Ai-Ml
Recent articles
Showing 24 of 71
Level 4: AI and Building
Production AI, vibe coding, and language models. How AI systems actually work in production, how to direct AI …For Product Managers
The AI vocabulary your team assumes you already have. Understand what engineers are building, evaluate …Tool Use (in Language Models)
The capability of a language model to invoke external tools: APIs, code execution, retrieval, computation: and …Structured Output
Constraining a language model to emit output that conforms to a specified schema (JSON, regex, grammar). The …Reasoning Models
Language models post-trained to allocate substantial inference-time compute to internal reasoning before …Prompt Caching
Server-side caching of attention key/value tensors for repeated prompt prefixes, reducing latency and cost for …Model Context Protocol (MCP)
An open protocol that standardises how language models connect to tools, data sources, and external systems …Mixture of Experts (MoE)
A neural network architecture in which only a small subset of parameters is activated for each input, enabling …LLM-as-a-Judge
Using a language model as an automated evaluator of another model's outputs: methodology, calibration with …LLM Routing
Architectures that direct each request to one of several available language models based on cost, capability, …Function Calling
Structured tool invocation by language models: how the model emits typed function calls, how runtimes execute …Direct Preference Optimization (DPO)
An alignment method that fine-tunes language models directly on preference data without training an explicit …Chain-of-Thought (CoT) Prompting
Eliciting intermediate reasoning steps from language models to improve performance on multi-step problems, …Agentic RAG
Retrieval-Augmented Generation systems in which the language model actively plans, queries, critiques, and …AI Systems Are Software Systems
Why production AI requires the same engineering discipline as any distributed system, and how this wiki covers …Prompt Engineering for Enterprise AI Applications
Practical prompt engineering patterns for production AI systems: system prompts, few-shot examples, …Model Versioning and Artifact Management
Why model versioning matters and how to implement it: S3 for artifacts, Git for configuration, SageMaker Model …Amazon Translate - Neural Machine Translation
Using Amazon Translate for real-time and batch document translation in multilingual AI applications.Amazon Polly - Text-to-Speech for Applications
Using Amazon Polly to generate natural-sounding speech from text in AI applications, with SSML control and …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 …Vector Database
What vector databases are, how they enable semantic search, popular options including Pinecone, Weaviate, and …Tokenization in AI
What tokens are, how different models tokenize text, why token count matters for cost and context limits.Text-to-Speech (TTS)
What text-to-speech technology is, how AWS Polly, Azure Speech, and GCP Text-to-Speech compare, and key …Speech-to-Text (STT)
What speech-to-text technology is, how AWS Transcribe, Azure Speech, and GCP Speech-to-Text compare, and key …
71 articles in this section. Search for a specific topic.
Open source projects