Skip to content
Behind the Scenes

How this site's AI actually works

Every AI feature on this site is powered by real AWS infrastructure. Explore the architecture, services, and technical flows behind each one.

Sheet 01 AI Playground

Describe it. Watch it build.

Type a plain-English description of any UI component and watch AI generate production-ready HTML + Tailwind CSS in real time. Supports multi-turn conversations to refine and iterate on your component.

Try it

How It Works

Your prompt is sent to an API Gateway endpoint backed by a Lambda function. The Lambda calls Amazon Bedrock with Claude, streaming tokens back through a chunked HTTP response. The frontend renders each chunk into a live preview iframe as it arrives.

Technical Flow

01

User types a component description in the browser

02

Request hits API Gateway with rate limiting (10/day per IP)

03

Lambda constructs a system prompt optimized for HTML/Tailwind generation

04

Amazon Bedrock streams Claude's response token-by-token

05

Frontend renders each chunk into a sandboxed iframe in real time

06

Conversation history is maintained client-side for multi-turn refinement

AWS Services

Amazon Bedrock
LLM inference with Claude
AWS Lambda
Serverless request handler
API Gateway
REST endpoint with throttling
CloudWatch
Logging and monitoring
Sheet 02 Tech Stack Advisor

Describe your project. Get your stack.

Describe your project requirements and get AI-powered architecture recommendations with a complete tech stack, reasoning, and a Mermaid architecture diagram. Follow up with questions to refine the recommendations.

Try it

How It Works

The Lambda function sends your project description to Claude via Bedrock with a specialized system prompt that instructs the model to analyze requirements, recommend technologies, and generate a Mermaid diagram. Responses stream back with a special marker format for the diagram section.

Technical Flow

01

User describes their project requirements

02

Lambda sends the prompt to Bedrock with architecture-focused system instructions

03

Claude analyzes requirements and generates structured recommendations

04

Response includes a Mermaid diagram between ---DIAGRAM--- markers

05

Frontend renders markdown recommendations and loads Mermaid.js for the diagram

06

Follow-up questions maintain conversation context for deeper analysis

AWS Services

Amazon Bedrock
Architecture analysis with Claude
AWS Lambda
Prompt orchestration
API Gateway
REST endpoint with rate limiting
CloudWatch
Request logging
Sheet 03 AI Agent Visualizer

Watch AI think step-by-step.

Select a scenario (code review, data analysis, deployment, bug fix) and watch an AI agent break down the problem, plan a solution, execute steps, and verify results — all streamed live to a terminal-style interface.

Try it

How It Works

The Lambda receives a scenario ID, constructs a multi-step prompt chain, and calls Bedrock for each agent phase (think → plan → execute → verify → result). Each phase's output is streamed as newline-delimited JSON, with the frontend updating the pipeline visualization in real time.

Technical Flow

01

User selects a predefined scenario (e.g., 'Code Review')

02

Lambda receives the scenario and initiates a multi-phase prompt chain

03

Each phase (Think, Plan, Execute, Verify, Result) calls Bedrock independently

04

Responses stream as NDJSON with step metadata

05

Frontend highlights the active pipeline step and appends terminal output

06

Rate limiting tracks daily usage per IP

AWS Services

Amazon Bedrock
Multi-step agent reasoning
AWS Lambda
Agent orchestration
API Gateway
Streaming endpoint
CloudWatch
Step-level tracing
Sheet 04 AI Chat Assistant

Ask anything about creative-it.

A floating chat widget that answers questions about creative-it's services, process, team, and capabilities. Maintains session context for natural follow-up conversations with streaming responses.

How It Works

The Lambda uses a Bedrock Knowledge Base backed by an S3 bucket of curated company documents. When a user asks a question, it performs RAG (Retrieval-Augmented Generation) — retrieving relevant chunks from the knowledge base, then generating a grounded answer with Claude. Session IDs enable multi-turn conversations.

