Turning “off sick tonight” into an updated nurse roster
Absence messages read, checked against the ward's staff and skills, and turned into roster changes — with a manager pulled in only when the message is unclear

These figures match the published metrics on the Predictim GenOR-Twin product page — this walkthrough is a composite scenario, not a specific engagement.
Absence messages read, checked against the ward's staff and skills, and turned into roster changes — with a manager pulled in only when the message is unclear
Segment: Hospital nurse rostering
The roster lives in a scheduling model; the disruptions live in messages, calls and handover notes. A ward manager has to translate each one by hand, often at night, and either patch the roster locally or rebuild it — without much time to check whether the patch quietly breaks a skill-mix or rest-time rule somewhere else.
How the approach works
Read the message, propose the constraint
A message like “night nurse on ward 4 off sick tonight” is translated into a constraint the rostering model understands — this person, this shift, unavailable — with a confidence score attached.
Checked before it touches the roster
The proposed constraint is validated against the ward's knowledge graph: the staff member exists on that ward, the shift is in the future, and the change is physically possible. In offline validation, this layer caught 88.2% of the incorrect extractions a language model produced on highly ambiguous messages.
A response sized to the problem
If cover exists within the roster's slack, it's a local repair. If not, or if a critical skill would be missing, the roster is fully re-optimized. If the system isn't confident it understood the message, a manager checks that one interpretation instead of rebuilding the roster.
Nurse scheduling is one of the six problem types GenOR-Twin was validated on. The figures above come from that published evaluation: 299 of 300 annotated logs translated exactly as experts read them, and planners working with the system picked the right type of response 98.0% of the time, against 79.5% working alone.
Related reading
Repair or Re-Optimize? Choosing How Hard to React When a Schedule Breaks
When a disruption hits a live schedule, there are two instinctive reactions: patch it, or rebuild it. Both are right some of the time. The skill is knowing which one the situation calls for — and deciding that quickly.
ReadNurse Rostering When the Absences Arrive by Text Message
Nurse rosters are built carefully weeks in advance and then rebuilt, piece by piece, from messages that arrive at 5 a.m. The planning model is rarely the weak point. Getting the message into it is.
ReadLet the LLM Translate, Not Solve: How Shift Notes Become Safe Scheduling Constraints
Most schedule disruptions arrive as a sentence, not a data field. Large language models can read that sentence. They should not be trusted to plan around it — and they don't need to be.
ReadOther use cases
All use cases
A cost contingency you can defend when the risk assessments disagree
View
When the consensus says 0.25%, and one claim says otherwise
View
Cutting damage claims and load time across a multi-site grocery network
ViewReady to optimize your operations?
Talk to our technical team about your operational challenge. An engineer replies within 72 hours, Monday to Friday.