Online Cursussen

Cursussen in eigen tempo met videolessen, praktijkprojecten en uitgebreide leerpaden.

Audience

Level

✎You

◆Agent

✉Email

📅Calendar

📄Files

★Skills

💬Slack

⏱Schedule

✔Done

Build Your Personal AI Agent Assistant

All LevelsBinnenkort

AgentsPersonal assistant

Learn to build your own personal AI agent that manages email, calendar, files, and workflows. No programming experience required — configure Claude Code and Cowork with MCP integrations, custom skills, and automation to work for you daily.

Binnenkort

> make an AI agentclass Agent: def run(self, task): return self.think(task)

AI-Powered Development

All LevelsBinnenkort

CodingDevelopmentAgentsFullstackDevOps

Learn to build and ship your own AI agent chatbot interface using agentic AI coding tools. From first mockup to deployed product — master prompting, spec-driven design, databases, auth, and CI/CD with AI as your co-pilot.

Binnenkort

▸Prompt

◆Agent

◫RAG

◓Memory

⌕Search

</>Code

⇄API

⚙Planner

✔Output

Building Agentic Systems with Python

INTERMEDIATEBinnenkort

CodingPythonAgentsMistralMCPRAGEvals

Build AI agents from first principles in Python. Write the agent loop yourself against the Mistral API, design tools, manage context and memory, build a search agent and measure it against a fixed retrieval pipeline, then harden it with evals, guardrails and MCP.

Binnenkort

from sklearn.ensemble import RandomForestClassifierclf = RandomForestClassifier()clf.fit(X_train, y_train)clf.score(X_test, y_test)▸ 0.94

Applied Machine Learning

BEGINNERBinnenkort

CodingPythonMachine Learning

A practical introduction to machine learning: Python environments, core ML concepts, and hands-on projects.

Binnenkort

β = (XᵀX)⁻¹Xᵀyθ = θ − α∇J(θ)σ(x) = 1 / (1 + e⁻ˣ)L = ¹⁄ₙ Σ(ŷ − y)²m = β₁m + (1−β₁)ga · b = Σ aᵢbᵢD = √((x−μ)ᵀΣ⁻¹(x−μ))P(y) = eᶻ / ΣeᶻH = −Σ y log(ŷ)P(A|B) = P(B|A)P(A) / P(B)G = 1 − Σ pᵢ²J + λ‖w‖²

Foundational Machine Learning

ADVANCEDBinnenkort

CodingPythonFundamentalMachine Learning

50+ video hours, 6+ projects covering ~50 ML topics. From data cleaning to model explainability.

Binnenkort

Recommender Systems with Python

INTERMEDIATEBinnenkort

CodingPythonRecommender SystemsMachine LearningEvaluationEmbeddings

Build recommenders from first principles in Python: popularity baselines, neighborhood methods, matrix factorization, implicit feedback and exposure, embedding maps, neural models and production pipelines. Every technique is measured on MovieLens against the baselines it has to beat.

Binnenkort