das ai-curriculum,kurs für kurs.

251 von 251 kursen · 700.5 kontaktstunden

• GroundModule2 std.

  Understanding Artificial Intelligence

  Learn how AI models actually work, from tokens to probability, and why the same question can produce two different answers.

  du lieferstA one-page explanation of tokens and probability in your own words

  AI Foundations·keine tools

• GroundModule1.5 std.

  Choosing the Right AI Model

  Discover the differences between frontier and small models, open and closed weights, and learn to pick the right one for a task.

  du lieferstA model-selection cheat sheet for your team

  AI Foundations·Claude, GPT, Gemini, Llama

• GroundModule2 std.

  Understanding AI Limitations

  Learn where AI models fail, covering invented facts, out of date knowledge, arithmetic errors and false confidence, by making each failure happen yourself.

  du lieferstA personal failure log with five real examples

  AI Foundations·keine tools

• GroundModule1.5 std.

  AI Safety and Data Handling at Work

  Learn what data can and cannot go into a prompt, which tools are approved, and what to do when something goes wrong.

  du lieferstA completed data-classification decision tree

  AI Foundations·keine tools

• GroundModule2 std.

  Getting Started with AI at Work

  Build a practical daily AI habit and learn to decide which tasks to delegate to a model and which to keep.

  du lieferstA weekly AI habit plan with three named tasks

  AI Foundations·Claude, Copilot, Gemini

• GroundModule2 std.

  Verifying AI Output

  Learn practical techniques for checking AI answers, including source checking and cross-model verification.

  du lieferstA reusable verification checklist for your function

  AI Foundations·keine tools

• GroundModule1.5 std.

  Understanding AI Costs

  Discover how tokens, context length and model choice drive the cost of AI, and learn to estimate the price of a workflow.

  du lieferstA cost estimate for one of your own workflows

  AI Foundations·keine tools

• GroundCase1.5 std.

  Redesigning Your Role with AI

  Break your job into tasks and learn to decide which to automate, which to augment and which to keep human.

  du lieferstA task inventory split into automate / augment / keep

  AI Foundations·keine tools

• GroundModule1 std.

  Communicating About AI Clearly

  Learn to describe what AI systems actually do, without the hype that makes projects hard to evaluate.

  du lieferstA rewritten internal update stripped of hype

  AI Foundations·keine tools

• GroundModule2 std.

  Introduction to Prompt Engineering

  Learn the parts of an effective prompt, covering the task, context, constraints, examples and output format, and why vague instructions fail.

  du lieferstA before/after prompt pair with measured difference

  Prompt Engineering·Claude, ChatGPT, Gemini

• OperatorModule2.5 std.

  Intermediate Prompt Engineering

  Master six reusable prompting patterns, including role framing, few-shot examples, decomposition and output contracts.

  du lieferstSix reusable prompt patterns for your function

  Prompt Engineering·Claude, ChatGPT

• OperatorModule3 std.

  Context Engineering

  Learn what to put in a model's context window and in what order, and why a large window is not permission to paste everything.

  du lieferstA restructured long-context prompt with measured lift

  Prompt Engineering·Claude

• OperatorModule2.5 std.

  Prompt Chaining and Decomposition

  Discover how to split a difficult request into a sequence of simple ones, and learn where chains break down.

  du lieferstA three-stage chain that beats a single prompt

  Prompt Engineering·Claude, ChatGPT

• OperatorModule2 std.

  Controlling Model Reasoning

  Learn to use extended thinking and effort budgets, and to judge when deeper reasoning is worth the extra cost.

  du lieferstA cost/quality curve across three thinking budgets

  Prompt Engineering·Claude, GPT

• OperatorModule2 std.

  Managing Prompts as a Team

  Learn to version, name, own and review prompts so they become shared assets rather than private tricks.

  du lieferstA versioned prompt library with owners

  Prompt Engineering·keine tools

• OperatorModule2 std.

  Prompting with Images and Documents

  Learn to work with images, PDFs, screenshots and charts as model input for contracts, invoices and reports.

  du lieferstA document-to-structure workflow you use weekly

  Prompt Engineering·Claude, Gemini

• BuilderModule2.5 std.

  Writing System Prompts for Products

  Learn to write the instruction layer behind a production feature, covering tone, refusals, escape hatches and drift.

  du lieferstA production system prompt with a change log

  Prompt Engineering·Claude, OpenAI

• GroundModule1.5 std.

  Introduction to Prompt Injection

  Understand why pasting untrusted content into a model is a security risk, and learn to recognise it without writing code.

  du lieferstA red-flag list for your team's tools

  Prompt Engineering·keine tools

• BuilderDrill2 std.

  Structuring Model Output

  Learn to force reliable output shapes using schemas, enums and citations so downstream code can trust what it receives.

  du lieferstA schema-locked prompt with a 100-case pass rate

  Prompt Engineering·Claude, OpenAI

• BuilderModule3 std.

  Working with the Messages API

  Learn to call a language model API directly, handling roles, system instructions, stop reasons, errors and retries.

  du lieferstA working client with retry and timeout handling

  Building AI Applications·Claude, OpenAI

• BuilderModule3 std.

  Structured Outputs and Schemas

  Learn to extract reliably typed data from a model, covering schema design, validation and repair loops.

  du lieferstAn extraction service with schema validation

  Building AI Applications·Claude, OpenAI

• BuilderModule3.5 std.

  Introduction to Tool Use

  Learn to give a model access to your own functions and APIs, handling definitions, arguments, results and errors.

  du lieferstA model that queries your own API correctly

  Building AI Applications·Claude, OpenAI

• BuilderModule2.5 std.

  Streaming and Responsive AI Interfaces

  Learn to stream model output token by token, with partial rendering, cancellation and good waiting states.

  du lieferstA streaming endpoint with graceful cancellation

  Building AI Applications·Claude, OpenAI

• BuilderModule3 std.

  Building Multimodal Pipelines

  Learn to process images, PDFs and audio at scale, including pre-processing, page splitting and cost control.

  du lieferstA document pipeline handling 200 mixed files

  Building AI Applications·Claude, Gemini

• BuilderModule2.5 std.

  Prompt Caching and Batch Processing

  Learn to cut AI costs using prompt caching, batch endpoints and request shaping, with measured results.

  du lieferstA workload with a measured cost reduction

  Building AI Applications·Claude, OpenAI

• ArchitectModule3 std.

  Model Routing and Fallbacks

  Learn to route requests between cheap and expensive models and handle provider outages with circuit breakers.

  du lieferstA router with a documented escalation policy

  Building AI Applications·Claude, OpenAI, OSS

• BuilderLab4 std.

  Building a Chat Application

  Build a production chat feature covering conversation state, truncation, memory, rate limits and abuse handling.

  du lieferstA deployed chat feature with history and limits

  Building AI Applications·Claude, OpenAI

• BuilderLab3.5 std.

  Building Document Processing Systems

  Build a pipeline that turns contracts and forms into structured records through ingest, extract, validate and review.

  du lieferstA pipeline turning contracts into structured records

  Building AI Applications·Claude

• BuilderModule3 std.

  Classification and Extraction at Scale

  Learn when a language model beats a trained classifier, and how to set thresholds, abstention and review queues.

  du lieferstA classifier with a published confusion matrix

  Building AI Applications·Claude, OSS

• BuilderModule2.5 std.

  Generating Synthetic Data

  Learn to generate test cases, edge cases and training data, and to measure diversity and avoid model collapse.

  du lieferstA synthetic test set with diversity metrics

  Building AI Applications·Claude, OSS

• BuilderCase2 std.

  Choosing Between Prompting, RAG and Fine-Tuning

  Learn to make the build decision for an AI feature using cost, latency and accuracy evidence rather than preference.

  du lieferstA written decision memo for one real feature

  Building AI Applications·keine tools

• BuilderModule3 std.

