LEAD GENERATION

AI-Qualified Account Discovery from Brave to Salesforce

Discovers companies via Brave keyword search, then an agent researches each one and writes only ICP-qualified accounts into Salesforce with a fit summary and score.

CategoryLead Generation
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule fires
  • ActionBrave Search watchlist keywords for candidatesBraveBrave Search
  • ActionAgent researches each company and scores ICP fit
  • LogicGate on ICP score threshold
  • ActionCreate qualified Salesforce leads with fit summarySalesforce
  • OutputPost new-qualified-account digest to SlackSlack

What it does

This is an agent-driven pipeline that goes beyond raw search hits. It pulls candidate companies from Brave Search on your watchlist keywords, then a research agent investigates each one (what they do, size signals, recent activity), scores it against your ICP definition, and creates a Salesforce lead only for the ones that clear the bar.

When to use it

Use it when raw search results are too noisy to dump into your CRM and you want a research-qualified queue, not a link dump. Ideal for teams whose ICP is nuanced (vertical, stage, tech stack) and can't be captured by a keyword filter alone.

How it works

  1. 1A daily schedule starts the run.
  2. 2Brave Search returns candidate companies for each watchlist keyword.
  3. 3The agent researches each company and drafts a one-paragraph fit summary plus an ICP score.
  4. 4A logic step gates on the score threshold, discarding low-fit companies.
  5. 5Qualified accounts become Salesforce leads carrying the fit summary, score, and source keyword.
  6. 6A digest of new qualified accounts is posted to Slack for the rep to action.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Brave SearchWeb, news, image, video search.
  2. 2
    Connect SalesforceAccounts, opportunities, cases.
  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.