Technical Flow

01

User types a question in the floating chat widget

02

Request includes a session ID for conversation continuity

03

Lambda queries the Bedrock Knowledge Base for relevant document chunks

04

Retrieved context is injected into Claude's prompt (RAG pattern)

05

Claude generates a grounded answer, streamed back to the widget

06

Session state persists across messages for follow-up questions

AWS Services

Amazon Bedrock
LLM inference + Knowledge Bases
Amazon S3
Document storage for RAG
AWS Lambda
Query orchestration
API Gateway
Chat endpoint with session tracking
Sheet 05 Website Remix

Restyle this site with AI.

Type a visual theme (e.g., 'retro 80s neon' or 'minimalist monochrome') and AI generates custom CSS that transforms the entire site's look in real time. Reset anytime to return to the original.

How It Works

The Lambda sends your theme description to Claude with a system prompt containing the site's CSS custom properties and design token structure. Claude generates override CSS that targets the existing theme variables. The frontend injects the CSS as a <style> tag, instantly restyling the page.

Technical Flow

01

User types a theme description (e.g., 'warm earthy tones')

02

Lambda sends the prompt with the site's CSS variable schema

03

Claude generates CSS overrides targeting theme custom properties

04

Response streams with CSS between ---CSS--- markers

05

Frontend extracts the CSS and injects it as a <style> element

06

A banner appears with a reset button to restore the original theme

AWS Services

Amazon Bedrock
CSS generation with Claude
AWS Lambda
Theme prompt handler
API Gateway
Remix endpoint
Sheet 06 Live Translation

Read this site in 25+ languages.

Click any language flag and the entire page is translated in place — headlines, paragraphs, buttons, and all. Translations are context-aware and preserve formatting. Reset to return to English anytime.

How It Works

The frontend collects all translatable text nodes from the DOM, batches them (50 per request), and sends them to a Lambda that calls Claude with translation-specific prompts. Claude returns a JSON array of translated strings, which the frontend applies back to the corresponding DOM elements.

Technical Flow

01

User clicks a language flag (e.g., German, Japanese)

02

Frontend traverses the DOM and collects text from translatable elements

03

Original text is stored in a Map for later reset

04

Texts are batched (50 per request) and sent to the translation Lambda

05

Claude translates the batch while preserving formatting and context

06

Translated strings are applied to DOM elements; a banner shows active language

AWS Services

Amazon Bedrock
Context-aware translation with Claude
AWS Lambda
Batch translation handler
API Gateway
Translation endpoint
Sheet 07 Agentic Coding Stats

Live GitHub activity from AI agents.

Displays real-time GitHub statistics — commits, lines changed, and a 7-day activity chart — from my organization's repositories. An AI-generated narrative summarizes the day's development activity.

Try it

How It Works

Two Lambda functions power this feature. The stats Lambda queries the GitHub API for commit and diff data across all org repos, caching results in DynamoDB with TTL. The story Lambda takes the stats and sends them to Claude, which generates a creative narrative about the day's coding activity.

Technical Flow

01

Page loads and fetches /github-stats from the API

02

Stats Lambda checks DynamoDB cache (5-minute TTL)

03

On cache miss, Lambda queries GitHub API for org-wide commit data

04

Stats are aggregated (24h, 7d) and history points are stored

05

Frontend renders stats cards and draws a Canvas-based activity chart

06

Story Lambda sends stats to Claude for a narrative summary

AWS Services

Amazon Bedrock
AI story generation with Claude
Amazon DynamoDB
Stats caching with TTL
AWS Lambda
GitHub API integration + story generation
API Gateway
Stats and story endpoints
Sheet 08 Cloud Cost Check

What does your cloud really cost?

Describe any system — cloud-based or on-premise — and get a realistic monthly AWS cost estimate as ranges, plus what a serverless redesign of the same workload would cost and save.