  Introduction to Embeddings

  Learn how embeddings represent meaning as vectors, and build a working semantic search over your own documents.

  du lieferstA working semantic search over your own docs

  Retrieval & RAG·OpenAI, Cohere, OSS

• BuilderModule3 std.

  Preparing Documents for Retrieval

  Learn structure aware chunking, overlap, metadata and table handling, the step that quietly decides retrieval quality.

  du lieferstA chunking strategy with a retrieval score

  Retrieval & RAG·LangChain, LlamaIndex

• BuilderModule3 std.

  Working with Vector Databases

  Learn to index, filter and update vectors in production, covering multi-tenancy, namespaces and operational cost.

  du lieferstA store with filters, namespaces and backups

  Retrieval & RAG·Pinecone, Weaviate, pgvector

• BuilderLab3.5 std.

  Building RAG Applications

  Build a retrieval-augmented assistant end to end, with query rewriting, grounding, citation and refusal.

  du lieferstA grounded assistant with citations

  Retrieval & RAG·LangChain, Claude

• BuilderModule3 std.

  Hybrid Search and Reranking

  Learn to combine keyword and vector search with a reranker, usually the biggest available quality gain.

  du lieferstA measured precision gain over pure vector search

  Retrieval & RAG·BM25, rerankers

• ArchitectModule3 std.

  Introduction to Graph RAG

  Learn to use graph databases for retrieval when relationships matter more than similarity, including multi-hop questions.

  du lieferstA graph-backed answer to a multi-hop question

  Retrieval & RAG·Neo4j, LangChain

• BuilderModule3 std.

  Evaluating Retrieval Quality

  Learn to measure recall, precision and faithfulness, and to score retrieval separately from generation.

  du lieferstA retrieval scorecard on your own corpus

  Retrieval & RAG·RAGAS, custom

• BuilderModule3 std.

  Building Text-to-SQL Systems

  Learn to query a warehouse in natural language, with schema context, guardrails, validation and review gates.

  du lieferstA guarded query interface with a review gate

  Retrieval & RAG·Claude, dbt

• ArchitectModule2.5 std.

  Keeping Knowledge Bases Current

  Learn to detect change, re-embed efficiently and set staleness targets so answers do not silently go out of date.

  du lieferstAn index refresh design with staleness SLOs

  Retrieval & RAG·keine tools

• ArchitectLab3.5 std.

  Search Over Messy Enterprise Data

  Build a working index over real corporate content: duplicates, contradictions, dead policies and scanned PDFs.

  du lieferstA working index over genuinely bad source data

  Retrieval & RAG·Claude, hybrid stack

• OperatorModule2 std.

  Introduction to AI Agents

  Learn what an agent actually is, namely a loop with tools and a stopping condition, and how to judge which work is worth automating.

  du lieferstA written spec for one candidate agent

  AI Agents·keine tools

• BuilderModule3 std.

  Building Your First AI Agent

  Build an agent loop by hand before using a framework, covering tools, termination, iteration caps and error recovery.

  du lieferstA working agent with three real tools

  AI Agents·Claude, OpenAI

• BuilderModule3 std.

  Agent Memory and State

  Learn to give an agent durable state so it survives a restart, and understand memory versus a longer prompt.

  du lieferstAn agent that survives a restart mid-task

  AI Agents·Claude, LangGraph

• BuilderModule3 std.

  Agent Planning Patterns

  Learn plan-and-act, reflection and decomposition patterns, and which genuinely improve results rather than burning tokens.

  du lieferstA planner/executor split with a measured gain

  AI Agents·LangGraph, Claude

• ArchitectModule3.5 std.

  Building Multi-Agent Systems

  Learn supervisor, parallel and hand off patterns for multiple agents, and recognise when a single agent is the better design.

  du lieferstA parallel fan-out with a synthesis stage

  AI Agents·LangGraph, CrewAI, Claude

• BuilderModule3 std.

  Introduction to Model Context Protocol (MCP)

  Learn the MCP standard for connecting models to tools and data, including primitives, transport and configuration.

  du lieferstA client connected to three MCP servers

  AI Agents·MCP, Claude

• BuilderLab3.5 std.

  Building MCP Servers

  Build your own MCP server to expose an internal system as tools, covering schema design, auth and versioning.

  du lieferstA published MCP server over an internal system

  AI Agents·MCP

• ArchitectModule3 std.

  Agent Permissions and Sandboxing

  Learn to scope what an agent can touch using least privilege, allow-lists, execution isolation and action gates.

  du lieferstA permission matrix and an enforced sandbox

  AI Agents·Claude, containers

• BuilderModule2.5 std.

  Designing Human-in-the-Loop Approval

  Learn to design approval checkpoints people actually read, and avoid the rubber stamp that defeats the control.

  du lieferstAn approval flow with a measured intervention rate

  AI Agents·keine tools

• ArchitectModule3 std.

  Agent Observability and Tracing

  Learn to trace an agent run with spans, tool calls and token accounting so failures can be reconstructed.

  du lieferstA traced agent run you can debug from logs

  AI Agents·LangSmith, OTel

• ArchitectModule3 std.

  Long-Running and Scheduled Agents

  Learn to run agents on a schedule or for hours, covering idempotency, resumption, drift and unattended failure.

  du lieferstA scheduled agent with alerting and a kill switch

  AI Agents·Claude, queues

• OperatorLab3 std.

  Workflow Automation Without Code

  Build real business automations in a visual builder, covering triggers, branching, error paths and handover.

  du lieferstA live automation replacing a manual routine

  AI Agents·n8n, Power Automate

• ArchitectModule3 std.

  Browser and Computer-Use Agents

  Learn to drive interfaces that have no API, with a candid look at reliability, cost and the security surface.

  du lieferstA guarded browser task with a scoped profile

  AI Agents·Claude, Playwright

• ArchitectModule2.5 std.

  Controlling Agent Cost and Risk

  Learn to apply loop detection, spend caps, dry runs and reversibility so a bad agent run does not become an incident.

  du lieferstA budget guard and a rollback plan

  AI Agents·keine tools

• OperatorModule2.5 std.

  Getting Started with AI Coding Assistants

  Learn to use AI coding assistants effectively and establish an honest baseline of your current speed.

  du lieferstA measured baseline on your own repository

  AI for Software Engineering·Copilot, Claude Code, Cursor

• BuilderModule3 std.

  Spec-Driven Development with AI

  Learn to write the specification a model needs in order to produce correct code first time.

  du lieferstA spec that produced working code first time

  AI for Software Engineering·Claude Code

• BuilderModule2.5 std.

  Reviewing AI-Generated Code

  Learn to review code you did not write, spotting hallucinated APIs, silent assumptions and plausible nonsense.

  du lieferstA review checklist adopted by your team

  AI for Software Engineering·keine tools

• BuilderModule2.5 std.

  Generating Tests with AI

  Learn to generate tests that actually fail when the code is wrong, verified with mutation testing.

  du lieferstA suite with mutation-tested quality

  AI for Software Engineering·Claude Code, Copilot

• BuilderLab3 std.

  Understanding Unfamiliar Codebases with AI

  Learn to map a large unfamiliar repository quickly, covering call graphs, dead code and hidden coupling.

  du lieferstA written architecture map of an unfamiliar repo

  AI for Software Engineering·Claude Code

• ArchitectLab3.5 std.

  Large-Scale Refactoring with AI Agents

  Learn to run codebase-scale migrations with agents, covering batching, verification gates and rollback.

  du lieferstA migration executed across 50+ files

  AI for Software Engineering·Claude Code

• BuilderModule3 std.

  Debugging with AI Agents

  Learn a disciplined debugging loop of reproduce, bisect, hypothesise and verify that keeps the model honest.

  du lieferstA reproducible bug hunt logged end to end

  AI for Software Engineering·Claude Code

• OperatorModule2 std.

