)

    Output: JSON dispatched support package summary with activated agency services

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Deploy a Life Event Proactive Service Dispatcher with Mastra AI