Screening & Candidate Shortlisting

CONTEXT
You will be provided with an Evidence Extraction Table and the original candidate resumes it was derived from.

TASK
Compare each evidence entry in the table 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 Table that maps each candidate’s application evidence to the must-have criteria for the role.

TASK
For each candidate, generate a summary card that consolidates the evidence into a concise profile. Each card should state the candidate’s overall strength against the criteria, highlight the strongest evidence, and note any criteria with weak or missing evidence.

OUTPUT FORMAT
For each candidate, use this structure:

### [Candidate Identifier]
- **Overall Fit**: [Strong Fit / Moderate Fit / Weak Fit]
- **Strongest Evidence**: 2–3 bullet points citing the most compelling criterion-evidence pairs
- **Gaps or Weak Areas**: 1–2 bullet points noting criteria with Partial or No Evidence ratings
- **Screening Note**: One sentence summarizing the recruiter’s overall impression

EXAMPLE
### Candidate A
- **Overall Fit**: Strong Fit
- **Strongest Evidence**:
  - Technical Skills: "Led migration of three legacy systems to cloud infrastructure" (Resume)
  - Experience: "8 years in enterprise platform engineering" (Resume)
- **Gaps or Weak Areas**:
  - Core Competencies: No evidence of stakeholder management experience
- **Screening Note**: Strong technical profile with a gap in stakeholder-facing experience.

CONSTRAINTS
Do not introduce qualifications or evidence not present in the Verified Evidence Table. Do not rank or recommend candidates — summary cards are descriptive only.

CONTEXT
You will be provided with a Verified Evidence Table showing each candidate’s evidence against the must-have criteria.

TASK
Produce a Risk & Gaps Log that identifies every instance where a candidate has Partial or No Evidence against a must-have criterion. Group findings by criterion so reviewers can see which requirements are hardest to fill across the candidate pool.

OUTPUT FORMAT
Use a markdown structure with two sections:

**By Criterion**
For each criterion with gaps, list affected candidates:
- **[Criterion Name]**: [Candidate A — No Evidence], [Candidate B — Partial]

**By Candidate**
For each candidate with gaps, list the criteria:
- **[Candidate Identifier]**: [Criterion 1 — Partial], [Criterion 2 — No Evidence]

CONSTRAINTS
Do not include candidates or criteria with Strong evidence ratings — this log covers risks only. Do not recommend actions or mitigations.

CONTEXT
You will be provided with a Verified Evidence Table, Candidate Summary Cards, and a Risk & Gaps Log for a set of screened candidates.

TASK
Assign each candidate to one of three shortlist buckets — Advance, Hold, or Decline — based solely on the strength of evidence against the must-have criteria. Produce a Draft Shortlist Table with a brief rationale for each placement.

OUTPUT FORMAT
Use a markdown table with columns:
- **Candidate** — candidate identifier
- **Bucket** — [Advance / Hold / Decline]
- **Strong Criteria Count** — number of criteria rated Strong
- **Gap Count** — number of criteria rated Partial or No Evidence
- **Rationale** — one sentence explaining the bucket placement, citing the key evidence or gap

Sort the table: Advance candidates first, then Hold, then Decline.

CONSTRAINTS
Do not use subjective impressions — every bucket placement must trace to evidence in the Verified Evidence Table. Do not introduce information beyond the provided inputs.

CONTEXT
You will be provided with a Draft Shortlist Table and specific feedback from the hiring manager on bucket adjustments.

TASK
Update the shortlist table based on the feedback to produce the final Shortlist Table (Buckets/Ranked). Adjust bucket placements and rationales as directed.

OUTPUT FORMAT
Use a markdown table with the following columns:
- **Candidate** — candidate identifier
- **Bucket** — [Advance / Hold / Decline]
- **Strong Criteria Count** — number of criteria rated Strong
- **Gap Count** — number of criteria rated Partial or No Evidence
- **Rationale** — one sentence explaining the bucket placement, citing the key evidence or gap
- **Change** — [No Change / Moved from X to Y] indicating any adjustment from the draft

Sort the table: Advance candidates first, then Hold, then Decline. Mark any rows changed from the draft with the adjustment reason from the hiring manager feedback.

CONSTRAINTS
Do not change bucket placements unless explicitly instructed in the feedback. Do not remove candidates from the table — only reassign buckets.