LEAD GENERATION

Webhook-triggered Brave rising-keyword check into a Notion trend queue

When an external trend or alert tool fires a webhook with a keyword, checks Brave for current intent volume and freshness, has an LLM judge whether it's a real warm signal.

CategoryLead Generation
Enginesim
Difficultyintermediate
Triggerwebhook
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWebhook delivers candidate keywordHTTP webhook
  • ActionCheck Brave for volume and recencyBraveBrave Search
  • LogicDiscard thin or stale keywords
  • ActionJudge intent and draft recommended play (OpenAI)OpenAI
  • LogicForward only confirmed warm signals
  • OutputAppend entry to Notion trend queueNotionNotion

What it does

Turns any external signal — a trend tracker, a social listening tool, an internal alert — into a vetted entry in a Notion trend queue. It takes the inbound keyword, validates it against live Brave results, and only queues it if an LLM confirms genuine buying intent and recommends a concrete play.

When to use it

Use it when you already have a system that spots rising topics but it's too noisy to act on directly. This adds a Brave-backed validation gate so your team's Notion queue only fills with keywords worth a campaign or outreach push.

How it works

  1. 1An inbound webhook delivers a candidate keyword from your trend source.
  2. 2Brave Search checks current result volume and recency for that keyword.
  3. 3A filter discards keywords with thin or stale coverage.
  4. 4OpenAI judges whether the results reflect real buying intent and drafts a recommended play.
  5. 5A branch forwards only confirmed warm signals.
  6. 6Notion appends a queue entry with the keyword, evidence links, and recommended play.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Brave SearchWeb, news, image, video search.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect NotionPages, databases, comments.
  4. 4
    Connect HTTP webhookTrigger any URL on agent actions.
  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.