LISA
LISA is an AI Assistant in Conducttr specialised in writing directly into the MEL. Designers can utilise LISA in AXS as well as the Sidekick side panel in the Editor.
LISA dramatically reduces the time it takes to create an exercise
Create injects on the fly with instant MEL updates
LISA helps to overcome the creative berrier
With Sidekick, work without switching between AXS and the Editor
Quickly transforms a storyline into a MEL using an ISO 22398 structure
LISA understands and generates content in multiple languages
Continuity of work in Sidekick
Creates a 3-act MEL
AXS
Talking to LISA
LISA will ask for additional information and confirmation if you don't provide enough detail. She does this to ensure the best results.
Have a conversation
In the example below, LISA is asking about the player role. This is because although the user has given details of a flood in Slovenia, the exercise would be quite different if played by e.g. a bank in Slovenia vs a local authority.

The user has added details and LISA lists what she has, asking for confirmation.

Sidekick
You can use LISA in Sidekick too, an AI-powered sidebar featured in the Editor. Based on your conversations, LISA will write directly into the MEL.

Chatting with LISA
Provide clear context of the scenario
Make sure to tell LISA:
What scenario you'd like to build
Who is involved
What the scenario should avoid
As is best practice with all AI tooling, the clearer your input the better LISA's results will be. Here's an example prompt:
I want to design an exercise about a severe weather scenario — a coastal depot facing flood risk from an incoming storm. Those involved are: the internal crisis team (this will be the players), the depot duty manager, dispatch/drivers, the comms teams, and the regional director/board. Please avoid adding any hazard types, avoid resolving or escalating to casualties/major damage.
Add attachments
LISA accepts:
PDFs
Images (JPG, PNG)
PPT
Docs (TXT, DOCX)
Attach anything from full exercise specifications, policies, or even just a draft of your ideas. LISA will use the provided info to develop your MEL.
Experiment before LISA generates
Just like an intern, LISA doesn't always get it right first time. If she makes a mistake, correct her!
Go back and forth with LISA during the first few messages (we call this discovery mode). This way you can experiment before LISA locks in your scenario idea and starts generating your serials and injects.
After this, it's best to avoid drifting away from the original context or topic of the scenario. This can result in LISA generating more generic or mixed results.
Last updated
Was this helpful?


