← All runbooks
gooseworks-ai / composites-battlecard-generator

Battlecard Generator

Research one named competitor across public website messaging, reviews, ads, social/community signals, and pricing, then produce an opinionated sales battlecard for competitive deals. The battlecard should help a rep understand where to lead, where not to…

agent codexmodel gpt-5.5snapshot python312-uveval programmatic6 stepsv1.0.0

Deploy Battlecard Generator 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

6 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶
    1. Create /app/results if it does not exist.
    2. Verify the required inputs are present: your product name, your product URL, competitor name, and competitor URL.
    3. Initialize research_notes.md, evidence.json, battlecard.md, summary.md, and validation_report.json.
    4. Record the run timestamp and the public URLs that will be researched.
  2. 2
    Step 2

    Intake

    ▶

    Collect and normalize:

  3. 3
    Step 3

    Competitor Research

    ▶

    Fetch the competitor homepage, pricing page, about page, and primary product pages. Search for positioning phrases such as "we help", "the only", "unlike", case studies, and customer stories.

  4. 4
    Step 4

    Competitive Analysis

    ▶

    Build a strengths and weaknesses matrix across feature areas, pricing, ease of use, support, integrations, onboarding, and strategic fit. Identify:

  5. 5
    Step 5

    Generate Battlecard

    ▶

    Write /app/results/battlecard.md with these sections:

  6. 6
    Step 6

    Iterate on Errors (max 3 rounds)

    ▶

    Run validation after the first draft. If required files, source citations, pricing caveats, or battlecard sections are missing, revise the artifacts and re-run validation. Stop after max 3 rounds and…