AI Systems Are Software Systems
Why production AI requires the same engineering discipline as any distributed system, and how this wiki covers the full stack of AI …
Ai-Ml
Prompt Engineering for Enterprise AI Applications
Practical prompt engineering patterns for production AI systems: system prompts, few-shot examples, chain-of-thought, structured output, …
Amazon Polly - Text-to-Speech for Applications
Using Amazon Polly to generate natural-sounding speech from text in AI applications, with SSML control and neural voice options.
Amazon Translate - Neural Machine Translation
Using Amazon Translate for real-time and batch document translation in multilingual AI applications.
Model Versioning and Artifact Management
Why model versioning matters and how to implement it: S3 for artifacts, Git for configuration, SageMaker Model Registry, Bedrock model …
AI for Citizen Services - Modernizing Government Interactions
Chatbot-based citizen inquiries, form pre-filling, status tracking, and multilingual support for government agencies.
AI for Clinical Data Analysis
Practical AI applications for clinical data analysis: extracting insights from unstructured clinical notes, supporting documentation, and …
AI for Environmental Monitoring and Compliance
Air and water quality monitoring, pollution detection, compliance reporting, and satellite-based environmental tracking with AI.
AI for Financial Compliance Automation
KYC/AML screening, transaction monitoring, regulatory reporting, and audit trail generation for financial services.
AI for Insurance Claims Processing
Automated claims intake, fraud detection, and document extraction for insurance operations - from first notice of loss to payment …
AI for Medical Imaging Analysis
Radiology assistance, pathology screening, imaging quality assessment, and clinical decision support using AI.
AI for Power Grid Optimization
Load balancing, renewable energy integration, demand forecasting, and smart grid management with AI.
AI for Recruitment and Talent Screening
How AI assists recruitment teams with resume screening, candidate matching, and interview scheduling - with guidance on bias mitigation and …
AI for Satellite Data and Geospatial Intelligence
Using multi-agent AI systems to query and analyze satellite imagery and geospatial data through natural language, with public data sources …
AI for Supply Chain Optimization
AI applications in supply chain: demand forecasting, inventory optimization, route planning, and disruption detection - with practical …
AI Fraud Detection for Financial Services
Real-time transaction scoring, anomaly detection, behavioral biometrics, and investigation prioritization for financial fraud prevention.
AI Predictive Maintenance for Energy Infrastructure
Sensor data analysis, failure prediction, maintenance scheduling, and cost optimization for energy infrastructure operators.
AI Quality Control in Manufacturing
How computer vision AI enables automated visual inspection in manufacturing - detecting defects, reducing false positives, and integrating …
AI Spark: AI-Assisted Document Review for Legal Teams
How AI can reduce contract review time by surfacing non-standard clauses, missing provisions, and high-risk language - a practical build …
AI Spark: Auto-Classify and Route Incoming Emails
Use AI to classify incoming emails by type, urgency, and intent, then route them to the right team or workflow automatically.
AI Spark: Automate Invoice Processing in 3 Steps
A practical AI spark for automating invoice data extraction - the problem, the approach, and a three-step build path.
AI Spark: Never Write Meeting Notes Again
Automate meeting summaries and action item extraction using transcription and LLM post-processing - a practical three-step build.
Amazon Bedrock - Enterprise AI Foundation
A comprehensive reference for Amazon Bedrock: available models, key features, use cases, and pricing patterns for enterprise teams.
Amazon Bedrock vs Azure OpenAI - Which to Choose?
A practical comparison of Amazon Bedrock and Azure OpenAI Service for enterprise AI deployments, covering model selection, pricing, …
Amazon Comprehend - NLP at Scale
Sentiment analysis, entity extraction, topic modeling, and language detection with Amazon Comprehend. When to use Comprehend vs Bedrock for …
Amazon Rekognition - Image and Video Analysis
What Rekognition does, which features work well in enterprise applications, accuracy considerations, pricing, and common integration …
Amazon SageMaker - Custom ML Model Training and Deployment
What SageMaker is, when to use it instead of Bedrock, key capabilities, pricing model, and the workflows that suit it best.
Amazon SageMaker vs Bedrock - Build vs Buy
When to use SageMaker for custom ML versus Bedrock for managed foundation models - a practical comparison for enterprise AI teams.