Try it

How It Works

A Lambda function sends your description to Claude via Bedrock with a cost-consultant system prompt grounded in eu-central-1 list prices. The model states its assumptions explicitly, estimates per-service costs, and calculates the serverless savings potential. The response streams back token-by-token.

Technical Flow

01

User describes their system and workload

02

Lambda forwards the description to Bedrock with cost-analysis instructions

03

Claude derives assumptions (traffic, storage, region) and lists them transparently

04

Per-service estimates and a serverless comparison stream back as markdown

05

Follow-up questions refine the estimate using conversation context

AWS Services

Amazon Bedrock
Cost reasoning with Claude
AWS Lambda
Streaming request handler
Amazon DynamoDB
Per-IP rate limiting
CloudFront
Streaming edge endpoint
Sheet 09 EU AI Act Check

Which risk class is your AI?

Describe an AI use case and get a first assessment under the EU AI Act (Regulation (EU) 2024/1689): risk classification with the relevant articles, your obligations, GDPR touchpoints, and practical next steps.

Try it

How It Works

The Lambda sends your use case to Claude with a compliance-analyst system prompt. The model starts its response with a machine-readable risk marker that the frontend turns into a colored badge, followed by the streamed assessment. Every response ends with a not-legal-advice note.

Technical Flow

01

User describes their AI use case

02

Lambda forwards it to Bedrock with AI-Act-classification instructions

03

Claude classifies the case (prohibited / high / limited / minimal / unclear)

04

A ---RISK--- marker at the start of the stream drives the badge in the UI

05

Obligations, GDPR touchpoints, and next steps stream back as markdown

AWS Services

Amazon Bedrock
Regulatory reasoning with Claude
AWS Lambda
Streaming request handler
Amazon DynamoDB
Per-IP rate limiting
CloudFront
Streaming edge endpoint
Sheet 10 Model Compare

One prompt. Three models.

Sends the same prompt to three model families on Amazon Bedrock — always the latest available generations of Claude Sonnet, Claude Haiku, and Amazon Nova Lite — and shows their answers side by side with latency, token usage, and approximate cost per call.

Try it

How It Works

The Lambda uses Bedrock's Converse API, which normalizes requests across model vendors, and invokes all models in parallel. Each result is written to the response as a newline-delimited JSON event the moment that model finishes, so the fastest model appears first in the UI.

Technical Flow

01

User enters a single prompt

02

Lambda invokes all three models in parallel via the Converse API

03

Each model's latency and token usage are measured per call

04

Cost is computed from on-demand list prices per 1K tokens

05

Results stream back as NDJSON events and fill their column as they arrive

AWS Services

Amazon Bedrock
Multi-model inference via Converse API
AWS Lambda
Parallel invocation + NDJSON streaming
Amazon DynamoDB
Per-IP rate limiting
CloudFront
Streaming edge endpoint
Sheet 11 Architecture

The Full Stack

All AI features run on a serverless AWS architecture. Here's every service involved, grouped by layer.

AI / ML Layer

Amazon Bedrock

Managed LLM inference with Claude — powers all AI features

Bedrock Knowledge Bases

RAG pipeline for the chat assistant's document retrieval

Compute Layer

AWS Lambda

Serverless functions for every API endpoint — zero idle cost

API Gateway

REST APIs with throttling, CORS, and custom domain mapping

Data Layer

Amazon DynamoDB

Low-latency caching for GitHub stats and rate limiting

Amazon S3

Document storage for the knowledge base and static assets

Networking & Orchestration

Amazon CloudFront

CDN for the static Astro site and asset delivery

AWS CDK

Infrastructure as code — the entire stack defined in TypeScript

Amazon CloudWatch

Centralized logging, metrics, and alerting across all Lambdas

AWS IAM

Fine-grained permissions between services

Want This for Your Product?

Every feature on this site is built with the same tools and patterns I use for client projects. Let's build something intelligent together.

Start a Conversation
Ask AI Remix Translate