Technical practice, explained.

How to run an LLM on your own server: Ollama, llama.cpp and vLLM compared

GUIDE · 7 MIN READ

Running a language model on hardware you control means prompts and documents never leave your building, the cost is the hardware…

Small language models explained: when smaller beats bigger

A small language model (SLM) is a language model small enough to run on modest hardware, such as one workstation, a phone or an e…

TPBOK

What is the TPBOK? The Technical Practitioner Body of Knowledge, explained

The TPBOK, the Technical Practitioner Body of Knowledge, is the written standard behind every IICTP exam. It describes what a tec…

The technical practitioner career path: from Associate to Portfolio level

A credential ladder is only useful if each step matches a real change in the work. IICTP’s four core credentials are built around…

How to prepare for a scenario-based certification exam

A scenario-based exam does not ask you to recall a definition. It describes a situation and asks what you would do. That changes…

How employers verify a certification, and why a public registry matters

A certificate is a claim. Anyone can type a credential onto a CV, and a PDF is easy to alter. Verification is the step that turns…

Digital badges and verifiable credentials, explained

A digital badge is a credential in a form that travels: it can be shared on a profile, checked by a machine and revoked by the is…

Technical practitioner interview questions, and what good answers show

Good interview questions for a technical lead or practitioner ask about decisions, not trivia. Here are twelve, each with what a…

AI agents explained: how agentic AI works in production

An AI agent is a program that uses a language model to decide what to do next, takes actions through tools, looks at the result a…

RAG explained: retrieval-augmented generation, step by step

Retrieval-augmented generation (RAG) gives a language model the documents it needs at the moment it answers, instead of relying o…

RAG vs fine-tuning: how to choose

Both RAG and fine-tuning adapt a model to your needs, but they change different things. RAG changes what the model can see at ans…

Prompt engineering in 2026: beyond prompts, context engineering

Writing a good prompt matters, but in a real system the prompt is only part of what the model sees. Context engineering is the wi…

How to evaluate an LLM application: evals, hallucination tests and guardrails

You cannot improve what you cannot measure, and an AI feature that “seems fine” in a demo can fail quietly in production. An eval…

LLMOps: running AI in production, covering cost, monitoring and versioning

LLMOps is the operational side of language-model applications: keeping them reliable, affordable and improvable once real users d…

Responsible AI in practice: bias, privacy and governance checklists

Responsible AI is less about principles on a poster and more about decisions made at specific points in a project. Here is a shor…

AI copilots at work: where they help and where they fail

AI copilots draft, summarise, suggest and search. They are strongest when a person is still doing the thinking and can check the…

LangChain and LangGraph: what practitioners need to know

LangChain and LangGraph are open-source libraries for building applications around language models. They are tools, not requireme…

Multimodal AI explained: text, image and audio in one system

A multimodal model takes more than one kind of input, such as text with images or audio, and can sometimes produce more than one…

Private AI for regulated industries: on-premise LLMs for law, health and finance

Law firms, clinics and financial teams handle material they may not be free to send to an outside service. Running a model on inf…

Local LLM vs cloud AI: cost, privacy and latency compared

The honest answer to “local or cloud?” is a comparison you do with your own numbers. Here is how to set it up, so you do not rely…

Quantization explained: GGUF, AWQ and running big models on small hardware

Quantization stores a model’s weights using fewer bits, so the model takes less memory and often runs faster. The trade-off is so…

Choosing hardware for local AI: GPUs, NPUs and Apple Silicon

For local models, the main constraint is memory, followed by memory speed, and only then raw compute. Match the hardware to the m…

RAG on a local LLM: private document search that never leaves your building

Combine retrieval with a locally hosted model and you can answer questions from sensitive documents without sending them anywhere…

Edge AI inference: small models on devices, offline and in real time

Edge inference runs a model on or near the device that produces the data: a phone, a gateway, a vehicle, a factory machine. It cu…