  Documenting Code with AI

  Learn to generate architecture decision records, runbooks and API documentation that stay accurate.

  du lieferstGenerated docs that survived a review

  AI for Software Engineering·Claude Code

• ArchitectModule3 std.

  AI in CI/CD Pipelines

  Learn to automate review, triage and release notes in your pipeline, and recognise where a bot becomes noise.

  du lieferstAn automated review step running on PRs

  AI for Software Engineering·GitHub Actions, Claude

• BuilderCase1.5 std.

  Knowing When Not to Use AI on Code

  Learn to define the boundary for cryptography, concurrency and regulated code paths before an incident defines it for you.

  du lieferstA written no-go list for your codebase

  AI for Software Engineering·keine tools

• ArchitectCase2 std.

  Measuring Engineering Productivity

  Learn to measure AI's real effect using cycle time and change failure rate rather than lines accepted.

  du lieferstA metric set your engineers do not game

  AI for Software Engineering·DORA

• BuilderModule3 std.

  AI for Data Engineering

  Learn to build pipelines and transformations with AI assistance, protected by data contract tests.

  du lieferstA generated pipeline with contract tests

  AI for Software Engineering·dbt, SQL, Claude

• OperatorModule2 std.

  Introduction to AI Evaluation

  Learn why a demo is not evidence, and how to define what good means for an AI feature before you build it.

  du lieferstA written quality definition for one feature

  Evaluation & Testing·keine tools

• BuilderLab3 std.

  Building Your First Eval Set

  Build a 100-case evaluation set from real examples and score your current system against it.

  du lieferstA 100-case eval set with a baseline score

  Evaluation & Testing·keine tools

• BuilderModule3 std.

  Using LLMs as Judges

  Learn to automate grading with a model judge, covering rubrics, position bias and calibration against humans.

  du lieferstA judge validated against human labels

  Evaluation & Testing·Claude, OpenAI

• BuilderModule2.5 std.

  Running Human Evaluation

  Learn to run annotators well, covering guidelines, inter-rater agreement, adjudication and cost per label.

  du lieferstAn annotation guideline with measured agreement

  Evaluation & Testing·keine tools

• BuilderModule2.5 std.

  Regression Testing for Prompts

  Learn to treat prompts as code, with version control and CI gates that block quality regressions.

  du lieferstAn eval gate blocking a bad prompt merge

  Evaluation & Testing·CI, promptfoo

• ArchitectModule3 std.

  Monitoring AI in Production

  Learn to measure quality live using sampling, implicit signals, drift detection and alert thresholds.

  du lieferstA production quality dashboard with alerts

  Evaluation & Testing·LangSmith, OTel

• BuilderModule3 std.

  Detecting Hallucination and Measuring Grounding

  Learn to score answers for unsupported claims automatically, and to treat abstention as a feature.

  du lieferstA faithfulness score wired into your pipeline

  Evaluation & Testing·keine tools

• ArchitectModule3 std.

  A/B Testing AI Features

  Learn to design experiments on systems whose output varies per call, covering variance and sample size.

  du lieferstA powered experiment design for one feature

  Evaluation & Testing·keine tools

• ArchitectModule3 std.

  Evaluating AI Agents

  Learn to score an agent's trajectory rather than its answer, covering tool choice, step efficiency and partial credit.

  du lieferstA trajectory rubric applied to 50 runs

  Evaluation & Testing·LangSmith

• ArchitectCase2 std.

  Running an AI Quality Review

  Learn to run a recurring forum that holds AI features to their measured numbers.

  du lieferstA standing review agenda and its first minutes

  Evaluation & Testing·keine tools

• ArchitectModule3 std.

  Introduction to LLMOps

  Learn the operational lifecycle of an AI system, from prompt and model to data, evaluation, release and monitoring, and how it differs from MLOps.

  du lieferstA reference architecture for your stack

  Deployment & Operations·keine tools

• ArchitectModule3 std.

  Building an AI Gateway

  Learn to put every model call behind one front door with keys, quotas, logging, routing and provider abstraction.

  du lieferstA gateway with keys, quotas and logging

  Deployment & Operations·LiteLLM, gateways

• ArchitectModule3 std.

  Reducing AI Latency

  Learn where the milliseconds go and how to cut them through model choice, output length, streaming and caching.

  du lieferstA P95 reduction with a documented method

  Deployment & Operations·keine tools

• ArchitectModule3 std.

  AI Cost Management

  Learn to model cost per request, per user and per outcome, and to forecast and control AI spend.

  du lieferstA per-request unit economic model

  Deployment & Operations·keine tools

• ArchitectModule2.5 std.

  Managing Rate Limits and Capacity

  Learn to handle provider limits with queuing, backpressure and graceful degradation under load.

  du lieferstA load plan surviving a 10x spike

  Deployment & Operations·keine tools

• ArchitectLab3.5 std.

  Self-Hosting Open Models

  Learn to serve open-weight models yourself, covering GPUs, quantisation and the true total cost.

  du lieferstA served open model with a cost comparison

  Deployment & Operations·vLLM, Llama, Mistral

• ArchitectModule3 std.

  Deploying AI on Cloud Platforms

  Learn to deploy models on Bedrock, Vertex or Azure AI Foundry, covering residency, networking and procurement.

  du lieferstA deployment meeting your residency rules

  Deployment & Operations·Bedrock, Vertex, Foundry

• ArchitectModule2.5 std.

  Migrating Between Models

  Learn to move to a new model version without a quality regression, using shadow traffic and staged rollout.

  du lieferstA migration runbook with an eval gate

  Deployment & Operations·keine tools

• ArchitectModule2.5 std.

  Incident Response for AI Systems

  Learn to detect, contain and disclose when a model is confidently wrong at scale, then run the post-mortem.

  du lieferstA runbook plus one tabletop exercise

  Deployment & Operations·keine tools

• ArchitectModule3 std.

  Privacy-Preserving AI Architecture

  Learn to design for redaction, tokenisation, residency, retention and zero-retention endpoints.

  du lieferstA data-flow diagram cleared by your DPO

  Deployment & Operations·keine tools

• BuilderModule2.5 std.

  Introduction to AI Security

  Learn to threat model an AI feature, covering assets, actors and entry points, mapped to the OWASP LLM risks.

  du lieferstA threat model for one live feature

  AI Security·keine tools

• BuilderLab3 std.

  Attacking Systems with Prompt Injection

  Learn direct and indirect prompt injection by breaking a system you built, then attempting to defend it.

  du lieferstThree successful injections against your own app

  AI Security·keine tools

• BuilderModule3 std.

  Preventing Data Exfiltration

  Learn to recognise and break the combination of private data, untrusted content and an outbound channel.

  du lieferstAn audit of your tools against the trifecta

  AI Security·keine tools

• ArchitectModule3 std.

  Securing AI Agent Permissions

  Learn to scope agent capability so that a compromised agent cannot cause real damage.

  du lieferstA least-privilege design for one agent

  AI Security·keine tools

• ArchitectLab3.5 std.

  Red-Teaming AI Applications

  Learn to run a structured campaign covering jailbreaks, extraction, poisoning and denial of wallet, then write it up.

  du lieferstA red-team report with severity ratings

  AI Security·keine tools

• ArchitectModule3 std.

  Securing the AI Supply Chain

  Learn to vet third-party models, MCP servers, skills and packages for provenance before adoption.

  du lieferstA vetting standard for third-party components

  AI Security·MCP, models, skills

• BuilderModule2.5 std.

  Handling Untrusted Model Output

  Learn to treat model output as untrusted input, preventing XSS, SQL injection and unsafe rendering.

  du lieferstA hardened rendering and execution path

  AI Security·keine tools

• BuilderModule2.5 std.

