MARKET RESEARCH

Turn rising competitor review topics into Linear feature-gap issues

Reads the fastest-growing positive review topics for competitor apps from BigQuery and opens deduplicated Linear issues for any praised capability your team doesn't already track.

CategoryMarket Research
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionQuery fastest-growing positive topics per appGoogle BigQueryBigQuery
  • LogicKeep capability topics, drop already-tracked ones
  • ActionCreate feature-gap issue per topicLinearLinear
  • OutputPost opened-issues digest to SlackSlack

What it does

Mines what users are increasingly praising about competitor apps and converts those into actionable product signals. It pulls the topics gaining the most positive share in BigQuery, filters to ones representing capabilities (not generic praise), checks them against existing issues, and files a Linear issue describing the gap with supporting review quotes and the trend data.

When to use it

Use it when product and competitive intel should feed the roadmap directly — instead of a PM manually reading reviews, the workflow proposes feature-gap candidates backed by evidence. Best run weekly into a triage-labeled Linear project.

How it works

  1. 1A weekly schedule starts the run.
  2. 2A BigQuery query returns topics with the largest positive-sentiment share growth per competitor app.
  3. 3A logic step filters to capability-type topics and drops ones already covered by an existing issue.
  4. 4For each surviving topic, a Linear issue is created with the trend numbers, top quotes, and a triage label.
  5. 5A digest of the issues opened is posted to Slack for the product team.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect LinearIssues, projects, cycles, triage.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  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.