Skip to main content
Back to challenges
Challenge

Enterprise Calendar and Email Agent with Claude Sonnet 4.6.6 and Google ADK

Construct an agentic application using Google ADK that manages enterprise productivity tasks such as email filing and calendar synchronization. This challenge focuses on utilizing the Claude Sonnet 4.6.6 model for nuanced instruction following and task prioritization. The development process involves using Lovable to prototype the interface, routing API requests through OpenRouter for model flexibility, and integrating Bito AI to assist with rapid code generation and debugging. The system utilizes Vellum for managing and versioning the complex prompt chains required for enterprise calendar orchestration.

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 intelligent agentic assistant using Google ADK and Claude Sonnet 4.6.6 to streamline calendar and email management workflows.

Delivery guide

How work is evaluated

Evaluation

Evaluation of calendar scheduling logic

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

Availability Check

Detects conflicts

Binary check

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

Dimension 2

Success Rate

Percentage of correctly parsed events • 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

  • Master Google ADK patterns for multimodal input processing and agentic tool use

  • Design robust prompt management pipelines using Vellum for model versioning

  • Configure OpenRouter to optimize inference costs and latency for agent tasks

  • Implement interface components using Lovable to visualize agent-managed schedules

  • Use Bito AI for accelerating the development of tool-calling functions for Gmail and Calendar APIs

  • Implement error handling for long-running agent processes within Google ADK

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

Evaluation of calendar scheduling logic

Challenge input

Email raw text

Google ADK

Agent Development Kit for

Google

Google AI model provider

OpenRouter

Unified model API and router.

Evaluated output

Calendar event object

Evaluation checks
  • Detects conflicts
  • Percentage of correctly parsed events • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Success Rate target: 90%
  • 1 public reference case
Configured runtime
  • JavaScript execution harness

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
  • Google ADK · Required
  • Google · Optional
Policy Serving
  • OpenRouter · Optional
Orchestration
  • OpenRouter · Optional

Evaluation contract

  • Availability Check · Weight 1
  • Success Rate · Weight 1

Metrics

  • Success Rate · Target 0.9

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Email raw text

    Output: Calendar event object

    Execution harness: JavaScript

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Enterprise Calendar and Email Agent with Claude Sonnet 4.6.6 and Google ADK