  Redacting Secrets and PII

  Learn to keep sensitive data out of prompts, logs and traces, and to measure how well redaction works.

  du lieferstA redaction layer with measured recall

  AI Security·keine tools

• ArchitectCase3 std.

  Building an AI Security Review Process

  Learn to design a review gate every AI feature passes, sized so that it does not become theatre.

  du lieferstA review gate adopted into your SDLC

  AI Security·keine tools

• OperatorModule2 std.

  Writing an AI Acceptable Use Policy

  Learn to write an AI policy short enough to be read and specific enough to be applied.

  du lieferstA one-page AI policy fit for your company

  Governance & Compliance·keine tools

• BuilderModule3 std.

  Understanding the EU AI Act

  Learn the risk tiers, obligations, timelines and roles under the EU AI Act from a deployer's perspective.

  du lieferstA risk classification of your AI inventory

  Governance & Compliance·keine tools

• BuilderModule3 std.

  Introduction to ISO/IEC 42001

  Learn to build an AI management system that survives an audit without stalling delivery.

  du lieferstA gap analysis against the standard

  Governance & Compliance·keine tools

• OperatorModule2.5 std.

  Building an AI Use Case Inventory

  Learn to discover, register and maintain a live inventory of every AI system in your organisation.

  du lieferstA populated register with owners and tiers

  Governance & Compliance·keine tools

• BuilderModule3 std.

  Conducting AI Impact Assessments

  Learn to assess a use case before build, covering affected people, severity, reversibility and mitigation.

  du lieferstA completed assessment on a real use case

  Governance & Compliance·keine tools

• BuilderModule2.5 std.

  AI Vendor Due Diligence

  Learn to assess an AI vendor on training data, retention, sub-processors, evaluations and incident history.

  du lieferstA vendor questionnaire and a scoring rubric

  Governance & Compliance·keine tools

• OperatorModule2 std.

  AI, Copyright and Intellectual Property

  Learn who owns model output, what your inputs expose, and where the real legal risk sits today.

  du lieferstA guidance note for your content teams

  Governance & Compliance·keine tools

• BuilderLab3 std.

  Testing AI Systems for Bias

  Learn to move from fairness principles to actual tests, covering subgroup measurement, proxies and remediation.

  du lieferstA bias test report on a real system

  Governance & Compliance·keine tools

• OperatorModule2 std.

  AI Transparency and Disclosure

  Learn to tell users that AI was involved, in language that informs rather than disclaims.

  du lieferstDisclosure copy shipped in a real product

  Governance & Compliance·keine tools

• BuilderModule2.5 std.

  Audit Trails for AI Systems

  Learn to log what a regulator or auditor will ask for, before they ask for it.

  du lieferstAn evidence pack for one AI system

  Governance & Compliance·keine tools

• BuilderCase3 std.

  Sector-Specific AI Regulation

  Learn where financial services, healthcare, public sector and employment rules bite harder than AI law.

  du lieferstA sector obligation map for your business

  Governance & Compliance·keine tools

• ArchitectCase2.5 std.

  Designing an AI Governance Operating Model

  Learn to set decision rights and accountability so that governance does not become a bottleneck.

  du lieferstAn RACI and a decision-rights map

  Governance & Compliance·keine tools

• OperatorModule2.5 std.

  Choosing the Right AI Product Opportunity

  Learn to screen AI feature ideas on error tolerance, value of speed and availability of ground truth.

  du lieferstA scored shortlist of five candidate features

  AI Product & Design·keine tools

• BuilderLab3 std.

  Writing PRDs for AI Features

  Learn to write requirements for a feature whose output varies, with acceptance criteria expressed as evaluations.

  du lieferstA PRD with acceptance criteria as an eval set

  AI Product & Design·keine tools

• BuilderModule3 std.

  Designing for Uncertainty

  Learn to design confidence, ambiguity and the honest 'I do not know' as intentional interface states rather than failures.

  du lieferstThree interface states designed and tested

  AI Product & Design·keine tools

• BuilderModule2.5 std.

  Designing Trust and Disclosure

  Learn to use citations, provenance, edit affordances and consent to earn trust without overclaiming.

  du lieferstA trust pattern set for your product

  AI Product & Design·keine tools

• BuilderModule3 std.

  Agent User Experience Patterns

  Learn patterns for showing work, interruption, approval and undo on tasks with no progress bar.

  du lieferstAn agent flow prototype with approval points

  AI Product & Design·keine tools

• BuilderModule2.5 std.

  Designing AI Error Recovery

  Learn what the interface should do when a model is wrong, slow, refuses, or is unavailable.

  du lieferstA recovery flow for three failure modes

  AI Product & Design·keine tools

• BuilderCase2.5 std.

  Pricing and Packaging AI Features

  Learn to price a feature with variable marginal cost, covering seats, credits, outcomes and the margin trap.

  du lieferstA pricing model with a margin floor

  AI Product & Design·keine tools

• BuilderModule3 std.

  Instrumenting AI Features

  Learn to measure the funnel that matters, from invoked through completed, accepted, edited and reverted, instead of raw usage.

  du lieferstAn event schema and a live funnel

  AI Product & Design·keine tools

• BuilderModule2.5 std.

  Rolling Out AI Features Safely

  Learn to plan staged release, guardrails and the kill criteria you agree before launch.

  du lieferstA rollout plan with pre-agreed kill criteria

  AI Product & Design·keine tools

• OperatorLab3 std.

  Prototyping AI Products

  Learn to build a throwaway AI prototype quickly, test it with users, and avoid accidentally shipping it.

  du lieferstA tested prototype plus a written learning

  AI Product & Design·Claude, Replit, v0

• OperatorModule3 std.

  AI for Sales

  Learn to use AI for account research, call preparation, follow-up and proposals, with clear honesty rules.

  du lieferstA live pre-call research workflow

  AI for Business Functions·Claude, Copilot, CRM

• OperatorModule3 std.

  AI for Marketing

  Learn to run a content pipeline from brief to review at volume, with brand voice and fact-checking built in.

  du lieferstA content pipeline with a brand-voice check

  AI for Business Functions·Claude, Gemini

• OperatorModule3 std.

  AI for Customer Support

  Learn to use AI for draft assistance, deflection and quality assurance, and when to hand over to a human.

  du lieferstA deflection design with an escalation policy

  AI for Business Functions·Claude, Zendesk

• OperatorModule3 std.

  AI for Finance

  Learn to use AI for variance analysis, commentary and reconciliation, with controls an auditor will accept.

  du lieferstA reconciliation workflow with a control step

  AI for Business Functions·Claude, Excel, Copilot

• OperatorModule3 std.

  AI for Legal and Contracting

  Learn to use AI for contract review, clause extraction and first drafts, with privilege and confidentiality protected.

  du lieferstA clause-review workflow with a risk register

  AI for Business Functions·Claude

• OperatorModule3 std.

  AI for Human Resources

  Learn to use AI across job design, screening, interviews and onboarding, with fairness testing built in.

  du lieferstA hiring workflow that passes a bias review

  AI for Business Functions·Claude, Copilot

• OperatorModule2.5 std.

  AI for Learning and Development

  Learn to build training content, assessments and personalised paths with AI, without generating filler.

  du lieferstA generated course outline with assessments

  AI for Business Functions·Claude

• OperatorModule2.5 std.

  AI for Procurement

  Learn to use AI for supplier analysis, tender review and spend analysis on real documents.

  du lieferstA supplier comparison built from real documents

  AI for Business Functions·Claude, Excel

• OperatorLab3 std.

  AI for Operations

  Learn to map a process, find the AI-shaped step, rebuild it and measure what changed.

  du lieferstOne process re-designed and instrumented

  AI for Business Functions·n8n, Claude

• OperatorModule2.5 std.

