Enrich a Lead List: Claude + Make

A wedding-band booker gets inquiries from venues all over the state, and the first question is always the same: what kind of venue is this, how big, what is their deal. Answering it means opening each site, skimming the about page, and typing notes into a spreadsheet. Forty inquiries in, the notes get thin and the good leads blur together.

This build does the skimming. You keep a sheet with a Domain column. Paste one, and Make fetches the homepage, Claude reads it and fills in the industry, a one-line description, and a rough size, straight back into the row. By the time you sit down to triage, the list is already sorted.

It is the same toolkit as our other guides with one extra box: an HTTP step that grabs the homepage so Claude has something to read. We build it in Make, part of the data and research set. If you have done our web-page-to-blurb build, the fetch step will feel familiar.

What does this workflow actually do?

In one line: a domain becomes an enriched row. Make watches your sheet. When you add a domain, it fetches that company’s homepage, hands the text to Claude, and Claude writes back an industry, a short description, and a size estimate into the same row. A bare list becomes a sortable one.

A few real cases, none of them the usual ones:

• The wedding-band booker above, triaging venues by type and size at a glance.
• A sustainability consultant sorting inbound companies by industry before the first call.
• A freelance grant writer sizing up which nonprofits are worth pursuing this quarter.
• A regional food distributor qualifying new restaurant leads by cuisine and scale.

Gathering the domains is easy; they arrive on their own. Reading each site to size it up is the repetitive judgment that eats an afternoon. That is the part Claude takes.

Why use Make if Claude can already read and write?

Reasonable question. Claude is good at reading a homepage and saying, in a line, what a company does and roughly how big it is. It is not built to watch a sheet, fetch each site, and write results back into the right row. That is plumbing, and Make does plumbing.

Make handles the no-judgment steps: spotting the new domain, fetching the page, putting the answer back in place, looping down the list. Claude handles the one step that needs reading, the summary. Make is the conveyor; Claude is the analyst who reads each page. I built a version that asked the AI to manage the sheet too, and it lost track of rows; letting Make own the spreadsheet and Claude own the reading keeps it clean.

What do you need before you start?

• A Make account. The free 1,000 operations a month covers a steady stream of leads.
• A Claude API key from the console, not the chat app. See how to use Claude.
• A Google Sheet with a Domain column and empty columns for Industry, Description, and Size.
• Nothing else. The HTTP step needs no account; it fetches public homepages.

Two Make words. A scenario is the whole sheet-to-sheet automation. A module is one box. Four boxes here, because fetching the homepage is its own step.

How does the workflow work, step by step?

Four modules, left to right:

Module	App	What it does
1. Trigger	Google Sheets	Fires when you add a row with a domain
2. Fetch	HTTP	Downloads that company’s homepage
3. Brain	Claude	Reads the page and writes industry, description, size
4. Output	Google Sheets	Writes the answers back into the row

Step 1: Set up the lead sheet

Make a Google Sheet with columns: Domain, Industry, Description, Size. In Make add Google Sheets, Watch New Rows, connect your account, and point it at the sheet. This trigger fires whenever you paste a new domain.

Step 2: Fetch the homepage

Add an HTTP, Make a request module. Set the method to GET and map the URL to the Domain column from Step 1 (add https:// if your domains are bare). This downloads the homepage so Claude reads the real company, not just its address.

Step 3: Let Claude enrich it

Add a Claude module, Create a Prompt, paste your key, pick Sonnet, and map the page text from Step 2:

From this company homepage, return three fields on one line,
separated by a pipe, nothing else.
Page: {{data from Step 2}}

Industry (2-4 words) | One-line description | Size estimate
(solo, small, mid, large) based only on what the page shows.

Asking for a labeled estimate, not a hard number, stops Claude overstating what a homepage can actually tell you.

Step 4: Write it back

Add Google Sheets, Update a Row, point it at the row from Step 1, and map Claude’s three fields into Industry, Description, and Size. Now each domain you paste fills in its own row within seconds.

How do you run it and check the result?

Click Run once. Make reads a test domain, fetches the homepage, enriches it, and fills the row. When I tested this with a handful of domains, the industry and description were reliably right; the size is a read off public signals, so I labeled that column an estimate and treated it as a hint, not a fact. Tune the Step 3 prompt, then turn the scenario on so your list fills as you add to it.

After that, a raw list of domains turns into a sortable picture: who does what, and roughly how big. You go from reading every site to scanning a table, which is the whole job of triage made quick.

What does this cost to run?

Piece	Free tier	If you outgrow it
Make	1,000 operations/month free	Core plan from about $9/month
Claude API	Pay per use	One homepage read on Sonnet costs well under a cent
Google Sheets	Free	Free
HTTP	Free	Free

Each domain uses four Make operations and a sliver of Claude. A list of a hundred is four hundred operations, still inside the free plan. More on tiers in our Make guide.

What can go wrong, and how do you avoid it?

• The homepage is thin or script-only. Some sites give Claude little to read, so the enrichment is only as good as the page. A few will come back sparse.
• The size estimate overreaches. Label it an estimate; for verified firmographics, use a paid data provider, not a homepage read.
• It updates the wrong row. Make sure Step 4 updates the row from Step 1, not a fixed cell.
• Big lists burn operations fast. Add rows in batches and watch your monthly count.

This fetch-read-write pattern adapts to many jobs. More in Make AI scenarios.

How do you build this in Zapier or n8n instead?

Same four jobs, different names.

Job	Make	Zapier	n8n
Catch a new domain	Watch New Rows	New Spreadsheet Row trigger	Google Sheets Trigger node
Fetch the homepage	Make a request (HTTP)	Webhooks / Code by Zapier	HTTP Request node
Enrich it	Claude module	Claude (Anthropic) action	Anthropic node
Write it back	Update a Row	Update Spreadsheet Row	Google Sheets node

Make and Zapier are friendliest for a first build. n8n handles big lists cheaply. Compare them in Zapier vs Make vs n8n.

Frequently asked questions

Is this as good as a paid data provider?

No, and it should not pretend to be. It reads what a homepage says, which is great for a quick first read but not for verified revenue or headcount. Use a data provider for that.

What if a domain has no real website?

Claude returns sparse fields or “not found”. You can add a filter to flag rows that came back empty for a human to check.

Can it enrich from a company name instead of a domain?

A name alone is weaker, because the fetch needs a URL. If you only have names, add a search step first, then feed the top result in.

Will it overwrite my domains?

No. It writes only to the Industry, Description, and Size columns. Your domains stay put.

Is the chat app the same as the API?

Same models, different access. Make needs an API key from the console, not the chat login.

Sources and references

• HTTP module (Make Help)
• Claude API overview (Anthropic)
• Google Sheets basics (Google)
• Claude on Make (integrations)
• Lead generation — Grokipedia

Last reviewed: May 2026. Make, Claude, and Google update their interfaces; check the official pages for exact button names.

You may also like

• AI Automation for Beginners (the hub)
• Summarize any web page into a newsletter blurb
• Draft WordPress posts from a spreadsheet with Claude + Make
• Make.com Complete Beginner’s Guide
• How to use Claude AI
• n8n Complete Beginner’s Guide
• The AI Tools Directory