MARKET RESEARCH

Quarterly Competitor Earnings Theme Brief by Email

After each earnings season, reads the quarter's stored theme data for the whole watchlist and emails a concise written brief that calls out the biggest narrative shifts…

CategoryMarket Research
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEnd-of-season schedule fires
  • ActionQuery this and last quarter's theme recordsGoogle BigQueryBigQuery
  • ActionSynthesize executive theme briefOpenAI
  • LogicValidate brief covers every watchlist company
  • OutputEmail formatted brief to stakeholdersGmailGmail

What it does

Produces the readable narrative on top of the data. Once a quarter it gathers the theme records already collected for every competitor, then writes an executive brief: who pivoted, which themes are spreading across the field, where competitors diverged, and what to watch next quarter. The finished brief lands in stakeholders' inboxes as formatted email.

When to use it

Use it when executives want a digestible end-of-season read rather than raw rows or per-call pings. Pairs naturally with a warehouse loader that already stores the structured theme data this brief summarizes.

How it works

  1. 1A schedule fires once the quarter's transcripts have all been processed.
  2. 2The flow queries BigQuery for this quarter's and last quarter's theme records across the entire watchlist.
  3. 3OpenAI synthesizes the comparison into an executive brief with a sector-wide themes section and a per-company highlights section.
  4. 4A logic step verifies the brief is non-empty and every watchlist company is represented before sending.
  5. 5Gmail delivers the formatted brief to the configured distribution list, archiving a copy for the record.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect GmailRead, draft, send, label.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.