← All runbooks
gooseworks-ai / composites-sponsored-newsletter-finder

Sponsored Newsletter Finder

Discover newsletters in a target niche that are relevant to the user's ideal customer profile, evaluate audience fit, estimate sponsorship cost, and produce a ranked shortlist ready for outreach. The runbook uses web research to identify candidate newsletters, scores each one aga

agent codexmodel gpt-5.5snapshot python312-uveval programmatic9 stepsv1.0.0

Deploy Sponsored Newsletter 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

9 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶
    1. Create results_dir if it does not exist.
    2. Resolve today's UTC date for output filenames.
    3. Confirm icp_definition and monthly_budget are present before research begins.
    4. If required inputs are missing, write validation_report.json with overall_passed=false, write summary.md explaining the missing inputs, and stop.
    mkdir -p /app/results
python - <<'RUNBOOK_PY'
from pathlib import Path
Path('/app/results').mkdir(parents=True, exist_ok=True)
print('Environment ready')
RUNBOOK_PY
  2. 2
    Step 2

    Intake

    ▶

    Capture the operating brief:

  3. 3
    Step 3

    Discovery via Web Search

    ▶

    Run searches from multiple angles and collect candidates with source URLs:

  4. 4
    Step 4

    Evaluate Each Newsletter

    ▶

    Score every candidate across five dimensions from 1 to 5:

  5. 5
    Step 5

    Competitive Intelligence

    ▶

    For each known competitor, search for newsletter sponsorship evidence:

  6. 6
    Step 6

    Budget Allocation Recommendation

    ▶

    Build a monthly test plan that fits the declared budget and campaign goal. Prefer a small validation test before broad rollout. Include a table with newsletter, send frequency, cost per send, planned sends per month, and monthly cost. State the recommended first test and the meas

  7. 7
    Step 7

    Generate Outputs

    ▶

    Write the final markdown report to `/app/results/newsletter-sponsors-<YYYY-MM-DD>.md` using this structure:

  8. 8
    Step 8

    Iterate on Errors (max 3 rounds)

    ▶

    If validation fails or output quality is incomplete, perform up to max 3 rounds of targeted repair:

  9. 9
    Step 9

    Final Checklist

    ▶

    Run this verification script before finishing: