Learn

Practical guides to artificial intelligence

A practical guide connects concepts with a task you can complete and verify. These routes gather decisions about models, evaluation and implementation alongside related articles. Start with the problem closest to your project and move toward the foundations you need.

Learn by making a check

Define a small deliverable and preserve your starting point. Follow the process while noting assumptions, inputs and results. If a tool returns something unexpected, locate the failing stage before changing every parameter. Understanding why an example works helps you adapt it more thoughtfully than copying an entire configuration.

A concrete example

To try local AI, choose a task and measure the model on your equipment before buying hardware. To compare services, use the same sample and a simple rubric. To read a benchmark, identify what was measured and what lies outside the test.

What to check

Review each guide’s requirements, versions and limits. Avoid sensitive data in examples unless the environment is prepared. At the end, check the saved or executed result and record decisions you will need to revisit if the model changes.

Practical guides

Complete tours to resolve a specific decision.

LOCAL AI

How to choose a local model

Memory, quantization, context and speed without buying blindly.

Complete guide ASSESSMENT

How to read a benchmark

Dataset, metrics, conditions and limits before comparing results.

Method DECISION

How to compare models

A common table for capacities, prices and traceability.

Comparator
ANALYSIS

Related analysis

How to Choose, Quantize, and Evaluate a Local Language Model
GUIA

How to Choose, Quantize, and Evaluate a Local Language Model

A reproducible workflow for selecting a model, estimating memory, testing quantizations, and checking privacy and performance before deployment.

21 Oct 2026
Technical Validation Protocol for Local AI Models: From Download to Execution
GUIA

Technical Validation Protocol for Local AI Models: From Download to Execution

An operational guide to verifying the integrity, compatibility, and functionality of local language models before integrating them into production workflows.

20 Oct 2026
From Specification to Contract: Defining and Validating the Data Interface Between Your Application and an AI Model
GUIA

From Specification to Contract: Defining and Validating the Data Interface Between Your Application and an AI Model

A technical guide for designing robust interface contracts that guarantee the structural validity of AI model outputs, distinguishing format errors from content failures and establishing automatic validation protocols.

19 Oct 2026
From Model to Network: How to Expose a Local Inference Server Without Opening Random Doors
GUIA

From Model to Network: How to Expose a Local Inference Server Without Opening Random Doors

A practical guide to configuring network access for local inference servers such as Ollama, vLLM, and LM Studio. Learn how to manage bind addresses, firewalls, and authentication so you can share access over a local network or VPN without exposing the service to the internet.

19 Oct 2026
Evaluating Quantized Local Models: Measuring Quality and Speed on Your Hardware
GUIA

Evaluating Quantized Local Models: Measuring Quality and Speed on Your Hardware

A reproducible protocol to compare GGUF models and determine if their quality and performance are sufficient for a specific task, without assuming a single quantization is best for all cases.

18 Oct 2026
How to Audit AI-Generated SQL Before Using It
GUIA

How to Audit AI-Generated SQL Before Using It

A query can run without errors and still calculate a metric incorrectly. This protocol explains how to inspect joins, filters and aggregations, test in a controlled environment, and compare results with known references.

18 Oct 2026
GGUF, Quantization, and VRAM: Estimate the Memory Needed to Run Local Models
GUIA

GGUF, Quantization, and VRAM: Estimate the Memory Needed to Run Local Models

Q4_K_M, Q5_K_M, and Q8_0 alone do not tell you how much hardware you need. Learn to estimate weight memory, calculate the KV cache, and validate a setup with task-specific speed and quality tests.

18 Oct 2026
How to instrument an AI application to investigate failures, latency, and usage
GUIA

How to instrument an AI application to investigate failures, latency, and usage

A practical guide to logging each request and its stages without indiscriminately storing sensitive data. It covers an event schema, an instrumentation example, privacy criteria, diagnostic dashboards, and a process for investigating failures and distinguishing API-reported usage from final charges.

18 Oct 2026
Designing Safe Degradation: A Guide to AI Automations
GUIA

Designing Safe Degradation: A Guide to AI Automations

Learn how to define failure states, recovery policies, and acceptance tests that prevent duplicate effects in AI-powered automated workflows.

18 Oct 2026

Keep exploring

APIs and development Agent patterns Research explained
SourcesHugging Face Transformershuggingface.co