MARKET RESEARCH

On-demand competitor review teardown

Triggered by a webhook with a competitor app ID, scrapes a large sample of its reviews, builds a themed strengths-and-weaknesses teardown, and returns a shareable Notion page.

CategoryMarket Research
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWebhook with competitor app IDHTTP webhook
  • ActionScrape deep review sampleApify
  • ActionCluster into complaint and praise themesOpenAI
  • ActionWrite structured teardown narrativeOpenAI
  • OutputPublish teardown as Notion pageNotionNotion

What it does

Fire this on demand for any competitor: pass an app ID and it scrapes a deep sample of that app's reviews, clusters both complaints and praise into themes, and assembles a one-page teardown — top weaknesses, top loved features, and notable verbatim quotes — published as a Notion page you can drop into a deal review or strategy doc.

When to use it

Use it for ad-hoc research: prepping a competitive battlecard, evaluating a new entrant, or answering a sales question about how a rival's users feel. It's the manual, deep-dive counterpart to the scheduled trackers.

How it works

  1. 1A webhook trigger receives a competitor app ID and store.
  2. 2Apify scrapes a large recent review sample for that app.
  3. 3OpenAI separates reviews into complaint themes and praise themes, ranks each by volume, and pulls representative quotes.
  4. 4A second OpenAI pass writes a structured teardown narrative from the themed data.
  5. 5The teardown is published as a formatted Notion page and the page URL is returned in the webhook response.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect ApifyActors, scrapers, datasets.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect NotionPages, databases, comments.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.