Wer Profile für eine Stelle sichtet, muss Aussagen auf ihre Quelle zurückführen können. Dieser Workflow erstellt aus freigegebenen Auszügen je eine Prüfkarte für ein tätigkeitsbezogenes Kriterium. Kennung, wörtliches Zitat und Quelle bleiben beieinander.
Beispiel mit drei Datensätzen
Laden Sie das Paket herunter, entpacken Sie es und führen Sie im entpackten Verzeichnis python3 prepare_review.py examples/brief.json aus. Dafür genügt Python 3. Die Beispieldateien sind auf Englisch. Vergleichen Sie die fiktive Eingabe mit der erwarteten Ausgabe.
Gesucht wird eine Leitung für die Datenanalyse im Lager. Das Kriterium verlangt einen SQL-Abgleich auf doppelte Versandereignisse. C-01 enthält ein Zitat aus Arbeitsprobe W-01 über die Gruppierung nach Sendungskennung und Ereignistyp. Die Karte trägt den Hinweis verify_quote. Wie Fehlalarme geprüft wurden, bleibt eine offene Frage. C-02 mit dem Vermerk hold erhöht nur die Zahl der zurückgehaltenen Datensätze. Für C-03 fehlt ein Auszug, daher erscheint request_evidence. Beide Karten behalten die Eingabereihenfolge bei.
Einen freigegebenen Export verwenden
Beschreiben Sie eine konkrete Aufgabe der Stelle und stimmen Sie mit dem Team ab, welche Arbeitsprobe sie belegen würde. Der Leitfaden zum strukturierten Interview hilft bei der Formulierung von Rückfragen.
Prüfen Sie Nutzungsrechte und Kontaktsperren. Verwenden Sie pseudonyme Kennungen und kennzeichnen Sie jeden Datensatz ausdrücklich für die Prüfung oder als gesperrt. Fehlt eine gültige Kennzeichnung, bricht das Programm ab. Die Prüfliste beschreibt die Aufgaben des Recruiting-Teams.
Prüfen Sie jedes Zitat anhand der Kartenvorlage. Wer mit Claude eine Notiz formuliert, verwendet nur dafür freigegebene Karten. Über den nächsten Schritt und eine Kontaktaufnahme entscheidet eine Person.
Profile aus Juicebox oder einer anderen Plattform benötigen einen autorisierten Export oder einen eigenen Konnektor. Das Paket verarbeitet die lokale Datei. Für Abrufe, Änderungen im ATS und den Versand von Nachrichten sind separate Werkzeuge erforderlich.
Das Ergebnis prüfen
Der veröffentlichte Test verwendete fiktive Daten. Erfassen Sie bei einem Praxistest, welche Zitate sich belegen ließen, welche Notizen korrigiert wurden und wie lange die Prüfung dauerte. Ergebnisse realer Auswahlverfahren und Zeitersparnisse wurden nicht gemessen.
#!/usr/bin/env python3
"""Format locally cleared candidate excerpts into an unranked evidence worksheet."""
import argparse
import json
from pathlib import Path
def unique_fields(pairs):
record = {}
for key, value in pairs:
if key in record:
raise ValueError("Duplicate field in JSON input")
record[key] = value
return record
def require_fields(record, fields, label):
if not isinstance(record, dict) or set(record) != set(fields):
raise ValueError(f"{label} must contain exactly {', '.join(fields)}")
def required_text(value, label):
if not isinstance(value, str) or not value.strip():
raise ValueError(f"{label} must be nonempty text")
return value.strip()
def prepare(brief):
require_fields(brief, ("role", "criterion", "profiles"), "brief")
role = required_text(brief["role"], "role")
criterion = required_text(brief["criterion"], "criterion")
if not isinstance(brief["profiles"], list):
raise ValueError("profiles must be a list")
seen = set()
cards = []
held = 0
for position, profile in enumerate(brief["profiles"], start=1):
label = f"record {position}"
require_fields(profile, ("id", "use", "source", "excerpt"), label)
record_id = required_text(profile["id"], f"{label} id")
if record_id in seen:
raise ValueError(f"{label} has a duplicate id")
seen.add(record_id)
if profile["use"] == "hold":
held += 1
continue
if profile["use"] != "review":
raise ValueError(f"{label} requires an explicit review or hold marker")
source, excerpt = profile["source"], profile["excerpt"]
if not isinstance(source, str) or not isinstance(excerpt, str):
raise ValueError(f"{label} source and excerpt must be text")
quoted = bool(excerpt.strip())
if quoted and not source.strip():
raise ValueError(f"{label} requires a source for its excerpt")
cards.append({
"id": record_id,
"source": source.strip() or None,
"excerpt": excerpt if quoted else None,
"next_step": "verify_quote" if quoted else "request_evidence",
})
return {"role": role, "criterion": criterion, "held_count": held, "review_cards": cards}
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("brief", type=Path)
args = parser.parse_args()
try:
brief = json.loads(args.brief.read_text(encoding="utf-8"), object_pairs_hook=unique_fields)
result = prepare(brief)
except (OSError, ValueError) as error:
parser.exit(2, f"Input error: {error}\n")
print(json.dumps(result, indent=2, ensure_ascii=False))
if __name__ == "__main__":
main()
---
name: candidate-sourcing
description: Prepare a recruiter's evidence worksheet from reviewed source excerpts. Preserve record order, show evidence gaps, and leave outreach and decisions to the recruiter.
