Professional learning for member companies
Short videos about tools, methods and experience. Descriptions are public; the videos themselves require access through company membership.
Watch the videos before the discussion meeting.
AI · Sprint 1
Trust the answer, not the model, not the vendor
For companies considering running AI on their own server. You learn why local AI gives control over data, cost and access, and how many agents checking each other give answers you can trust, even when a single model guesses wrong. The video shows that a server scales in two directions: how large a model it holds, and how many conversations it runs at once. It ends with a checklist of what a company should settle before it invests.
View videoAI · Sprint 2
Too much of a good thing: how context can affect answers from AI
For anyone who uses AI on models, drawings and regulations. You learn what the context is, why everything is sent again at every step of a conversation or an agent, and why more context can give worse answers. In a test with an IFC model and the Norwegian building code TEK17, the AI model approved a fire compartment that is missing a wall, in all ten runs, when it was given the whole building and the rules. Given only the room, it found the gap every time. The video ends with how to tidy the context, both by hand and with agents.
View video