  AI for Executive Support

  Learn to run briefings, meeting synthesis, decision logs and follow-through at executive tempo.

  du lieferstA weekly executive briefing pipeline

  AI for Business Functions·Claude

• OperatorModule2.5 std.

  AI for Research and Competitive Intelligence

  Learn to run structured research with citation discipline, gaining depth without fabrication.

  du lieferstA sourced competitive brief

  AI for Business Functions·Claude, Gemini

• OperatorModule2.5 std.

  AI for Project Management

  Learn to use AI for status synthesis, risk detection and reporting that reflects reality.

  du lieferstA status pipeline drawn from real artefacts

  AI for Business Functions·Claude

• BuilderLab3.5 std.

  AI for Data Analysis

  Learn to take an analysis from question to query to chart to narrative, with verification at every stage.

  du lieferstAn analysis delivered end to end with AI

  AI for Business Functions·Claude, SQL, Python

• OperatorModule3 std.

  Creating Documents and Presentations with AI

  Learn to produce finished reports, decks and spreadsheets rather than raw text.

  du lieferstThree real deliverables produced and reviewed

  AI for Business Functions·Claude, Copilot, Gemini

• GroundModule2 std.

  AI for Frontline Teams

  Learn mobile-first, low-friction AI uses for field, retail, logistics and support staff.

  du lieferstA shift-level use case adopted by a team

  AI for Business Functions·Claude, Copilot

• OperatorModule2 std.

  AI for Executives

  Learn what has genuinely changed in AI, what has not, and which vendor claims to discount.

  du lieferstA briefing you could give your own board

  Leadership & Strategy·keine tools

• BuilderCase3 std.

  Building an AI Strategy

  Learn to build a portfolio of AI bets across horizons, managing concentration risk and killing projects on time.

  du lieferstA scored portfolio across three horizons

  Leadership & Strategy·keine tools

• BuilderCase2.5 std.

  Buy, Build or Wait

  Learn to make the three-way AI investment decision using switching cost, differentiation and time to value.

  du lieferstA decision memo for one live proposal

  Leadership & Strategy·keine tools

• BuilderModule2.5 std.

  Organising Teams for AI

  Learn to choose between central, embedded and federated AI teams, and decide who owns the platform.

  du lieferstA target operating model for your org

  Leadership & Strategy·keine tools

• BuilderLab3 std.

  Building the Business Case for AI

  Learn to build an AI business case that survives finance, with baselines, attribution and sensitivity analysis.

  du lieferstA defensible business case with sensitivities

  Leadership & Strategy·keine tools

• OperatorModule2.5 std.

  Leading Teams Through AI Change

  Learn to handle fear, resistance and quiet non-adoption, and what not to promise.

  du lieferstA communication plan and a listening loop

  Leadership & Strategy·keine tools

• BuilderModule2 std.

  Running an AI Operating Cadence

  Learn to set the review rhythms, decision forums and the few metrics leadership should actually track.

  du lieferstA cadence with named owners and metrics

  Leadership & Strategy·keine tools

• BuilderCase2.5 std.

  AI Skills and Talent Strategy

  Learn to map the capability you need, decide what to build versus hire, and retain people afterwards.

  du lieferstA capability map with a build/hire split

  Leadership & Strategy·keine tools

• BuilderModule2 std.

  Reporting AI Progress to the Board

  Learn to report AI progress with evidence rather than ambition, and survive the follow-up question.

  du lieferstA board-ready section with real evidence

  Leadership & Strategy·keine tools

• BuilderModule3 std.

  Machine Learning Fundamentals

  Learn supervised learning, validation, leakage and metrics, the foundation that generative AI still rests on.

  du lieferstA trained model with a validated metric

  Machine Learning·Python, scikit-learn

• BuilderModule4 std.

  Introduction to Deep Learning

  Learn networks, gradients, optimisation and regularisation by building and training them yourself.

  du lieferstA network trained from scratch

  Machine Learning·PyTorch

• ArchitectLab4 std.

  Building a Transformer from Scratch

  Learn attention, embeddings and positional encoding by writing a working small transformer.

  du lieferstA working small transformer you wrote

  Machine Learning·PyTorch

• ArchitectLab4 std.

  Fine-Tuning Language Models

  Learn supervised fine-tuning end to end, covering dataset construction, training and honest evaluation.

  du lieferstA fine-tuned model beating its base on your task

  Machine Learning·PyTorch, HF

• ArchitectModule4 std.

  Preference Tuning with RLHF and DPO

  Learn how preference data and reward modelling shape model behaviour, and what alignment training really does.

  du lieferstA preference-tuned model with a win rate

  Machine Learning·HF, TRL

• ArchitectModule3.5 std.

  Parameter-Efficient Fine-Tuning with LoRA

  Learn to adapt large models on modest hardware using LoRA and QLoRA, and to judge when it is enough.

  du lieferstAn adapter trained on a single GPU

  Machine Learning·LoRA, QLoRA

• ArchitectModule3 std.

  Model Distillation and Small Models

  Learn to teach a small model to do one job well at a fraction of the inference cost.

  du lieferstA small model within 5% of a large one

  Machine Learning·HF

• ArchitectModule3 std.

  Quantization and Inference Optimization

  Learn how precision, batching and KV cache affect throughput, and where quality starts to degrade.

  du lieferstA served model with a latency/quality curve

  Machine Learning·vLLM, GGUF

• ArchitectModule3 std.

  Explainable AI

  Learn attribution and probing techniques, and the honest limits of explaining a large model's behaviour.

  du lieferstAn explanation a regulator would accept

  Machine Learning·SHAP, probes

• BuilderCase3 std.

  Classical Methods That Still Win

  Learn where forecasting, ranking, optimisation and rules beat a language model, and benchmark it yourself.

  du lieferstA benchmark where the simple model wins

  Machine Learning·Python

• GroundModule2 std.

  Introduction to Claude

  Learn to set up Claude as a working environment using projects, artifacts, memory and connectors.

  du lieferstA configured workspace with three live projects

  AI Foundations·Claude

• OperatorModule2.5 std.

  Context Engineering with Claude

  Learn to work with Claude's large context window deliberately, covering document structure, ordering and caching.

  du lieferstA long-context workflow with a measured lift

  Prompt Engineering·Claude

• OperatorModule3 std.

  Introduction to Claude Code

  Learn to install and configure Claude Code on your own repository, covering permissions, memory files and first tasks.

  du lieferstClaude Code configured on your own repository

  AI for Software Engineering·Claude Code

• BuilderLab3.5 std.

  Claude Code in Practice

  Learn to use Claude Code for feature work, tests and refactors in an existing codebase under a real review gate.

  du lieferstA merged pull request produced with Claude Code

  AI for Software Engineering·Claude Code

• BuilderLab3 std.

  Building Agent Skills with Claude

  Learn to author, package and distribute Claude Agent Skills, including executable scripts and versioning.

  du lieferstA packaged skill your team can install

  AI Agents·Claude

• ArchitectModule3 std.

  Working with Claude Subagents

  Learn to delegate work to subagents and run tasks in parallel without losing the thread.

  du lieferstA parallel workflow across a large task

  AI Agents·Claude Code

• BuilderModule3 std.

  Connecting Claude with MCP

  Learn to connect Claude to internal systems using MCP, covering server configuration, authorisation and scopes.

  du lieferstClaude connected to three internal systems

  AI Agents·Claude, MCP

• ArchitectLab3.5 std.

  Building Secure MCP Servers

  Learn to build your own MCP server and then attack it, covering tool design, auth and injection surface.

  du lieferstA reviewed MCP server exposing internal data

  AI Agents·MCP

• ArchitectLab3.5 std.

