AI technologies, explained one by one
What each AI technology does, and the four ways to run it: managed on AWS, Azure or Google Cloud, or on your own machines. With architectures from real projects.
Ready-made AI capabilities
One job, one API call, a model you never see.
Speech to text
Transcription, also called automatic speech recognition, turns audio into written text and records when each word was said.
Read more →
Image recognition
Computer vision models look at an image or a video frame and return what they see: objects, scenes, text or faces, each with a confidence value.
Read more →
TReading documents (OCR)
Optical character recognition (OCR) turns a scan, a photo of a page or a PDF into text. Document services also return the layout: which word sits in which table cell and form field.
Read more →
Text analysis
Natural language processing (NLP) reads text and returns structure: the entities in it, key phrases, sentiment, the language, and personal data that should not travel further.
Read more →
PText to speech
Neural text-to-speech turns text into natural-sounding audio, in many languages and voices, and can tell you when each word is spoken.
Read more →
Machine translation
Neural machine translation moves text between languages at a fixed price per character, and respects a glossary of terms you insist on.
Read more →Managed models and agents
You choose the model and design the request. The provider runs the inference.
Foundation models (LLMs)
Large language models and other foundation models answer prompts: summarise, compare, classify, draft, explain. You choose the model and write the request; somebody runs the inference.
Read more →
Multimodal content understanding
Content understanding services take a document, image, audio file or video and return structured output for the whole thing, such as the scenes of a video with a summary for each.
Read more →
AI agents
An agent is a model plus the tools it may call. An agent runtime runs it, keeps sessions apart, gives each agent an identity and memory, and records what it did.
Read more →Your own model
Your data, your weights, on a managed platform or your own.
The AI tools people open every day, family by family: Claude, ChatGPT, Gemini, Copilot and more →
Learn to decide
The course “From Managed to Hybrid” teaches where AI should run: what each layer costs, what you operate and where your data has to stay. It is in preparation, with a free live session first.
Build it with me
Tell me what you want to build. In 30 minutes we check which of the four ways fits your data, your rules and your budget, and whether AWS funding for a proof of concept can cover part of it.
