Structural decisions with evidence
Show the role-level basis for a design or headcount decision instead of defending a judgement call.
— Organisation & Workforce
Answer an inbound employee relations question accurately: the relevant clauses pulled from your own policy library, checked against current employment regulation, with a ready-to-send reply, a case note and an escalation flag when the sources do not cover it.
30–45 minutes → ~3 minutes
For one query answered from your own sources
No coding required
— USE CASES
Show the role-level basis for a design or headcount decision instead of defending a judgement call.
Apply the same criteria to every part of the organisation in scope, so functions are genuinely comparable.
Re-run against updated org data each cycle and see what actually moved.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Roles are sorted into your categories using the same rules each time, which is what makes a large volume of org data and role documentation readable.
Each role is assessed against criteria you control and weight, so the same standard applies to every role in the organisation in scope.
All of your org data and role documentation is processed as one set, so patterns across documents surface instead of being read one file at a time.
Current external sources on the organisation in scope are researched during the run rather than recalled from training data, and every source travels with the output.
Work on the organisation in scope normally means pulling org data, role documentation and headcount exports together by hand, then applying a standard that only exists in the head of whoever is doing it. Structural decisions with evidence is the typical trigger — show the role-level basis for a design or headcount decision instead of defending a judgement call. Get it right and the conclusion holds up in the room; get it rushed and it gets picked apart. Either way it costs roughly 30–45 minutes of experienced attention.
As a Skill, the work is already sequenced. You bring the evidence, and the run produces a role-level view of the organisation in scope with the reasoning attached plus a roll-up for leadership at the level you report at. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. The practical effect: 30–45 minutes of manual work becomes a ~3 minutes run, held to an identical standard on the tenth engagement as on the first.
Employee relations query responder exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Location strategy builder
Score a shortlist of locations against your own weighted criteria, stress-test the cost case, and hand the board a ranked recommendation with a full audit trail.
Employee engagement & culture diagnostic
Hundreds of free-text survey comments in — a theme-by-theme sentiment read by department, what actually drives the overall mood, and an action plan out. No one hand-codes a comment.
Workforce capacity planner
Demand, headcount, absence and productivity in — the FTE gap under base, P50, P90 and stress scenarios out, team by team, with a hiring plan the numbers support.