  Building Agents with the Claude Agent SDK

  Learn to build and deploy production agents with the Agent SDK, covering the loop, tools, sessions and permissions.

  du lieferstA deployed agent built on the SDK

  AI Agents·Agent SDK

• GroundModule2.5 std.

  Claude for Documents and Spreadsheets

  Learn to produce finished Excel, PowerPoint, Word and PDF deliverables with Claude.

  du lieferstThree finished deliverables produced end to end

  AI for Business Functions·Claude

• ArchitectModule3 std.

  Deploying Claude on Bedrock and Vertex

  Learn to run Claude inside your own cloud, covering regions, networking, IAM and quotas.

  du lieferstA deployment meeting your residency requirements

  Deployment & Operations·Bedrock, Vertex

• BuilderModule2.5 std.

  Administering Claude for Business

  Learn to manage seats, roles, data controls, retention and audit logs across an organisation.

  du lieferstAn admin configuration with a written policy

  Governance & Compliance·Claude Enterprise

• OperatorModule2 std.

  Understanding Claude's Safety Behaviour

  Learn how Constitutional AI and the usage policy shape refusals, and how to design around them honestly.

  du lieferstA refusal-handling guide for your teams

  Governance & Compliance·Claude

• BuilderModule2 std.

  Managing Claude API Costs

  Learn to reduce spend with prompt caching, batch processing, model tiering and context discipline.

  du lieferstA cost reduction with cache-hit evidence

  Deployment & Operations·Claude

• GroundModule2 std.

  Claude for Non-Technical Teams

  Learn to get real work out of Claude without writing code, using projects, files and artifacts.

  du lieferstA personal workflow adopted for a week

  AI Foundations·Claude

• BuilderModule2.5 std.

  Comparing and Evaluating Claude Models

  Learn to choose between Claude model tiers and thinking budgets using evaluations rather than defaults.

  du lieferstA model-choice decision backed by evals

  Evaluation & Testing·Claude

• GroundModule2.5 std.

  Introduction to Microsoft Copilot

  Learn to use Copilot across Word, Excel, PowerPoint, Outlook and Teams, including its real limits.

  du lieferstA weekly workflow across three apps

  AI for Business Functions·Copilot

• OperatorLab3 std.

  Microsoft Copilot in Excel

  Learn to use Copilot for analysis, formulas, cleaning and modelling, with verification built in.

  du lieferstA rebuilt model with checks

  AI for Business Functions·Copilot, Excel

• BuilderLab3 std.

  Building Agents with Copilot Studio

  Learn to build, publish and govern an internal agent on Microsoft's stack.

  du lieferstA published internal agent

  AI Agents·Copilot Studio

• OperatorLab3 std.

  Automating Workflows with Power Automate

  Learn to automate real business processes, including the error paths most people skip.

  du lieferstA production flow with error handling

  AI Agents·Power Automate

• ArchitectModule3 std.

  Introduction to Azure AI Foundry

  Learn to deploy, filter, evaluate and monitor models in Azure AI Foundry.

  du lieferstA deployed endpoint with monitoring

  Deployment & Operations·Azure

• BuilderModule2.5 std.

  Governing Microsoft Copilot

  Learn to handle oversharing, sensitivity labels and the permission clean-up a Copilot rollout requires.

  du lieferstA rollout plan with permission remediation

  Governance & Compliance·Purview, Copilot

• OperatorModule2.5 std.

  GitHub Copilot for Teams

  Learn to roll out GitHub Copilot with team standards, review expectations and honest measurement.

  du lieferstA team standard with measured adoption

  AI for Software Engineering·GitHub Copilot

• GroundModule2.5 std.

  Introduction to Google Gemini

  Learn to use Gemini across Docs, Sheets, Slides, Gmail and Meet for everyday work.

  du lieferstA weekly workflow across Docs, Sheets and Gmail

  AI for Business Functions·Gemini

• GroundModule2 std.

  Research and Synthesis with NotebookLM

  Learn to synthesise your own sources with grounded answers and citation discipline.

  du lieferstA sourced synthesis of a real document set

  AI for Business Functions·NotebookLM

• ArchitectModule3 std.

  Introduction to Vertex AI

  Learn to deploy, ground and evaluate models on Google Cloud using Vertex AI.

  du lieferstA deployed model with grounding configured

  Deployment & Operations·Vertex

• BuilderLab2.5 std.

  Building Agents with Google ADK

  Learn to build and deploy multi-tool agents with the Agent Development Kit.

  du lieferstA working multi-tool agent

  AI Agents·ADK

• BuilderModule3 std.

  Generative AI in BigQuery

  Learn to run embeddings and inference next to your warehouse in SQL, with cost control.

  du lieferstA warehouse-native AI workflow

  Retrieval & RAG·BigQuery

• BuilderModule2 std.

  Governing Gemini in Google Workspace

  Learn to configure admin controls, data handling and retention across a Workspace tenancy.

  du lieferstAn admin configuration with a data policy

  Governance & Compliance·Workspace

• BuilderModule2 std.

  Introduction to Open Source AI Models

  Learn the differences between open weights and open source, and where open models genuinely win.

  du lieferstA shortlist with licence notes

  AI Foundations·Llama, Mistral, Qwen, DeepSeek

• BuilderLab2.5 std.

  Running AI Models Locally

  Learn to run models on a laptop or single server with Ollama and llama.cpp, with realistic expectations.

  du lieferstA local model serving your own tool

  Deployment & Operations·Ollama, llama.cpp

• BuilderModule3 std.

  Introduction to Hugging Face

  Learn to use models, datasets and pipelines from the Hugging Face Hub in working code.

  du lieferstA pipeline built from hub components

  Machine Learning·Hugging Face

• ArchitectLab3.5 std.

  Serving Open Models with vLLM

  Learn to serve open models at scale, covering throughput, batching, KV cache and cost per million tokens.

  du lieferstA benchmarked serving stack

  Deployment & Operations·vLLM

• ArchitectCase3.5 std.

  Building a Self-Hosted AI Stack

  Learn to design a fully self-hosted or air-gapped AI architecture, and what you take on by doing so.

  du lieferstAn architecture meeting an air-gap requirement

  Deployment & Operations·vLLM, pgvector

• BuilderModule2.5 std.

  Open Source Embeddings and Rerankers

  Learn to build a retrieval stack with no external API calls, and compare it to hosted alternatives.

  du lieferstA retrieval stack with no external calls

  Retrieval & RAG·BGE, E5

• BuilderModule3 std.

  The AI-Native Software Lifecycle

  Learn how each phase of software delivery changes when agents write most of the code, from requirements through to maintenance.

  du lieferstA map of your own lifecycle

  AI-Native SDLC & Harness·keine tools

• BuilderModule2.5 std.

  From Vibe Coding to Agentic Engineering

  Learn the difference between prompting your way to code and engineering a system that produces it, and work out where your team actually sits.

  du lieferstA placement of your team on the spectrum

  AI-Native SDLC & Harness·keine tools

• BuilderCase2.5 std.

  The Factory Model

  Learn to treat your output as the system that produces code rather than the code itself, covering specifications, agents, quality gates and feedback.

  du lieferstA written design for your delivery system

  AI-Native SDLC & Harness·keine tools

• BuilderModule3 std.

  Harness Engineering Fundamentals

  Learn why an agent is a model plus a harness, and what the harness is made of: instructions, tools, sandboxes, orchestration, hooks and observability.

  du lieferstA harness diagram for one team

  AI-Native SDLC & Harness·Claude Code, Cursor

• BuilderLab3 std.

  Writing Rule Files for Agents

  Learn to write the instruction files that define how an agent behaves in your codebase, and to keep them short enough to stay effective.

  du lieferstA reviewed rule file in your repository

  AI-Native SDLC & Harness·Claude Code, AGENTS.md

• BuilderLab3 std.

