Resources / What’s new

What’s new in HosPortal

The substantial new things we have built, and why we built them. Smaller improvements are listed in the release notes.

November 2026 / In its first allocation round at a large Western Sydney public hospital

AI term preferences for trainee doctors

Collect every trainee’s term and leave preferences, apply the training and workforce rules, and build a complete year of term allocations in minutes.

Line drawing: trainee doctors with ranked preferences on the left, a grid of term allocations filling in, a list of rules being ticked, and the roster the allocations flow into

01 / What it is

One place for the whole term allocation

Each year a hospital has to place its first and second year doctors into a sequence of terms. The Term Preference Module does that in one place.

Trainees rank the terms they want and the leave they would like. The hospital enters its terms, its positions and its rules. HosPortal’s AI then builds a complete set of allocations for the whole cohort, and the Medical Workforce team reviews, adjusts and publishes it.

02 / Why we built it

It looks like matching. It is closer to Sudoku.

Allocating junior doctors to terms can look simple: collect preferences, assign the positions, publish. In practice every placement changes what is left for everyone else, so the whole year has to be worked out together.

Each doctor needs a sequence of terms that gives the right breadth of clinical experience. Each term has a number of positions. There are specialty and subspecialty limits, service terms such as relief and nights, clinical pathways, and leave that several doctors want at once.

Most hospitals still do this with generic forms, spreadsheets and weeks of manual checking. The first hospital to use it manages about 143 junior doctors. Across a Local Health Network, the number in rotation planning can exceed 600.

03 / What is different

It builds the allocation, and it is joined to the roster

Most hospitals do this with forms, spreadsheets and weeks of checking. We do not know of another rostering system that builds the allocation itself.

  • The whole cohort is solved together. Not one doctor at a time, with the awkward cases left to the end.
  • The rules are part of the build. Prevocational training requirements, PGY1 and PGY2 rules, and specialty, subspecialty and service-term limits are applied while the allocation is worked out, not checked afterwards.
  • Leave is solved with the terms. Leave preferences are placed in the same pass, so a term can move to keep someone’s leave in one piece.
  • Fairness is measured, not hoped for. The build spreads disappointment across the cohort and limits how much any one doctor carries.
  • It carries on into the roster. A doctor’s term decides where they can be rostered. The published allocation flows into HosPortal rostering, so nothing is typed in twice.
  • People stay in control. The team can fix any placement and build again around it, and nothing is published until they say so.

Term allocation is a good example of work that looks simple until you understand everything a hospital has to balance.

Dr Chris Jones, practising anaesthetist and founder of HosPortal

04 / Under the hood

An exact solver, not a guess

The allocation is worked out by a constraint solver, not written by a language model. Every possible placement, each doctor in each block of the year in each term, becomes a yes-or-no decision. Every rule becomes arithmetic over those decisions: how many terms of a kind, a minimum or maximum number of days, a share of the year, enough different specialties, and the head count each term can take from each year group. The solver then searches for the set of decisions that breaks no rule and costs the least.

What “costs the least” means

  1. Fill every position first. Then give everyone their minimum leave, then meet each term’s staffing target, and only then weigh preferences. A preference never outranks an empty position.
  2. One bad result counts for more than two mild ones. The cost of a placement grows with the square of how far down the doctor’s list it is, so disappointment is spread across the cohort instead of landing on a few people.
  3. Nobody carries the worst of it. The build also keeps down the total cost carried by the single worst-off doctor.
  4. A doctor who ranks nothing is not a free square. They are treated as holding a middle preference for everything.

Leave, half terms and what is already fixed

Leave requests become blocks that the solver places in the same pass as the terms, with limits on how many people can be away in the same week. Terms that split a block of the year in two, terms a doctor already holds from an earlier allocation, and placements the team has fixed by hand are all taken into account.

When the rules cannot all be met

Sometimes they cannot. The solver then finds the smallest set of rules that cannot hold together, relaxes them in a set order, and builds again. Every rule it relaxed is reported to the team. Nothing is dropped silently.

Every answer is checked twice

Before any draft is written, a separate rule engine rechecks the solver’s answer against every rule. A build takes minutes.

Ready to simplify your healthcare rostering?

Start saving time, improving communication, and optimising your hospital operations today with HosPortal's proven rostering solution.