— Talent & Leadership
Synthesises year-end performance ratings, objectives and manager commentary into an evidence-led assessment of goal attainment, rating consistency and priorities for the next review cycle.
3–4 weeks → ~40 minutes
For a full population, not a sample
No coding required
— USE CASES
Identifies gaps between manager ratings and objective evidence, alongside self-versus-manager differences. Highlights unsupported ratings and cases with missing ratings or evidence for focused calibration discussions.
Compares average ratings and distributions across managers and departments, making potential leniency, severity and skew visible without treating those patterns as proof of bias.
Shows rating movement from the prior year alongside current goal attainment and supporting commentary, helping reviewers assess whether changes have a clear evidential basis.
Connects commentary themes and tone to the behaviours being described, using the organisation’s performance framework or a standard framework. Gives reviewers a structured view of qualitative evidence alongside ratings.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Each row of your export is processed on the same basis, so no signal is skipped however long the table is.
Movement across the market being watched is visualised from the computed data, so the trend is legible at a glance.
Findings on the market being watched are written up as a document that reads like professional output, with each claim tied back to a signal.
Detail rows are summarised into the grouped view of the market being watched without losing the underlying signals.
Year-end performance reviews combine numerical ratings with commentary that varies in detail, tone and evidential support. In practice it shows up as preparing for rating calibration: identifies gaps between manager ratings and objective evidence, alongside self-versus-manager differences. Highlights unsupported ratings and cases with missing ratings or evidence for focused calibration discussions. It is the kind of work that decides whether a recommendation survives scrutiny — and the kind that quietly eats 3–4 weeks of senior time whenever it comes round.
As a Skill, the work is already sequenced. You bring the evidence, and the run produces performance review synthesis report with reference-only individual identification plus goal attainment measures and rating-versus-evidence gaps. The judgement is built in — how items are broken up, what standard they are held to, and where the run stops for a human review. Net effect: 3–4 weeks down to ~40 minutes, no drift between runs, and every conclusion traceable back to the evidence behind it.
Performance review synthesis 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.
Builds evidence-backed employee skills profiles within HR systems, mapping documented experience to the organisation’s skills catalogue and assigning proficiency levels using consistent rules.
Assesses how clearly people explain their technical work against a consistent four-level rubric, producing a human-approved report with quoted evidence behind every score.
Reveals how organisational culture is lived through anonymous employee accounts, producing an evidence-backed diagnostic of shared themes, differences between functions and gaps between values and practice.
Turns a high-potential's assessment evidence into an acceleration plan weighted to real experience and exposure, naming the stretch assignments, mentors and programmes that will compound fastest.
Builds a calibrated, reusable benchmark from source material so every later screen, shortlist or review is graded against the same bar.
Screens candidate evidence against a saved Blueprint, applying the same calibrated bar and traceable reasoning to every applicant.