  Building Skills as Shared Capability

  Learn to turn engineering standards, workflows and debugging practice into reusable skills rather than prompts people copy between chats.

  du lieferstA packaged skill your team installs

  AI-Native SDLC & Harness·Claude, Agent Skills

• BuilderModule2.5 std.

  Rules, Policies and Constraints

  Learn the difference between deterministic rules such as naming conventions and organisational policies such as data handling and approval requirements.

  du lieferstA rule and policy set for one team

  AI-Native SDLC & Harness·keine tools

• ArchitectModule3 std.

  Treating Context as Code

  Learn to version, review and lint the context your agents run on, so that specifications, rules and outputs stay consistent with each other.

  du lieferstA versioned context repository

  AI-Native SDLC & Harness·Spec Kit, Git

• BuilderLab3 std.

  Specification Design for Agents

  Learn to write specifications precise enough for an agent to execute without clarification, and to spot the ambiguity that causes rework.

  du lieferstA specification an agent completed unaided

  AI-Native SDLC & Harness·Spec Kit

• BuilderLab3.5 std.

  Building the Agent Loop

  Learn the loop at the centre of every agent, covering perceive, plan, act, observe and iterate, by building one without a framework.

  du lieferstA working loop you wrote yourself

  AI-Native SDLC & Harness·Python, Claude

• ArchitectLab3.5 std.

  Loop Engineering

  Learn to control how an agent iterates, using termination conditions, deterministic quality gates, and feedback that pushes the agent back on course.

  du lieferstA loop with working quality gates

  AI-Native SDLC & Harness·Claude Code, CI

• ArchitectLab3.5 std.

  Graph Engineering for Agent Workflows

  Learn to model work as a graph of nodes and edges rather than a single loop, covering branching, joins, shared state and parallel execution.

  du lieferstA graph running work in parallel

  AI-Native SDLC & Harness·LangGraph, Python

• BuilderModule2.5 std.

  Conductor and Orchestrator Modes

  Learn the two ways developers work with agents, hands on in real time and asynchronously across several agents, and when to switch between them.

  du lieferstA written split of the two modes

  AI-Native SDLC & Harness·Claude Code, Cursor

• BuilderModule3 std.

  Human in the Loop Orchestration

  Learn to run a supervised chain of agents through planning, implementation, testing and review, with clarifications flowing through a person.

  du lieferstAn orchestration flow with approval points

  AI-Native SDLC & Harness·Claude Code

• ArchitectLab3.5 std.

  Autonomous Multi-Agent Orchestration

  Learn to run agents in parallel that coordinate through shared context, and to recognise when this is genuinely better than one agent.

  du lieferstA parallel workflow with shared state

  AI-Native SDLC & Harness·Claude, subagents

• ArchitectLab3 std.

  Hooks and Deterministic Guardrails

  Learn to run your own code at fixed points in an agent's lifecycle, before a tool call, after an edit or before a commit, for the things agents forget.

  du lieferstA hook set enforcing your standards

  AI-Native SDLC & Harness·Claude Code, hooks

• ArchitectModule3 std.

  Agent Sandboxing and Isolation

  Learn to contain what an agent can reach, covering isolation layers, the threats each one addresses, and how agents escape when containment is weak.

  du lieferstA sandbox design with named threats

  AI-Native SDLC & Harness·Containers, Claude

• ArchitectLab3.5 std.

  Evaluating the Harness

  Learn to evaluate the system around the model across four layers, from reviewing skills for conflicts through to measuring whether real tasks succeed.

  du lieferstA four layer evaluation suite

  AI-Native SDLC & Harness·LLM judge, CI

• ArchitectModule3.5 std.

  Agent Memory Architecture

  Learn how agent memory develops from simple project files through structured indexes to semantic retrieval, and how to choose the level you need.

  du lieferstA memory design for your team

  AI-Native SDLC & Harness·Claude Code, memory

• ArchitectModule3 std.

  Feedback Loops and Harness Improvement

  Learn to turn production usage into signal that improves the system, using human corrections, evaluation results and retrieval tuning.

  du lieferstA improvement loop with measured gain

  AI-Native SDLC & Harness·Evals, telemetry

• BuilderLab3 std.

  Connecting Agents to Your Toolchain

  Learn to give agents access to the systems they need to plan, build and ship, covering source control, tickets, design files and pipelines.

  du lieferstThree connected internal systems

  AI-Native SDLC & Harness·MCP, GitHub, Jira

• ArchitectModule3 std.

  Running Agents in Parallel

  Learn the practical options for supervising many agents at once, and the coordination problems that appear as soon as you run more than a few.

  du lieferstA working parallel setup

  AI-Native SDLC & Harness·Claude Code, tmux

• BuilderCase3 std.

  The Economics of Agentic Engineering

  Learn why casual prompting is cheap to start and expensive to run, and how upfront investment in context and tests reverses that.

  du lieferstA cost model for your team

  AI-Native SDLC & Harness·keine tools

• ArchitectModule2.5 std.

  Intelligent Model Routing

  Learn to send each task to the cheapest model that can complete it, and to measure what routing saves without losing quality.

  du lieferstA router with a measured saving

  AI-Native SDLC & Harness·Gateways

• BuilderModule2.5 std.

  The Eighty Percent Problem

  Learn why agents produce most of a feature quickly and then stall on edge cases and integration, and where to direct human attention instead.

  du lieferstA written boundary for your codebase

  AI-Native SDLC & Harness·keine tools

• BuilderModule3 std.

  Reviewing Code You Did Not Write, at Volume

  Learn to keep review meaningful when most code is generated, covering what to read closely, what to automate, and how to avoid rubber stamping.

  du lieferstA review process that scales

  AI-Native SDLC & Harness·GitHub, Claude

• BuilderModule3 std.

  Redesigning QA for the AI Lifecycle

  Learn how quality assurance shifts from running tests to owning the evaluation system that decides whether work can ship.

  du lieferstA test strategy with automated gates

  AI-Native SDLC & Harness·CI, evals

• BuilderModule2.5 std.

  Release Management with Automated Gating

  Learn to move release decisions from manual sign off to automated gates, and to decide which gates a human still has to hold.

  du lieferstA release process with defined gates

  AI-Native SDLC & Harness·CI/CD

• ArchitectCase2.5 std.

  Building a Platform Team for AI Engineering

  Learn to set up the team that owns the shared harness, covering what it builds, what it standardises and how it keeps the path easy to follow.

  du lieferstA team charter and golden path

  AI-Native SDLC & Harness·keine tools

• BuilderCase2.5 std.

  Starting an AI Engineering Programme

  Learn to start with a pilot rather than a mandate, covering how to choose the first team, build the sandbox and grow adoption from results.

  du lieferstA pilot plan with success criteria

  AI-Native SDLC & Harness·keine tools

• BuilderModule3 std.

  Cloud-Native DevSecOps Foundations

  Learn how security moves into every stage of delivery in a cloud-native pipeline, and where AI genuinely helps rather than adding noise.

  du lieferstA map of your current pipeline

  Cloud-Native DevSecOps·keine tools

• BuilderLab2.5 std.

  Auditing Your Delivery Pipeline

  Learn to audit a pipeline for the stages where security is manual or missing entirely, and to rank the gaps by risk rather than by ease.

  du lieferstA gap list ranked by risk

  Cloud-Native DevSecOps·CI/CD

• BuilderLab2.5 std.

  Catching Secrets Before They Are Committed

  Learn to detect hardcoded credentials and insecure patterns in the editor and at commit time, before they reach a repository.

  du lieferstScanning running on every commit

  Cloud-Native DevSecOps·Git, IDE plugins

• BuilderModule3 std.

  AI-Assisted Code Scanning

  Learn how contextual scanning cuts false positives by telling test credentials from production ones, and how to tune it for your stack.

  du lieferstA scan with a reduced false positive rate

  Cloud-Native DevSecOps·SAST tools

• BuilderLab3 std.

