Search & explore

• Level L05
• T02
• 20 min read

When 150 people use one assistant, its doors, budgets and records are yours to run. Put everyone behind the organisation's login, end a leaver's access with one tested action, give each group a budget, keep lean records, and hand it all to a substitute.

Matching textT02-L05 · Chat & assistants · Level 5 Operator · 20-minute read, plus 5 hours of doing Run One Assistant for a Whole Institute or Company, and Hand It Over Two people left, their access

• Level L04
• T02
• 20 min read

Start Open WebUI with Heidelberg AI Desk on one machine, connect a local model or a provider key, and learn where every prompt goes. Then do the Level 4 part: decide who can reach the assistant, how accounts are approved, and which data it may see, before colleagues log in.

Matching textT02-L04 · Chat & assistants · Level 4 Integrator · 20-minute read, plus 120 minutes of doing A Self-Hosted Assistant Your Team Can Use Safely Everyone wants the chat, nobody asked who can reach…

• Level L03
• T02
• 18 min read

Turn one recurring team question into a shared assistant: current sources only, pinned instructions and model, use and edit rights kept apart, and a test set that runs before every change goes live. It passes when your deputy updates a source, reruns the tests and publishes without you.

Matching textT02-L03 · Chat & assistants · Level 3 Builder · 16-minute read, plus 3 hours of doing Build a Shared Assistant Your Team Can Test and Take Over The answer from last year's manual A

• youtube
• 9 min video

Prompt and improve an answer through follow-up. General introduction, not the complete request framework.

Matching textT02-L01: See how a follow-up corrects an assumption in Claude's first draft. Then practise changing one thing at a time and checking the result against your notes. T02-L02: See how Claude Projects…

• youtube
• 14 min video

Run local models and understand the API endpoint. Not Open WebUI/Heidelberg AI Desk; older models; free title not total-cost/privacy evidence.

Matching textT02-L04: Learn how Ollama downloads a model and exposes a local API. The examples use older models; follow the book for Open WebUI connections and keeping the model port off the network.

• youtube

Scope gateway keys and set budgets. Logging/guardrails explicitly not covered despite title. No endorsement of shared-key practices.

Matching textT02-L05: See how LiteLLM scopes model access and sets budgets on gateway keys. Local-model prices are simulated; follow the book for per-person access and logging. Guardrails are mentioned, not…

One-page diagram to use with T02-L02, "Set Up Projects a Colleague Can Pick Up".

One-page diagram to use with T02-L04, "A Self-Hosted Assistant Your Team Can Use Safely", and 2 more books.

One-page diagram to use with T02-L02, "Set Up Projects a Colleague Can Pick Up".