← All runbooks
gooseworks-ai / composites-competitor-intel

Competitor Intelligence

Research and monitor a defined set of competitors across public web sources, social channels, review sites, blogs, and optional Apify-backed social scraping. Build one structured profile per competitor, compare competitors against the user's company context, and translate the fin

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

Deploy Competitor Intelligence 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 the results directory and initialize empty working notes.
    2. Confirm the user supplied two to five competitors, competitor websites when available, and the user's company context.
    3. Confirm the research depth and focus areas. If any required input is missing, ask one concise clarification before starting research.
    4. Check whether APIFY_API_TOKEN is available. Treat it as optional; never fail only because social scraping is unavailable.
    mkdir -p /app/results
  2. 2
    Step 2

    Intake

    ▶

    Ask for or confirm these inputs before collecting evidence:

  3. 3
    Step 3

    Competitor Profile Research

    ▶

    For each competitor, collect evidence across the following dimensions. Prefer primary sources first and label third-party claims clearly.

  4. 4
    Step 4

    Optional Social Monitoring

    ▶

    Use Apify only when `APIFY_API_TOKEN` is available and the user requested deeper social evidence. Keep this step bounded to max 2 rounds per competitor: one collection round and one gap-fill round.

  5. 5
    Step 5

    Write Competitor Profiles

    ▶

    Write `/app/results/competitor_profiles.md` using this structure for each competitor:

  6. 6
    Step 6

    Write Competitive Landscape Summary

    ▶

    Write `/app/results/competitive_landscape.md` with positioning, content, feature, takeaway, and recommended action sections. Include comparison tables for company claims, ICP focus, price point, differentiators, blog frequency, social presence, and feature coverage.

  7. 7
    Step 7

    Ongoing Monitoring Plan

    ▶

    Write `/app/results/monitoring_plan.md`. If the user did not request recurring tracking, include a short note that monitoring was not requested and still provide a lightweight monthly checklist.

  8. 8
    Step 8

    Source Index

    ▶

    Write `/app/results/source_index.json` with one entry per source consulted. Each entry should include competitor, URL, retrieval timestamp, category, and the claim supported.

  9. 9
    Step 9

    Iterate on Evidence Gaps (max 3 rounds)

    ▶

    Run up to max 3 rounds of targeted gap filling before finalizing: