Weekly lookalike target account list for outbound sales

Every Monday at 8am, build a fresh lookalike target account list and hand it to sales as a ranked outbound shortlist.

Step 1. Find our best recent customers. In HubSpot, use Search Deals to pull closed-won deals from the last 90 days above a minimum amount (default $10,000). For each matching deal, follow the association to the company and collect the unique set of company domains. This is the seed set of accounts that represent the kind of customer we want more of.

If the seed set is heterogeneous (mixed segments, very different sizes, very different industries), reason about which seeds best represent our ideal customer profile and prioritize those. Do not blindly use every domain.

Step 2. Find lookalikes. Call CompanyEnrich Find Similar Companies with the prioritized seed domains and reasonable firmographic filters (size band, geography, industry). Pick those filter defaults from the seed set itself. Ask for the 50 most relevant candidates.

Step 3. Dedupe against the CRM. For each candidate domain, run HubSpot Search Companies to check whether a company with that domain already exists. Drop any candidate that does. We only want net-new prospects.

Step 4. Enrich the survivors. Call CompanyEnrich Enrich Company by Domain on each surviving candidate to attach firmographics: headcount, industry, location, revenue band, tech stack signals, and anything else useful for ranking.

Step 5. Filter out bad fits. Skip candidates that look like consultancies, agencies, holding companies, parent-company shells, or other clear mismatches before writing anything to the CRM. Use the enrichment data plus your own judgment.

Step 6. Create the records. For each remaining lookalike, use HubSpot Create Company to create a new company record with the enriched properties (name, domain, industry, headcount, location, revenue). Set a custom property called lookalike_source_account pointing to the seed customer the candidate was matched from, so reps can see exactly why it was suggested.

Step 7. Notify sales. Use Slack Bot Send a Message to post a digest to the prospecting channel (default #prospecting) summarizing the top 10 newly created lookalikes ranked by AI-judged fit. For each one include the company name, a link to the new HubSpot record, the seed customer it was modeled on, and a one-line rationale explaining the match. Keep the message scannable: a ranked list, not a wall of text.

Trigger: cron, every Monday at 08:00 in the workspace's local timezone. Integrations used: HubSpot, CompanyEnrich, Slack Bot.

Additional information

What does this prompt do?

Pulls your best closed-won customers from the last 90 days out of HubSpot so the workflow knows what a good-fit account actually looks like.
Finds 50 lookalike companies that match those winners on size, industry, and geography, then drops anyone already in your CRM.
Adds each net-new account to HubSpot tagged with the existing customer it was modeled on, so reps know exactly why it showed up.
Posts a ranked top 10 to a Slack channel every Monday morning with a short rationale per account so sales can grab the list and start outreach.

What do I need to use this?

A HubSpot login with permission to read deals and read/write companies.
A CompanyEnrich account and API key (their dashboard generates one in a minute).
A Slack workspace and the channel where you want the weekly digest posted.

How can I customize it?

Change the schedule (Tuesday at 7am, daily instead of weekly) or shorten the 90-day lookback window.
Tighten what counts as a 'best customer': minimum deal amount, which deal stages count as a win, target headcount band, geography, or industry.
Pick a different Slack channel, post to multiple channels by region, or change how many lookalikes show up in the top-ranked digest.

Frequently asked questions

How does it decide which customers are my 'best' ones?

It looks at closed-won deals in the last 90 days above a minimum amount you set (default $10,000). You can change the stages, the lookback window, or the amount threshold at any time.

Will it add companies we already work with?

No. Before creating anything in HubSpot, the workflow checks your CRM for an existing record on that domain and skips any match, so only true net-new prospects get added.

What stops it from adding consultancies or holding companies?

The agent reviews each candidate before writing to the CRM and skips agencies, consultancies, holding companies, and other clear mismatches. You can also add your own exclusion rules.

How many new accounts get created each week?

Up to 50 lookalikes per run, minus anything already in your CRM and anything filtered out as a bad fit. The Slack digest highlights the top 10 by AI-judged fit so sales has a clear shortlist.

Can my reps see why a company was suggested?

Yes. Every new HubSpot company is tagged with the existing customer it was modeled on, and the Slack post includes a one-line rationale for each top 10 pick.