MARKET RESEARCH

Sector cross-competitor guidance rollup

On a quarterly schedule, gathers the latest transcripts for every competitor in a sector, extracts each one's guidance direction.

CategoryMarket Research
Enginesim
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerQuarterly schedule over peer list
  • ActionFind + scrape each competitor transcriptFirecrawl
  • ActionExtract guidance direction + themes per callOpenAI
  • LogicAggregate into raised/held/cut ranking, cluster themes
  • ActionDraft comparison narrativeOpenAI
  • OutputPublish sector rollup brief to NotionNotionNotion

What it does

Builds the sector-wide picture in one pass. Instead of one competitor at a time, it loops your full peer set, scrapes each latest transcript, extracts the direction of every guidance change, and rolls the results into a single Notion brief: a raised-vs-cut leaderboard plus the macro themes (pricing, demand softness, AI capex) that management teams repeated across calls.

When to use it

Run it once a quarter after the sector has largely reported, when you need a board-ready "state of the competitive set" rather than a single-name note.

How it works

  1. 1A quarterly schedule starts the rollup over the configured peer list.
  2. 2For each competitor, Exa finds the latest transcript and Firecrawl scrapes it.
  3. 3OpenAI extracts guidance direction and pulls candidate themes per call.
  4. 4A logic step aggregates directions into a raised/held/cut ranking and clusters shared themes across competitors.
  5. 5OpenAI drafts the comparison narrative from the aggregated table.
  6. 6A formatted brief with the leaderboard and theme cluster is published as a Notion page.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect ExaNeural search across the web.
  2. 2
    Connect FirecrawlCrawl, scrape, structured extract.
  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.