Blog
Build next-generation cloud apps in the AI Partner Catalyst hackathon
Participant resources

Build next-generation cloud apps in the AI Partner Catalyst hackathon

Create innovative AI solutions with Google Cloud, Datadog, Confluent, and ElevenLabs in the AI Partner Catalyst hackathon on Devpost.

Text reads "Google Cloud's AI Partner Catalyst Hackathon" next to the Google Cloud logo

Push the boundaries of what’s possible in the cloud in the AI Partner Catalyst: Accelerate Innovation Hackathon. Google Cloud has teamed up with Datadog, Confluent, and ElevenLabs for a hackathon focused on AI, ML, and cloud technologies. This is your chance to build with Vertex AI, Gemini, and enterprise-grade infrastructure—plus integrate powerful partner platforms for observability, real-time data streaming, or conversational AI. 

In this post, we'll walk you through all the essentials: the key details you need to know, the innovative projects you'll be building, an overview of the available resources, and how to get started.

Key details

  • Submission period: November 17, 2025 to December 31, 2025
  • Total prize amount: $75,000
  • What to build: Develop a new application to tackle one of the partner challenges by combining Google Cloud’s advanced AI tools with the technologies of Datadog, Confluent, or ElevenLabs.
  • What to submit: Your submission should include a demo video (under 3 minutes), the URL to your hosted project, the URL to your code repository, and your completed Devpost submission form indicating which challenge you’re submitting for.

Let’s explore what this hackathon has in store for you and how to get started.

What you’ll build

This hackathon invites you to explore the capabilities of Google Cloud as you develop a project for one (or all three!) of the exciting partner challenges.

You’ll tap into powerful data analytics, secure storage, and enterprise-grade security while exploring curated and public datasets. This multi-partner hackathon means you'll have access to Google Cloud, Datadog, Confluent, and ElevenLabs’ platforms for your chosen project.

Here’s what you’ll do:

  1. Dive into Google Cloud: Use Vertex AI, Gemini, or other Google Cloud products as your foundation.
  2. Integrate partner tech: Choose Datadog, Confluent, or ElevenLabs and leverage their platforms.
  3. Solve a real challenge: Build a working application that addresses one of the three partner challenges.
  4. Ship it: Submit a functional project that demonstrates innovation and technical depth.

Now, let's explore the specific challenges and available resources from each partner.

{{callout-1}}

Datadog Challenge: End-to-end LLM observability

Datadog is the essential monitoring platform for cloud applications, bringing together data from servers, containers, databases, and third-party services to make your entire stack observable.

What to build

Build comprehensive monitoring for an LLM application powered by Vertex AI or Gemini.

Stream telemetry to Datadog, create detection rules, and design a dashboard that surfaces what matters—application health, performance signals, security indicators. When detection rules trigger, configure actionable items (cases, incidents, alerts) with enough context for engineers to respond effectively.

You have full access to Datadog for 14 days to explore the tooling and use it to build your project.

See all the details here.

Requirements for your Datadog project

Ready to dive into the Datadog challenge? Check out these requirements as you get started:

  • Provide an in-Datadog view that clearly shows your application health (e.g., latency/errors/tokens/cost), SLOs, and actionable items from the detection rules you defined.
  • Create an actionable record inside Datadog with clear contextual information to drive next steps. (Incident Management or Case Management)
  • Applications must leverage Vertex AI or Gemini as the model host.
  • Report your application telemetry data to Datadog (e.g., LLM observability signals, APM, logs, infrastructure metrics, RUM, etc.) using your preferred method (auto-instrumentation, SDKs, or API).
  • Define at least 3 detection rules in Datadog to evaluate application signals and determine when the app requires attention (e.g., monitors/SLOs).
  • Create an actionable record inside Datadog with clear contextual information to drive next steps (e.g., Signal Data, Runbook, context around the signal).

Datadog challenge resources

To help bring your project for the Datadog challenge to life, you have access to the following resources:

Confluent Challenge: AI on data in motion

Confluent is the data streaming platform built on Apache Kafka® that lets organizations stream, connect, process, and govern real-time data across clouds and on-premises environments.

What to build

Combine Confluent's data streaming platform with Google Cloud AI to build an application that processes real-time data streams. Apply ML models to streaming data for predictions, dynamic experiences, or novel problem-solving. Show how real-time data unlocks possibilities that batch processing can't touch. Think event-driven AI that responds as data flows.

See all the details here.

Inspiration for your Confluent project

To help you get started and spark your creativity, here are some examples to consider for your Confluent project:

  • Dynamic Pricing: Instantly adjust e-commerce prices based on competitor actions and surging real-time demand.
  • Fraud Detection: Block suspicious transactions before they are completed, not after.
  • Predictive Maintenance: Identify potential IoT failures from a live stream of sensor data, enabling proactive service.
  • Hyper-Personalized Gaming: An AI Dungeon Master adapts the story and environment in real-time based on your every move.

Show how your innovation can shape the future, as it happens, by building a next-generation application powered by AI on data in motion!

Confluent challenge resources

Ready to dive into Confluent? Here’s a summary of the resources available to you, and be sure to check out the full list on the hackathon’s Resources page.

ElevenLabs Challenge: Voice-first AI experiences

ElevenLabs is the AI voice and audio platform that enables high-quality speech synthesis, dubbing, speech recognition, and real-time conversational agents at scale.

What to build

Make your app conversational using ElevenLabs and Google Cloud AI. Integrate ElevenLabs Agents with Vertex AI or Gemini to create voice-driven interactions with natural speech and personality. Users should be able to interact entirely through voice. Implement using the React SDK or server-side calls hosted on Google Cloud—whatever fits your architecture.

Tip from a judge: Thor from ElevenLabs recommends exploring the Conversational AI and Voice Design Best Practices sections in the docs to create lifelike, engaging voice experiences.

See all the details here.

Inspiration for your ElevenLabs project

Check out these examples from ElevenLabs to help kickstart your project:

  • Voice-enabled chatbots powered by Gemini and ElevenLabs
  • Interactive video or media experiences built on GCP with real-time narration
  • AI-driven customer service or sales agents running on Vertex AI + ElevenLabs

ElevenLabs challenge resources

Ready to explore ElevenLabs? Check out the available solutions and resources for this hackathon.

Get started: Steps to join the AI Partner Catalyst Hackathon

Ready to start building? Here’s how to get started:

  1. Register for the hackathon on Devpost
  2. Get access to Google Cloud by signing up for a no-cost trial at https://cloud.google.com/free or using an existing Google Cloud account for which you may request $50 in Google Cloud credits by completing this form.
  3. Decide whether you’ll tackle the Datadog, Confluent, or ElevenLabs challenge—or all three!
  4. Start building and submit your completed project before December 31, 2025, at 2 p.m. PT

Ready to build? Join the AI Partner Catalyst Hackathon

Pick a challenge, assemble your tools, and start building! Registration is open now. Be sure to check the hackathon’s Resources tab for full challenge specifications and technical details.

We can’t wait to see what you ship!

Get hackathon news and updates on Discord.
Join the Devpost Discord