← All runbooks
gooseworks-ai / capabilities-job-posting-intent

Job Posting Intent Detection

Detect buying intent from job postings. When a company posts a job in your problem area, they've allocated budget and are actively thinking about the problem. This skill finds those companies, qualifies them, extracts personalization context, and outputs…

agent codexmodel gpt-5.5snapshot python312-uveval programmatic8 stepsv1.0.0

Deploy Job Posting Intent Detection to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

The shape of the run

8 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶

    Create the output directory, install runtime dependencies, and verify required secrets before running any paid search.

    mkdir -p /app/results
    python -m pip install --quiet requests apify-client pandas pydantic
    
    if [ -z "${APIFY_API_TOKEN:-}" ]; then
      echo "ERROR: APIFY_API_TOKEN is required" >&2
      exit 1
    fi
    

    Source setup notes:

  2. 2
    Step 2

    Define the Search Intent

    ▶

    Convert the operator's ICP into explicit title, problem-area, and location filters. Treat job postings as budget signals: the hiring company has allocated headcount, acknowledged the problem, and is…

  3. 3
    Step 3

    Estimate Cost

    ▶

    Estimate Apify spend before execution and stop if the estimate exceeds max_cost. Write the estimate into the validation report so reviewers can audit paid API usage.

  4. 4
    Step 4

    Run the Search

    ▶

    Run the search only after setup and cost validation pass. Save both qualified results and raw payloads when requested.

  5. 5
    Step 5

    Qualify and Export Leads

    ▶

    For each candidate company, record signal strength, reasoning, likely decision makers, outreach angles, and personalization context. If Google Sheets export is enabled, create or update the sheet and…

  6. 6
    Step 6

    Validate Outputs

    ▶

    Validate that every mandatory artifact exists, that JSON outputs parse, and that lead records include company, job title, source URL, qualification reasoning, and signal strength.

  7. 7
    Step 7

    Iterate on Errors (max 3 rounds)

    ▶

    If setup, execution, export, or validation fails, inspect the specific failure, apply one targeted fix, and rerun validation. Stop after max 3 rounds and write the unresolved issue to…

  8. 8
    Step 8

    Write Summary

    ▶

    Write /app/results/summary.md with the query parameters, cost estimate, number of postings inspected, number of qualified leads, Google Sheet URL or skip reason, and any manual follow-up needed.