How to summarize long documents with AI without losing the important parts
A step-by-step method to get accurate summaries of reports, contracts and papers from any AI assistant, including how to check the result for missing facts.
AI Desk3 min read
Latent Daily · Guide
Guides & Tutorials
Step-by-step AI guides and tutorials for beginners, power users and developers.
22 stories RSS
Beginner's CornerGuide
What is generative AI? Text, images and audio explained simply
A plain-English introduction to generative AI: how chatbots and image generators create new content, what they are good at, and the mistakes to watch for.
AI Desk3 min read
Prompt EngineeringGuide
Few-shot prompting: how to teach an AI model with a handful of examples
Show, don't tell: how to use examples inside a prompt to get consistent formats, tone and classifications from any language model, with ready-to-use templates.
AI Desk3 min read
Prompt EngineeringGuide
Chain-of-thought prompting: getting better answers by asking for the reasoning
Why asking a model to reason step by step improves math and logic answers, how reasoning models changed the technique, and when it is not worth the extra tokens.
AI Desk3 min read
Cheat SheetsGuide
Cheat sheet: which kind of AI model to use for which task
A one-page decision guide: when to use a large model, a small one, a reasoning model, an open-weight model, an embedding model or a specialized model.
AI Desk4 min read
Cheat SheetsGuide
Prompting cheat sheet: 12 patterns that work with any AI assistant
Role, context, examples, format, constraints and self-checks: twelve reusable prompt patterns on a single page, each with a short template you can copy.
AI Desk4 min read
Math for AIGuide
The math behind AI: what you actually need to know
Linear algebra, calculus, probability and statistics: which parts of math matter for understanding and building AI, explained with intuition first.
AI Desk3 min read
Math for AIGuide
Gradient descent explained with one simple example
The algorithm that trains almost every AI model, explained with a hiker in the fog and a few lines of Python: gradients, learning rates and why training can fail.
AI Desk3 min read
AI CodingGuide
How to use AI coding assistants effectively: a practical workflow
Get better results from Copilot, Cursor, Claude Code and other coding assistants: give context, work in small steps, review every change and keep tests in the loop.
AI Desk3 min read
Agents & Agentic AIGuide
Model Context Protocol (MCP) explained: the "USB-C port" for AI tools
MCP is an open standard for connecting AI assistants to tools and data. How servers, clients and tools work, how to try it, and the security points to know.
AI Desk3 min read
APIs & SDKsGuide
Your first LLM API call: a step-by-step guide in Python
Set up an API key safely, send your first request to a language model in Python, understand messages, tokens and parameters, and handle errors and costs.
AI Desk3 min read
APIs & SDKsGuide
Structured outputs and function calling: getting reliable data from LLMs
How to make language models return valid JSON that matches a schema, how function calling works, and how to validate outputs so your application never breaks.
AI Desk3 min read
How retrieval-augmented generation (RAG) works, step by step
RAG lets AI answer from your documents. Each stage explained: ingestion, chunking, embeddings, retrieval, reranking, prompting and evaluation, with practical tips.
AI Desk3 min read
Vector databases explained: how they work and how to choose one
Embeddings, similarity search, indexes like HNSW and the trade-offs between pgvector, Pinecone, Weaviate, Qdrant, Milvus and Chroma for your RAG project.
AI Desk3 min read
Fine-tuning an LLM with LoRA: a practical overview
When fine-tuning helps, how LoRA and QLoRA make it affordable, how to prepare data, train, evaluate and deploy an adapter — and when not to fine-tune at all.
AI Desk3 min read
Local & On-device AIGuide
How to run a local LLM with Ollama: installation to first chat
Install Ollama, download an open model, chat in the terminal or a web interface, pick a model that fits your memory and use the local API from your own code.
AI Desk3 min read