← All runbooks
gooseworks-ai / playbooks-outbound-prospecting-engine

Outbound Prospecting Engine

End-to-end outbound prospecting: detect intent signals, research companies, find decision-maker contacts, personali

agent codexmodel gpt-5.5snapshot python312-uveval programmatic11 stepsv1.0.0

Deploy Outbound Prospecting Engine 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

11 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    1. Create results_dir and confirm it is writable.
    2. Load the client context, ICP, signal keywords, and any approved messaging.
    3. Confirm access to the selected signal sources, contact enrichment workflow, contact cache, and outreach platform.
    4. Initialize validation_report.json with setup status and an empty stage list.
  2. 2
    Step 2

    Define Signal Sources

    Select the signal sources that best match the client's ICP and sales motion. Include at least one source and prefer multiple independent intent signals when available.

  3. 3
    Step 3

    Run Signal Detection

    Execute the selected signal workflows with the client-specific keywords. Run sources in parallel when tooling allows. Preserve the source, company name, signal date, signal text, URL, and the reason the signal matters.

  4. 4
    Step 4

    Qualify and Score Leads

    Use `lead-qualification` to filter the raw signal list against the ICP. Score leads consistently:

  5. 5
    Step 5

    Find Decision-Maker Contacts

    For top qualified companies, use `company-contact-finder` to find the specific decision makers named by the ICP. Capture target title, name, company, email address, LinkedIn URL, source URL, and confidence.

  6. 6
    Step 6

    Deduplicate Against Contact Cache

    Use `contact-cache` to check all leads against previous outreach history. Add new contacts to the cache, skip contacts or companies already contacted within the configured cooldown, and record the deduplication decision in the contacts output.

  7. 7
    Step 7

    Personalize Outreach

    Generate a personalized 2-3 message sequence for each lead or segment using:

  8. 8
    Step 8

    Launch Campaign

    Use `cold-email-outreach` or the selected campaign tool to create the campaign, upload the approved lead list, configure the sequence, allocate mailboxes, and set the sending schedule.

  9. 9
    Step 9

    Monitor and Iterate (max 3 rounds)

    Review open rates, reply rates, positive reply rate, meeting bookings, bounces, unsubscribes, and account-quality feedback. Run at most 3 rounds of iteration in a single execution: adjust subject lines, improve the why-now hook, refine segmentation, and add new leads from fresh s

  10. 10
    Step 10

    Ongoing Cadence

    Document the operating cadence for the client:

  11. 11
    Step 11

    Final Checklist

    Before finishing, run this verification script and fix any failure: