Promotion / Calibration Panels

CONTEXT
You will be provided with a Promotion Evidence Matrix and the original performance review packs it was derived from.

TASK
Compare each evidence entry in the matrix against the original source document. Flag any entry where the quoted evidence cannot be found in the source, is materially paraphrased, or is attributed to the wrong candidate.

OUTPUT FORMAT
Return a markdown table with columns:
- **Candidate** — candidate identifier
- **Criterion** — the criterion in question
- **Status** — [Confirmed / Corrected / Removed]
- **Note** — explanation of any correction or removal

CONSTRAINTS
Do not add new evidence that was not in the original extraction. Only confirm, correct, or remove existing entries.

CONTEXT
You will be provided with a Verified Evidence Matrix mapping multiple promotion candidates to the same set of promotion criteria, each with strength ratings.

TASK
Produce a Comparative Case Analysis that places all candidates side by side for each promotion criterion. For each criterion, summarize the relative strength of evidence across candidates so the panel can see where cases diverge.

OUTPUT FORMAT
Structure the output as follows:

For each criterion, use a section header and a markdown table:

### [Criterion Name]
| Candidate | Strength | Key Evidence Summary |
|---|---|---|
| [Candidate A] | [Strong/Partial/No Evidence] | One-sentence summary of evidence |

After all criteria sections, include a **Summary Heat Map** — a single table with candidates as rows and criteria as columns, each cell showing [S / P / N] for Strong, Partial, or No Evidence.

CONSTRAINTS
Do not rank or recommend candidates — this step is purely comparative. Do not introduce evidence not present in the Verified Evidence Matrix. Do not editorialize about candidate potential.

CONTEXT
You will be provided with a Verified Evidence Matrix and a Comparative Case Analysis for promotion candidates being reviewed by a calibration panel.

TASK
Produce a Justification Strength Report that flags every candidate-criterion pair where the evidence is Partial or No Evidence, and identifies candidates whose overall case relies on fewer than half the criteria having Strong evidence. Highlight inconsistencies where a candidate is Strong on one criterion but has No Evidence on a closely related criterion.

OUTPUT FORMAT
Structure the output in three sections:

**1. Weak Evidence Flags**
A markdown table with columns:
- **Candidate** — candidate identifier
- **Criterion** — the weak criterion
- **Current Strength** — [Partial / No Evidence]
- **Risk Note** — one sentence describing why this gap matters for the promotion case

**2. Below-Threshold Cases**
List each candidate where fewer than half the criteria are rated Strong, with a count summary (e.g., "2 of 6 criteria rated Strong").

**3. Inconsistency Alerts**
List candidate-criterion pairs where strength ratings on related criteria are contradictory, with a brief explanation.

CONSTRAINTS
Do not recommend whether a candidate should be promoted. Do not fabricate risk notes — each must trace to specific evidence gaps. Do not include candidates with Strong ratings across all criteria.

CONTEXT
You will be provided with a Comparative Case Analysis and a Justification Strength Report for promotion candidates under panel review.

TASK
For each candidate, draft a calibration narrative that explains how their evidence compares to the promotion criteria and to other candidates reviewed in the same cycle. Each narrative should state the evidence basis, note any gaps flagged in the Justification Strength Report, and provide a clear recommendation category.

OUTPUT FORMAT
For each candidate, use this structure:

### [Candidate Identifier]
- **Recommendation**: [Promote / Defer with Development Plan / Do Not Promote]
- **Evidence Summary**: 2–3 sentences consolidating the strongest criterion-evidence pairs
- **Gaps Acknowledged**: 1–2 sentences noting criteria with Partial or No Evidence
- **Comparative Position**: One sentence stating how this case compares to other candidates on the shared criteria
- **Panel Discussion Point**: One question or concern the panel should address before finalizing

EXAMPLE
### Candidate A
- **Recommendation**: Promote
- **Evidence Summary**: Candidate A demonstrated Strong evidence on leadership impact ("led cross-functional initiative reducing cycle time by 30%") and technical depth ("redesigned data pipeline serving 200+ users").
- **Gaps Acknowledged**: No direct evidence of external stakeholder management, rated Partial on that criterion.
- **Comparative Position**: Strongest overall case in this cycle, with the highest count of Strong-rated criteria.
- **Panel Discussion Point**: Should the stakeholder management gap be addressed through a development plan post-promotion?

CONSTRAINTS
Do not fabricate evidence or achievements. Every claim must trace to the Comparative Case Analysis or Justification Strength Report. Do not use vague language like "shows promise" — cite specific evidence. Do not include compensation or personal details.

CONTEXT
You will be provided with Draft Calibration Narratives and specific feedback from the calibration panel on recommendation changes, additional discussion points, or evidence reassessments.

TASK
Update the calibration narratives based on panel feedback to produce the final Promotion Panel Outcomes document. Adjust recommendation categories, evidence summaries, and discussion points as directed. Add a decision rationale for any changes made from the draft.

OUTPUT FORMAT
For each candidate, use this structure:

### [Candidate Identifier]
- **Final Decision**: [Promote / Defer with Development Plan / Do Not Promote]
- **Evidence Summary**: 2–3 sentences consolidating the evidence basis
- **Gaps Acknowledged**: 1–2 sentences noting unresolved criteria gaps
- **Panel Rationale**: 1–2 sentences explaining the panel reasoning, especially where the final decision differs from the draft recommendation
- **Next Steps**: One sentence stating the immediate action

At the end, include a **Decisions Summary Table**:
| Candidate | Final Decision | Changed from Draft? | Key Rationale |
|---|---|---|---|

CONSTRAINTS
Do not change recommendations unless explicitly directed by panel feedback. Do not remove candidates from the document. Preserve the evidence trail from prior steps.