Amazon Textract - Document Data Extraction
A reference guide to Amazon Textract: OCR capabilities, table and form extraction, query-based extraction, and integration patterns for …
Amazon Transcribe - Speech-to-Text for Enterprise
Amazon Transcribe capabilities, accuracy characteristics, pricing, and the integration patterns that work well for enterprise transcription …
Case Pattern: Automated Content Generation for a News Agency
How a news agency automated structured report generation from data feeds - producing hundreds of articles per day from financial, sports, …
Case Pattern: Building a Geospatial AI Platform from Public Data
How a team built a geospatial intelligence platform combining satellite imagery, public datasets, and AI analysis to generate location-based …
Case Pattern: Insurance Claims Modernization with AI
Architecture and lessons from modernizing an insurance claims processing workflow using AI for document extraction, fraud detection, and …
Claude by Anthropic - Enterprise AI Assistant
What makes Claude useful for enterprise applications, model tiers, key strengths, access options including through Amazon Bedrock, and …
Claude vs GPT - Choosing an Enterprise LLM
A practical comparison of Anthropic Claude and OpenAI GPT for enterprise applications - capability differences, access options, compliance …
Computer Vision
What computer vision is, how it works in AI applications, and how AWS Rekognition, Azure Computer Vision, and GCP Vision AI compare.
Context Window Management Patterns
Summarization, sliding window, retrieval-augmented, and hierarchical context patterns for handling conversations and documents that exceed …
Custom ML Models vs Foundation Models - When to Build vs Buy
SageMaker custom training vs Bedrock foundation models. Data requirements, cost, accuracy trade-offs, and maintenance burden.
Daily AI Sparks - One Automation Idea Per Day
How the Daily AI Sparks series works and how to use short automation ideas to find your first AI quick win.
Embeddings - Vector Representations for AI Search
What embeddings are, how they enable semantic search, which embedding models to use, and how to choose vector database infrastructure.
Fine-Tuning vs Prompt Engineering vs RAG
The three main approaches to customizing LLM behavior for specific use cases - when each is appropriate and how they compare.
Foundation Models
What foundation models are, how they differ from task-specific models, the major model families, and the practical implications for …
Getting Started with Amazon Bedrock for Enterprise AI
A practical introduction to Amazon Bedrock: what it is, which models are available, how pricing works, and how to get your first use case …
GIS and AI Architecture on AWS
How to combine geospatial data processing (GeoPandas, Shapely, satellite imagery) with AI services (Bedrock, OpenSearch) for natural …
Inference - Running AI Models in Production
What inference means in AI context, the key operational parameters that matter (latency, throughput, cost), and the main deployment options …
Intelligent Document Processing with AI
A practical architecture for extracting structured data from invoices, contracts, and forms - combining OCR, classification, and LLM-based …
LLM - Large Language Model
What large language models are, how they work at a high level, key characteristics, and what they can and cannot do reliably.
Model Cards - AI Transparency Documentation
What model cards document, why they matter for AI governance, and how to create one.
Prompt Engineering
What prompt engineering is, why it matters in enterprise AI applications, and the most effective techniques for getting reliable outputs …
Prompt Engineering Patterns for Enterprise Applications
Proven prompt patterns for enterprise AI applications: structured output, chain-of-thought, few-shot examples, guardrails, and system prompt …
RAG - Retrieval Augmented Generation
What RAG is, how it works, when to use it, and the common implementation pitfalls that reduce retrieval quality.
RAG vs Fine-Tuning - When to Use Each
A practical framework for deciding between retrieval augmented generation and fine-tuning to customize LLM behavior for enterprise …
Speech-to-Text (STT)
What speech-to-text technology is, how AWS Transcribe, Azure Speech, and GCP Speech-to-Text compare, and key features like speaker …
Text-to-Speech (TTS)
What text-to-speech technology is, how AWS Polly, Azure Speech, and GCP Text-to-Speech compare, and key features like neural voices and …
Tokenization in AI
What tokens are, how different models tokenize text, why token count matters for cost and context limits.
Vector Database
What vector databases are, how they enable semantic search, popular options including Pinecone, Weaviate, and pgvector, and when to use …
Why Your AI Output Sounds Generic - And How to Fix It With Your Own Data
The difference between prompting and grounding. Five stages from zero context to production-ready assets. The Personal Inference Pack …