MARKET: Recruitment — Screening & Interview Pipeline

examples/46-market-recruitment.halo policies |* parallel |! people
Automate resume screening, skills matching, culture assessment, interview scheduling, and hiring manager notification. Replaces Lever/Greenhouse automation rules with a single declarative pipeline.
Open in the playground →
halo
// ============================================================
// MARKET: Recruitment — Screening & Interview Pipeline
// PURPOSE: Automate resume screening, skills matching, culture
//          assessment, interview scheduling, and hiring manager
//          notification. Replaces Lever/Greenhouse automation
//          rules with a single declarative pipeline.
// ============================================================

// --- Policies ---
policy BiasProtection : Block(DiscriminatoryLanguage) & Block(AgeDiscrimination)
policy CandidatePII   : Redact(SSN) & Redact(CreditCard) & Redact(Location)
policy CostGuard      : MaxSpend(1.00)

// --- Tools ---
tool ATSAPI        : REST("api.lever.co/v1/opportunities", apiKey: Env.LEVER_KEY)
tool CalendarAPI   : REST("www.googleapis.com/calendar/v3", apiKey: Env.GOOGLE_CAL_KEY)
tool HRSlack       : POST("hooks.slack.com/services/hiring-team")

// --- Store ---
tool RoleRequirements : VectorStore(Env.PINECONE_KEY, namespace: "job-descriptions")
tool PastHires        : VectorStore(Env.PINECONE_KEY, namespace: "successful-hires")

// --- Struct ---
schema CandidateDecision {
  candidate_name   : String
  match_score      : Number
  skills_gap       : Array
  culture_fit      : String
  recommendation   : String
  interview_slot   : String
}

// --- Agents ---
agent Screener [openai/gpt-4o-mini, temp: 0.0]
  requires BiasProtection, CandidatePII, CostGuard

agent CultureAssessor [anthropic/claude-sonnet-4, temp: 0.2]
  equips PastHires
  requires BiasProtection, CandidatePII, CostGuard

agent HiringCoordinator [openai/gpt-4o-mini, temp: 0.3]
  equips RoleRequirements, CalendarAPI
  requires CostGuard

// --- The Pipeline ---
@timeout(3m)
@retry(2, 5s)
pipeline ScreenCandidate(application: CandidateApplication) -> CandidateDecision:
  application
    // Step 1: Parallel assessment — skills match + culture fit
    |* {
         Screener.match_skills(
           resume: context.data.application.resume_text,
           role_id: context.data.application.role_id,
           required_skills: context.data.application.job_skills,
           years_required: context.data.application.min_experience
         ),
         CultureAssessor.assess_fit(
           cover_letter: context.data.application.cover_letter,
           values_statement: context.data.application.values,
           team_culture: context.data.application.team_id,
           past_successful_hires: PastHires
         )
       }

    // Step 2: Gate — reject if skills match is too low
    |? (context.data.match_skills.score < 40)

    // Step 3: Synthesize recommendation
    |> HiringCoordinator.recommend(
         skills: context.data.match_skills,
         culture: context.data.assess_fit,
         role: context.data.application.role_id,
         salary_band: context.data.application.salary_expectation
       )

    // Step 4: Gate — auto-reject if recommendation is "no"
    |? (context.data.recommend.decision == "reject")

    // Step 5: Gate — auto-advance top candidates
    |? (context.data.match_skills.score > 85)
    |> HiringCoordinator.schedule_interview(
         tool: CalendarAPI,
         candidate_email: context.data.application.email,
         interviewer_id: context.data.recommend.interviewer,
         duration: "45m",
         type: "technical"
       )

    // Step 6: Notify hiring manager for borderline candidates
    |> HRSlack.post(
         message: "📋 New candidate screened",
         candidate: context.data.application.name,
         role: context.data.application.role_title,
         match_score: context.data.match_skills.score,
         culture_fit: context.data.assess_fit.rating,
         recommendation: context.data.recommend.decision
       )

    // Step 7: Human decision for borderline candidates
    |! yield(
         HRSlack,
         context.data.recommend,
         [context.data.match_skills, context.data.assess_fit],
         48h
       )
    ~> listen(HRSlack.Reaction)

    // Step 8: If approved, push to ATS
    |> ATSAPI.post(
         event: "CANDIDATE_ADVANCED",
         candidate_id: context.data.application.candidate_id,
         stage: "interview",
         recommendation: context.data.recommend
       )
MARKET: Recruitment — Screening & Interview Pipeline ​

MARKET: Recruitment — Screening & Interview Pipeline
