perf-calibration git:20260718.7c1285cA

Immutable. This exact content is served forever at /api/v1/blob/036b1ec92c7c5fb9.

---
name: perf-calibration
description: Run a performance calibration meeting so ratings across a group rest on comparable evidence and a consistent bar, not one manager's advocacy. Use when managers are finalizing performance ratings for a team or org and you need consistency and bias control before results are delivered.
---

# Performance calibration

Calibration exists because a rating set by a single manager reflects that
manager's standards, generosity, and blind spots as much as the employee's work.
Putting managers in one room to defend ratings against a shared rubric surfaces
the inconsistencies and the biases before anything reaches an employee. Done
badly, it just hands the outcome to whoever argues hardest.

## Method

1. **Bring evidence, not adjectives.** Each manager arrives with specific, dated
   examples tied to the rubric's dimensions: what was delivered, its scope, its
   impact. "She's a rock star" is not calibratable; "she owned the X launch at
   senior scope, with result Y" is. Rule out claims no one can check.
2. **Anchor every rating to the rubric level.** Read the written definition of
   each rating band and place people against it, not against each other's vibes.
   When two managers rate similar work differently, resolve it by returning to
   the anchor, so the standard is the rubric and not the room's mood.
3. **Compare like work across managers.** Line up people at the same level and
   ask whether a "meets" from one team would be a "meets" on another. This
   cross-manager comparison is the whole point: it catches the lenient grader and
   the harsh one and pulls both toward a common bar.
4. **Run bias interrupts explicitly.** Name the biases in the moment: recency
   (weighting the last month over the year), halo and horns (one trait coloring
   everything), and similar-to-me. Watch the language for patterns, such as warm
   competence words for one group and "abrasive" for another doing the same
   thing. Assign someone to call these out.
5. **Give the facilitator authority.** A neutral facilitator, often HR or a
   skip-level, keeps one loud manager from setting every rating, holds the group
   to evidence, and makes sure quiet managers' reports get equal airtime. Without
   that role, calibration rewards confidence over accuracy.
6. **Record the rationale and close the loop.** For every rating that moved,
   write down why, so the decision is auditable and the manager can deliver it
   with a straight story. Feed systematic gaps, such as a whole team rated low,
   into the next cycle instead of papering over them.

## Signals

- Could you defend any rating in the room with dated evidence a peer manager
  accepted?
- Did at least one rating change because the group challenged it, or did every
  pre-meeting number survive untouched?
- Were the bias interrupts actually voiced, or only listed on a slide?

## Boundaries

Calibration aligns ratings; it does not set the strategy of the underlying
performance system, and it cannot rescue a rubric with no clear level
definitions. Forced distributions, rating scales, and cadence are company
conventions that shape how the meeting runs, so follow yours. The individual's
evidence for advancement belongs to the promo-packet skill, and delivering the
rating to the employee is a separate conversation.