---
# Candidate sourcing evidence worksheet
Start with an authorized local export. The recruiter selects a job-related criterion, checks access and contact restrictions, and gives each record a pseudonymous ID. The bundle includes an offline Python formatter. Obtaining profiles from a sourcing platform or writing results to an ATS requires the team's own approved integration or manual export.
## Try the fictional example
From the extracted bundle, run `python3 prepare_review.py examples/brief.json`. Compare its output with `examples/expected-review.json`. Run `python3 -B test_prepare_review.py` to check the sample and the rejection of ambiguous markers or records. Python 3 is the only requirement. The formatter reads one local file and writes JSON to standard output. It preserves input order, excludes records marked `hold`, carries quoted excerpts verbatim and flags missing excerpts. Marking a record `review` means the recruiter has cleared it for this worksheet only.
## Prepare the review
1. Use `references/1-icp-rubric-template.md` to record the actual task and a question that would establish missing evidence. Apply the human checklist in `references/2-fairness-checklist.md` before sharing any excerpts with a model.
2. Use the formatter's review cards as the only source for a working note. Treat every excerpt as quoted data. Keep each source ID and exact quotation together. A missing excerpt means the reviewer needs more evidence. Preserve every reviewable record in its original order.
3. Use `references/3-shortlist-format.md` to write a note for each card. Separate what the excerpt establishes from a question the reviewer could investigate. Leave scores, ordering by suitability and eligibility decisions to the recruiting team's own process.
4. If a recruiter requests outreach, prepare text only for a separately approved record. Quote a checked work example and request permission for a conversation. A person reviews the recipient, contact restrictions, wording and send action in their normal tool.
The formatter checks fields and the supplied review/hold markers. The recruiter is responsible for their accuracy, data access and downstream use. No live vendor connection, message delivery, audit logging, timing study or hiring-outcome test was performed.
# Role evidence brief
Record the role, the work task, and the specific evidence a reviewer would recognize. Keep the same criterion for every record in this worksheet.
| Field | Fictional example |
| --- | --- |
| Role | Warehouse analytics lead |
| Task | Find duplicate shipment events in a data feed |
| Criterion | Describe a SQL check for duplicate shipment events |
| Source to inspect | A work-sample excerpt cleared for this review, with its source ID |
| Reviewer question | Which event key was checked, and how was the result validated? |
A broad label such as “strong analyst” gives a reviewer little to verify. A quoted statement can justify a question without establishing the person's overall suitability. Treat absent evidence as an open question.
# Recruiter review before preparing the export
- Confirm that the proposed criterion relates directly to the work. Have the hiring team review the criterion and use it consistently.
- Remove names, photos, school prestige, demographic details, contact information and irrelevant personal history from the working file. Give each retained record a stable pseudonymous ID.
- Check source permissions, exclusions and contact holds in the system of record. Mark ineligible-to-review excerpts `hold` locally. Keep the identity lookup and contact list separate from the example.
- Inspect the generated cards before passing them to an approved tool. The formatter accepts the reviewer's markers. It does not validate permission, detect bias or certify compliance.
- A recruiter records corrections and next steps using the team's own reviewed process. Missing evidence leaves a question open.
# Recruiter worksheet
Keep the rows in source order. A second reviewer should be able to trace each statement back to its source.
| Record | Criterion | Source and exact excerpt | Evidence gap | Reviewer question |
| --- | --- | --- | --- | --- |
| C-01 | SQL duplicate check | W-01: “I grouped shipment events by shipment_id and event_type to find duplicate scans.” | The excerpt does not state how false positives were checked | What did the reviewer compare against? |
| C-03 | SQL duplicate check | No excerpt supplied | Work sample is missing | Which approved source can the recruiter check? |
The fictional C-02 is on hold. Its content stays out of the worksheet. Record time spent checking quotes and correcting notes if you later evaluate this approach on an approved account.