Recruitment Pipeline

Recruitment Pipeline defines a Growth-stage Acquire workflow from application through screening, interview, offer and hiring. Give each stage a clear exit criterion and record transition dates so stalled candidates are visible. Add scoring only when interviewers need a shared comparison scale. The field model supports candidate contact details, role, department, source, resume reference, experience, salary expectations, interview records and the eventual hired-employee relation. It describes the hiring process and requested empty artifacts rather than performing applicant assessment.

The default deliverable is a short recommendation. An explicit setup, build or conversion request produces artifacts after essential missing facts are resolved. Advice receives a direct answer, while a review works from the material provided. This keeps the size of the proposed setup tied to the requested outcome.

Use it for hiring trackers, applicant spreadsheets and interview scorecards when teams cannot see where candidates are stuck. It does not send emails, schedule interviews, parse resumes or compute KPIs. Human review is required for hiring decisions.

This is an empty-template workflow, not processing of real employee or customer records. Automation, reminders and synchronization require the separate integration layer. Sensitive decisions and adjustments require qualified human review before anything is acted on.

Establish open role count, departments and applicant volumes; interview rounds, interviewers and decision owner; scores versus comments, CV storage and timeline capture; the current spreadsheet or applicant tracking system and delays; and whether pipeline visibility, time-to-hire information or both are needed. Questions are asked one at a time, excluding anything already answered in earlier messages. Unknown facts stay unknown. Intent, confirmed facts, open questions and requested formats remain internal unless the user asks to inspect them; no missing answer is invented.

The field model includes Candidate Name (text); AI Match Score (number); Department (text); Email (email); Experience (Years) (number); Hired Employee (relation); Interview Date (date); Interview Score (number); Interviewer (text); Notes (long_text); Notice Period (text); Offered Salary (currency); Currency (text); Phone (text); Position (text); Applied Date (date); Rec ID (id); Resume URL (url); Salary Expectation (currency); Source (text); Stage (select).

Stage starts with Applied, Screening, Interview, Offer, Hired, Rejected, Withdrawn.

AI Match Score, Interview Date, Interview Score and Offered Salary may be absent before their lifecycle stage or without verified evidence. AI Match Score is optional supplied data, not an instruction to score applicants: require its method, scale and provenance or leave it blank. Never infer suitability from protected traits or proxies. Notion maps Email as Email and Resume URL as URL; Hired Employee links the employee master record.

Requested CSV, SQL DDL, JSON Schema and Notion mappings derive from one field list. Display names remain identical across CSV and JSON, and normalized SQL identifiers are documented. Relation fields keep their relational meaning, dates remain dates and money remains currency. Machine-readable data is separated from explanation, with validation failures and limitations reported separately.

One supplied SQL example is:

CREATE TABLE recruitment_pipeline (
  candidate_name VARCHAR(255),
  ai_match_score NUMERIC,
  department VARCHAR(255),
  email VARCHAR(255),
  experience_years NUMERIC NOT NULL,
  hired_employee VARCHAR(255),  -- relation -> target record
  interview_date DATE,
  interview_score NUMERIC,
  interviewer VARCHAR(255),
  notes TEXT,
  notice_period VARCHAR(255),
  offered_salary NUMERIC(14,2) NOT NULL,
  currency VARCHAR(255),
  phone VARCHAR(255),
  position VARCHAR(255),
  applied_date DATE NOT NULL,
  rec_id SERIAL PRIMARY KEY,
  resume_url TEXT,
  salary_expectation NUMERIC(14,2) NOT NULL,
  source VARCHAR(255),
  stage VARCHAR(100) NOT NULL,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

Excel-compatible CSV uses UTF-8 with a byte order mark. Because CSV has no column types, numeric, date and currency formatting is identified after the data. A CSV is not an .xlsx workbook; the latter is generated only when requested. Example rows require an explicit request and must be clearly synthetic. Sensitive identifiers are not unnecessarily repeated in a review, and generated templates remain empty.

Notion output goes to notion-manual-import for the CSV, property mapping, import steps and verification checklist. Manual mappings require no connection. Requested workspace changes require verified tool access, the actual target and authorization; a claimed connection is insufficient evidence. Notion relation columns resolve only after both databases have been imported. Select options are an initial vocabulary that can be renamed to match the business. people-directory supplies the related employee master record; notification-reminder-hub is the separate due-date reminder module. Personal identifiers and sensitive financial details stay out of generated templates.