MARKET RESEARCH

On-Demand Deep-Dive Brief for One App, Saved to Google Drive

Run manually for a single app: pulls its full BigQuery rank history, researches its competitor and release timeline on the web.

CategoryMarket Research
EngineSim + Paperclip
Difficultyadvanced
Triggermanual
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerManual run with target app
  • ActionQuery full rank history from BigQueryGoogle BigQueryBigQuery
  • ActionResearch competitors and release timelineBraveBrave Search
  • ActionAgent correlates inflections and reasons on causesOpenAI
  • OutputSave deep-dive brief to Google DriveGoogle DriveGoogle Drive

What it does

This is the manual, analyst-grade option. You launch it for one specific app and it does the heavy lifting: queries BigQuery for the app's complete install-rank history, then runs agent-driven research across the web to reconstruct its competitor landscape and release timeline. The agent reasons over both — correlating each notable rank inflection to a release or competitor event — and produces a structured long-form brief, saved as a formatted document in Google Drive for sharing.

When to use it

Use it when a single app warrants a real investigation — a board update, a competitive teardown, or a build-versus-watch decision — and you want depth and reasoning rather than a templated alert.

How it works

  1. 1A manual trigger starts the run with the target app as input.
  2. 2A BigQuery query returns the app's full rank history.
  3. 3An agent step researches competitors and the release timeline via web search.
  4. 4The agent correlates rank inflections to events and reasons about causes.
  5. 5The finished deep-dive brief is saved as a Google Drive document.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect Brave SearchWeb, news, image, video search.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect Google DriveDocs, sheets, slides, files.
  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.