  Securing Infrastructure as Code

  Learn to scan Terraform, Helm and CloudFormation for misconfiguration, and to separate deliberate overrides from genuine mistakes.

  du lieferstScanning across your templates

  Cloud-Native DevSecOps·Terraform, Helm

• BuilderModule2.5 std.

  Container and Registry Security

  Learn to audit images continuously against known vulnerabilities, and to keep base images current without blocking delivery.

  du lieferstA registry with continuous auditing

  Cloud-Native DevSecOps·Docker, registries

• ArchitectLab3.5 std.

  Kubernetes Runtime Security

  Learn to establish behavioural baselines for workloads, detect anomalies at runtime, and generate network policies from observed traffic.

  du lieferstBaselines and policies for one cluster

  Cloud-Native DevSecOps·Kubernetes

• ArchitectLab3 std.

  Admission Control and Policy as Code

  Learn to express security policy as code and enforce it at admission, so non-compliant workloads never reach the cluster.

  du lieferstPolicies blocking non-compliant workloads

  Cloud-Native DevSecOps·OPA, Kubernetes

• ArchitectModule3 std.

  Behavioural Threat Detection

  Learn to detect threats by deviation from normal behaviour rather than by signature, and to keep alert volume low enough to be useful.

  du lieferstA detection baseline with alert rules

  Cloud-Native DevSecOps·CWPP tools

• ArchitectLab3.5 std.

  Building an AI Security Pipeline

  Learn to assemble security into every pipeline stage in the right order, from editor and commit through build, deploy and runtime.

  du lieferstA pipeline secured end to end

  Cloud-Native DevSecOps·CI/CD, scanners

• ArchitectModule3 std.

  Securing an AI-Written Codebase

  Learn what changes when most of your code is generated, covering review depth, dependency choices and the vulnerabilities agents repeat.

  du lieferstA control set for generated code

  Cloud-Native DevSecOps·keine tools

• ArchitectModule3 std.

  Autonomous Security Response

  Learn to let agents act on security findings within firm limits, covering what they may remediate alone and what always needs a person.

  du lieferstA response playbook with defined limits

  Cloud-Native DevSecOps·SOAR, agents

• BuilderModule4 std.

  Deep Learning with Keras and TensorFlow

  Learn to build and train neural networks with Keras and TensorFlow, and understand where they differ from PyTorch in practice.

  du lieferstA trained network

  Machine Learning·Keras, TensorFlow

• BuilderLab4 std.

  Computer Vision with Deep Learning

  Learn to build models that work on images, covering convolutional networks, transfer learning and data augmentation.

  du lieferstAn image classifier with a measured accuracy

  Machine Learning·PyTorch, Keras

• BuilderModule3.5 std.

  Sequence Models and Recurrent Networks

  Learn how models handle ordered data such as text and time series, and why transformers largely replaced recurrent networks.

  du lieferstA working sequence model

  Machine Learning·PyTorch, Keras

• BuilderModule4 std.

  Reinforcement Learning Foundations

  Learn how an agent learns from reward rather than labelled examples, covering environments, policies, value functions and exploration.

  du lieferstAn agent that learns a task

  Machine Learning·Gymnasium, Python

• ArchitectLab4 std.

  Deep Reinforcement Learning

  Learn to combine reinforcement learning with neural networks, and understand why these systems are unstable and expensive to train.

  du lieferstA trained deep RL agent

  Machine Learning·PyTorch, Gymnasium

• BuilderModule4 std.

  Natural Language Processing Foundations

  Learn the text processing techniques that still matter alongside language models, covering tokenisation, entities, classification and topic modelling.

  du lieferstA working text pipeline

  Machine Learning·spaCy, Python

• BuilderLab2.5 std.

  Tracking Experiments with MLflow

  Learn to record parameters, metrics and artefacts for every training run, so results can be compared and reproduced later.

  du lieferstA tracked set of experiments

  Machine Learning·MLflow

• ArchitectModule3 std.

  Scaling Model Training

  Learn to train larger models across multiple GPUs, covering distributed strategies, mixed precision and checkpointing.

  du lieferstA training job across several GPUs

  Machine Learning·PyTorch Lightning

• BuilderLab3.5 std.

  Serving AI Models with FastAPI

  Learn to put a model behind an API that can handle real traffic, covering request validation, async handling, timeouts and containers.

  du lieferstA deployed inference endpoint

  Building AI Applications·FastAPI, Docker

• OperatorModule2.5 std.

  Building Custom Assistants and GPTs

  Learn to build a configured assistant for a specific job without writing an application, and to know when this is not enough.

  du lieferstA published internal assistant

  Building AI Applications·OpenAI, Claude

• BuilderCase2.5 std.

  Choosing an Agent Framework

  Learn what the main agent frameworks actually differ on, and how to choose one without rewriting your system six months later.

  du lieferstA framework decision with reasoning

  Building AI Applications·LangChain, LlamaIndex, CrewAI, Haystack

• BuilderModule3 std.

  Vector Search in Your Existing Database

  Learn to add vector search to the database you already run, and to judge when a dedicated vector store is genuinely worth adding.

  du lieferstVector search running on your own database

  Retrieval & RAG·Postgres, MongoDB, Elastic

• BuilderLab3 std.

  Generative AI in Snowflake

  Learn to run generative AI next to your data in Snowflake, covering built in functions, cost control and keeping data in place.

  du lieferstAn AI workflow running in the warehouse

  Retrieval & RAG·Snowflake

• BuilderLab3 std.

  Building AI Agents in Snowflake

  Learn to build agents that answer questions against warehouse data, with the access controls your data team will require.

  du lieferstAn agent answering questions over warehouse data

  Retrieval & RAG·Snowflake

• BuilderModule3 std.

  AI on Databricks

  Learn to build and serve AI workloads on Databricks, covering notebooks, model serving and governance across the lakehouse.

  du lieferstA working pipeline on Databricks

  Retrieval & RAG·Databricks

• OperatorModule2.5 std.

  AI in Business Intelligence Tools

  Learn to use the AI features built into business intelligence tools for summaries, natural language queries and anomaly detection.

  du lieferstAn AI assisted report

  Retrieval & RAG·Power BI, Tableau

• OperatorCase2.5 std.

  Choosing Your AI Coding Tools

  Learn what actually separates the main AI coding tools, and how to choose for your team rather than by preference or habit.

  du lieferstA tool decision for your team

  AI for Software Engineering·Cursor, Windsurf, Copilot, Claude Code

• GroundLab2.5 std.

  Rapid Prototyping with AI App Builders

  Learn to build a working prototype from a description using AI app builders, and to recognise when it must be rebuilt properly.

  du lieferstA working prototype

  AI for Software Engineering·Replit, v0

• OperatorModule3 std.

  AI for Consulting

  Learn to use AI across research, analysis, slide production and client deliverables, with the quality checks the work requires.

  du lieferstA client deliverable produced end to end

  AI for Business Functions·Claude, Copilot

• GroundModule2 std.

  AI Ethics

  Learn the ethical questions AI raises at work, covering fairness, consent, displacement and accountability, using real cases rather than abstractions.

  du lieferstA written position on three real dilemmas

  AI Foundations·keine tools

• BuilderModule2.5 std.

  Responsible AI Data Management

  Learn to manage the data behind AI responsibly, covering consent, purpose limitation, retention and what happens when someone asks for deletion.

  du lieferstA data handling standard for AI use

  Governance & Compliance·keine tools

• OperatorCase2.5 std.

  AI Business Models and Monetisation

  Learn how organisations actually make money from AI, covering direct products, embedded features, cost reduction and where margins disappear.

  du lieferstA monetisation model for one AI product

  Leadership & Strategy·keine tools