Learn to build AI-powered applications using AWS PartyRock, Amazon Kiro, and Amazon Bedrock. Register, train, and submit your capstone project for the competition.
Target: Thai citizens 18+ | Timeline: AugโDec 2026
Fill in your details below to register for the CPG-TDA AI Innovation Hackathon with AWS. All fields marked * are required.
| Registration Opens | 26 August 2026 |
| Registration Closes | 11 September 2026 |
| Training Period | 14 Sep โ 26 Oct 2026 |
| Submission Deadline | 6 November 2026 |
| Top 20 Bootcamp | 18โ20 November 2026 |
| Awards Ceremony | 10 December 2026 |
AWS PartyRock is a no-code generative AI app builder powered by Amazon Bedrock. It allows you to create AI applications without writing any code โ perfect for rapid ideation and prototyping.
Visit partyrock.aws and sign in with your Google, Apple, or Amazon account.
Browse the gallery to see what others have built. Get inspiration!
Describe what you want to build in plain English. PartyRock generates the app structure automatically.
Let's build a simple disaster alert generator as an example:
PartyRock creates an app with:
| Widget Type | What It Does | Use Case |
|---|---|---|
| User Input | Text field for user to type | Location, topic, question |
| Text Generation | AI generates text based on prompt | Analysis, recommendations, summaries |
| Image Generation | AI creates images from text | Visualizations, diagrams, mockups |
| Chatbot | Interactive conversation with AI | Q&A assistant, advisor |
Input: Thai province โ Output: flood risk level, historical data, evacuation recommendations, emergency contacts
Input: crop type + symptoms โ Output: likely disease, treatment steps, prevention tips
Input: symptoms in Thai โ Output: possible conditions, urgency level, nearby clinics
Input: subject + exam date โ Output: personalized study schedule, key topics, practice questions
Input: location + activity type โ Output: air quality assessment, health recommendations, best times for outdoor activity
Amazon Kiro is an AI-powered development environment that writes code for you. Think of it as a programming partner that understands natural language and can build full applications from your descriptions.
Download from kiro.dev, run the installer, and sign in with your AWS Builder ID (free).
Open Kiro โ File โ New Workspace โ Choose a folder for your hackathon project.
Open the chat panel and describe your project. Kiro will ask clarifying questions and start building!
Let's build a disaster alert dashboard as an example for the hackathon:
Kiro will:
Steering files are rules that Kiro follows every time you interact with your project. Write them once, and Kiro always remembers โ no need to repeat yourself.
Kiro creates steering files that ensure every new feature you add automatically follows these rules โ consistent colors, bilingual text, mobile-responsive layout, and the correct tech stack.
For complex features, use Kiro's Spec mode โ it breaks down your idea into requirements โ design โ implementation tasks, then builds each piece systematically.
Amazon Bedrock is a fully managed service that offers high-performing foundation models (FMs) from leading AI companies through a single API. It's the production-grade AI backbone for your application.
| Model | Provider | Best For |
|---|---|---|
| Claude 3.5 Sonnet | Anthropic | Complex reasoning, coding, analysis |
| Claude 3 Haiku | Anthropic | Fast responses, chat, simple tasks |
| Llama 3 | Meta | General text, multilingual (Thai) |
| Titan Text | Amazon | Summarization, search, embeddings |
| Titan Image | Amazon | Image generation & editing |
| Stable Diffusion XL | Stability AI | High-quality image generation |
AWS will provide temporary access to Bedrock during the finalist development phase (23โ27 Nov). You'll receive:
Use the credentials provided by the hackathon organizers
Search "Bedrock" in the AWS Console โ Click "Amazon Bedrock"
Go to "Model access" โ Request access to the models you need
Use the Playground to test prompts, then integrate via API
The Playground lets you test different models and prompts before writing any code:
Test your prompts in the Playground, then refine them before integrating into your application code. This saves time and API costs.
Use the AWS SDK to call Bedrock from your application (Kiro can help you write this code):
Kiro will:
During this 5-day sprint, you'll upgrade your prototype to a production-ready MVP using Bedrock:
The CPG-TDA AI Innovation Hackathon challenges you to build an AI-powered solution addressing Thailand's most pressing challenges. Your capstone project demonstrates your ability to apply Generative AI to real-world problems.
AI solutions for Thailand's pressing challenges. Focus areas include:
Complete Gen AI foundational training. Learn PartyRock, Kiro basics, and AI concepts.
Build your capstone project on AWS PartyRock. Submit your app URL + project description.
AI-automated scoring selects Top 20 teams based on judging criteria.
Top 20 teams attend 3-day bootcamp at CPG-TDA venue. Build prototypes with Amazon Kiro. Present at Demo Day.
Top 5 teams develop MVPs with Amazon Bedrock, mentored by AWS Solutions Architects.
Final pitches to judges. Winners announced! ๐
| 1. PartyRock App URL | Your published, working PartyRock application |
| 2. Project Title | Clear, descriptive name for your solution |
| 3. Problem Statement | What Thai challenge does this solve? (200 words max) |
| 4. Solution Description | How does your AI app address the problem? (300 words max) |
| 5. Target Users | Who benefits from this solution? |
| 6. Demo Video | 2-minute video showing your app in action (optional but recommended) |
| 7. Team Info | Team members, roles, university/organization |
| Criteria | Weight | What Judges Evaluate |
|---|---|---|
| Problem Relevance | 25% | Is this a real, significant Thai challenge? Clear problem definition? |
| AI Innovation | 25% | Creative use of Gen AI? Meaningful AI integration (not superficial)? |
| Feasibility & Impact | 20% | Can this be built? Would it actually help people if deployed? |
| User Experience | 15% | Is it intuitive? Good design? Accessible to target users? |
| Presentation | 15% | Clear explanation? Compelling demo? Team collaboration? |
เธฟ250,000
+ Incubation Opportunity + AWS Certification Vouchers + Amazon Echo/Kindle + Media Exposure
เธฟ150,000
+ AWS Certification Vouchers + Amazon Echo
เธฟ100,000
+ AWS Certification Vouchers
| Problem | Thailand loses เธฟ50B+ annually to floods. Rural communities get warnings too late to evacuate safely. |
| Solution | AI-powered flood prediction using weather data + river sensors. Sends alerts in Thai via LINE/SMS 6-12 hours before flooding. |
| AI Usage | Claude analyzes weather patterns + historical data โ generates risk assessment + personalized evacuation routes. |
| Target Users | Rural Thai communities in flood-prone provinces (Ayutthaya, Nakhon Sawan, Ubon Ratchathani). |
| Impact | Earlier warnings = more evacuation time = fewer casualties and property damage. |