Heb ik eerdere ervaring nodig?

Enige voorkennis wordt aanbevolen voordat je Build a Working AI Agent start.

Hoeveel tijd kost Build a Working AI Agent?

Build a Working AI Agent bevat 4 modules en 12 lessen. Je leert in je eigen tempo.

Hoe krijg ik toegang?

Build a Working AI Agent is inbegrepen bij elk betaald abonnement.

code ai

Build a Working AI Agent

An agent is a loop, and you are going to write it yourself before you are shown a framework that hides it. Four modules and four artefacts: the loop with its own tools and step cap, a defensible model choice, an agent that reads vendor documents and assembles a VAT return without double-counting anything, and a phishing-link scorer running against a model on your own machine.

trending_upIntermediate
schedule6h 56m
menu_book12 lessen
publicEnglish
workspace_premiumBasic

lock_open Start met leren

Inleiding

This segment is built out of agents that are actually in use, and it is the opposite of a tour. You write one file in module 1 and every later lesson imports it. You start with the loop, in about twenty lines, against a fake model, with the network unplugged — because everybody who begins with a real key spends the first hour debugging authentication instead of the thing they came to learn. Then you harden it until no reply a model can produce will kill a run, and only then do you put a key anywhere near it. Module 2 is the boring, valuable part: where a key must never live, what to do in the first ten minutes after one leaks, and how to choose a model on twenty cases and a threshold you wrote down beforehand rather than on how it felt when you tried it twice. Module 3 is where the agent touches something real. You build a reader over a folder of vendor agreements that hands back a page and not a document, and an invoice collector that assembles a VAT return from a folder — and you make it safe to run twice, because it will be run twice, by somebody who is not sure whether the first run worked. Module 4 is what happens when it goes wrong at four in the morning and nobody is awake. Retries that only retry what is worth retrying, a run log a stranger can read a week later, and then a model on your own machine so that nothing leaves the box at all. The segment ends on the build that ties it back to defence: a scorer for a link somebody was sent, whose output is not a number but a paragraph a non-technical colleague can act on. Everything is the Python standard library. No framework, no installed packages, and every check in every lesson runs offline, so a lesson never depends on a credential working. Segment A1, AI Without the Hype, is assumed: next-token prediction, the resend on every turn, and plan with the strong model, execute with the cheap one. None of it is repeated here. It is used. **Nothing in this segment is offensive.** The phishing material is a scorer. It weighs a link that somebody has already been sent and never produces a link, a lure, a page or a way past a filter, and the standing rules are printed in the lab that uses it.

Cursusopbouw · 4 modules

lockBeschikbaar met toegang

01 The Loop, Written By Hand
3 lessen·1h 32m

An agent is a loop. Every framework you will be shown is that loop with features bolted on, and you cannot tell which of those features you need until you have written the loop yourself.
02 Keys, Models and Evidence
3 lessen·1h 29m

Everybody picks a model on how it felt when they tried it twice. Twenty cases and a mechanical check take an afternoon once and five minutes whenever anything changes, and only one of the two…
03 Tools That Touch The Real World
3 lessen·1h 50m

Most tool-call failures are documentation failures. And any tool that changes something will be called twice, by a person who is not sure whether the first run worked, so calling it twice has to be…
04 The Failed Run, the Local Model, and the Link You Were Sent
3 lessen·2h 5m

Four in the morning. Eight invoices are recorded, the ninth call fails, the process exits and nobody is awake. Should it have retried, what did it already do, and how would anyone find out.

Veelgestelde vragen

Wat leer ik in Build a Working AI Agent?: An agent is a loop, and you are going to write it yourself before you are shown a framework that hides it. Four modules and four artefacts: the loop with its own tools and step cap, a defensible model choice, an agent that reads vendor documents and assembles a VAT return without double-counting any
Heb ik eerdere ervaring nodig?: Enige voorkennis wordt aanbevolen voordat je Build a Working AI Agent start.
Hoeveel tijd kost Build a Working AI Agent?: Build a Working AI Agent bevat 4 modules en 12 lessen. Je leert in je eigen tempo.
Hoe krijg ik toegang?: Build a Working AI Agent is inbegrepen bij elk betaald abonnement.

Meer in Programmeren

Beginner Binary, Hex and Data Units The topic that costs more marks than any other on the paper, taught by hand. Bits and bytes, binary and hex in all six directions, the 1000-versus-1024 trap, file sizes, transmission times, overflow, two's complement and character sets. Every module ends in a timed drill marked the way an examiner marks it.

Beginner Python From a White Sheet De exacte volgorde die negen studenten al hebben gelopen, van een leeg bestand naar een programma dat vragen stelt, antwoorden controleert en slechte invoer weigert. Geen eerdere programmeerervaring. Geen wiskunde. Je zult het herhaaldelijk opzettelijk breken.

Beginner First Program — Scratch for ages 5–9 Nine Scratch blocks, three sessions of about twenty-five minutes, and one small program a child of five to nine builds themselves. Written for the parent sitting beside them: what to click, what they will get stuck on, what to say when it goes wrong, and when to keep your hands off the mouse.

Beginner AI Without the Hype Wat het model werkelijk doet wanneer het je antwoord geeft, waarom dat iets oplevert dat op denken lijkt, waarom het citaten verzint, en het kostenmechanisme dat bijna niemand uitlegt: een chat stuurt bij elke beurt het hele gesprek terug. Je rekent het zelf uit.

Intermediate IGCSE en GCSE Computer Science — Theorie die daadwerkelijk wordt beoordeeld Het theoriegedeelte van het tentamen, onderwezen zodat het stand houdt in het examenlokal. De geheugenhiërarchie en wat er werkelijk gebeurt bij het opstarten. Compilers, interpreters en assemblers, inclusief het antwoord dat juist klinkt en niets oplevert. Databases van een spreadsheet tot sleutels en normalisatie. DNS en het volledige pad tussen het indrukken van Enter en het zien van de pagina. Systeemondersteunende software, en het ethische en juridische gedeelte dat de gemakkelijkste tien punten van het tentamen is.

Intermediate Programming for the Exam — Python Answers That Score The programming half of the paper, taught at exam pitch. Pseudocode translated both ways, because the mark scheme is written in a notation nobody practises. Trace tables done column by column, including the ones with a loop and a condition inside it. Linear and binary search, bubble and insertion sort, what each costs and the comparison questions boards love. Validation against verification, and the boundary test data everybody forgets. Procedures against functions, and a systematic method for finding your own error with four minutes left.