← All runbooks
gooseworks-ai / capabilities-company-contact-finder

company-contact-finder

Find decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location. This runbook converts that skill into a Jetty-comp

agent codexmodel gpt-5.5snapshot python312-uveval programmatic3 stepsv1.0.0

Deploy company-contact-finder 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.

Deploy on jetty.io →View source
The shape of the run

3 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶

    Verify the operator provided the required inputs and that Gooseworks MCP people-search tools are available in the active agent environment.

    mkdir -p /app/results
test -n "${company_name:-}" || echo "company_name must be supplied by the orchestrator"
test -n "${target_titles:-}" || echo "target_titles must be supplied by the orchestrator"

    Record the resolved company name, optional company LinkedIn URL, target titles, and requested result count before making search calls.

  2. 2
    Step 2

    Iterate on Errors (max 3 rounds)

    ▶

    If the search result set is empty or low confidence, perform at most 3 rounds of targeted recovery:

  3. 3
    Step 3

    Write Results

    ▶

    Write normalized contacts to `/app/results/contacts.json` and a concise executive summary to `/app/results/summary.md`.