Log Emails to Sheets: Claude + Make

A pottery studio runs its class sign-ups by email. By the time a term starts, the roster lives in two hundred messages, and building the actual class list means scrolling, copying names, and missing two. The information is all there; it is just trapped in the inbox in the worst possible shape for counting.

This build files the inbox into a sheet as it arrives. When an email lands, Claude pulls out the structured pieces, who it is from, what it is about, a one-line summary, how urgent it is, and Make writes them as a new row in Google Sheets. The roster builds itself while the term fills up.

We wire it in Make. It shares a trigger with our Gmail draft-replies guide, but instead of writing a reply, Claude does extraction: turning a messy email into clean fields a spreadsheet can hold.

What does this workflow actually do?

In one line: a new email becomes a structured row. Make watches your inbox. When an email arrives, Claude reads it and returns a set of fields, and Make writes those fields into the next empty row of your Google Sheet. The inbox becomes a list you can sort, count, and filter.

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

• The pottery studio above, watching its class roster build itself one email at a time.
• A scholarship committee logging applicant emails into a review sheet instead of a tangled inbox.
• A landscaping crew turning quote-request emails into a jobs pipeline they can sort by urgency.
• A small literary press logging manuscript submissions into a reading list with author and genre.

Collecting the emails is automatic; they already arrive. Turning each into clean, countable data is the grind. That extraction is exactly what Claude is good at.

Why use Make if Claude can already write?

Reasonable question. Claude is good at reading a loose email and pulling out tidy fields. It is not built to watch the inbox, find the next empty row, and write to the right cells. That is plumbing, and Make does plumbing.

Make handles the no-judgment steps: catching the email, writing the row, running on its own. Claude handles the one step that needs reading and structuring, the extraction. Make is the filing cabinet; Claude is the clerk who reads each letter and fills in the form. I tried asking the AI to manage the spreadsheet rows itself, and it lost track of where to write; letting Make own the sheet and Claude own the reading is what keeps the log clean.

What do you need before you start?

• A Make account. The free 1,000 operations a month covers a busy inbox.
• A Claude API key from the console, not the chat app. See how to use Claude.
• A Gmail account, ideally with one label for the mail you want logged.
• A Google Sheet with a header row: Name, Topic, Summary, Urgency, Action.

Two Make words. A scenario is the whole inbox-to-sheet automation. A module is one box. Three boxes, one scenario.

How does the workflow work, step by step?

Three modules, left to right:

Module	App	What it does
1. Trigger	Gmail	Watches the inbox and fires on each new email
2. Brain	Claude	Pulls out the fields the spreadsheet needs
3. Output	Google Sheets	Writes the fields as a new row

Step 1: Watch Gmail for new mail

Create a scenario and add Gmail, Watch emails. Connect your account and point it at the label you want logged, so the sheet does not fill with newsletters. This trigger hands the next step the sender, subject, and body.

Step 2: Let Claude pull out the fields

Add a Claude module, Create a Prompt, paste your key, pick Sonnet. The trick is to make the output trivially easy to split into columns:

Extract these fields from the email. Return them on one line,
separated by a pipe character, and nothing else.
From: {{sender from Step 1}} Subject: {{subject from Step 1}}
Body: {{body from Step 1}}

Name | Topic | One-line summary (max 12 words) | Urgency
(low/med/high) | Action needed (yes/no)

Telling Claude to return only the pipe-separated line, with a capped summary, is what keeps your columns aligned later.

Step 3: Write the row in Sheets

Add Google Sheets, Add a Row, connect Google, pick your sheet, and map each piece of Claude’s pipe-separated reply to its column. In Make you can split the reply on the pipe and drop each part into Name, Topic, Summary, Urgency, and Action. Now every email files itself into the right cells.

How do you run it and check the result?

Click Run once. Make takes a recent email, Claude extracts the fields, and a clean row appears in your sheet. Check it. When I tested this, a new email became a tidy row in seconds, and the fix that mattered was telling Claude to return only the pipe-separated fields, because its first replies wrapped the data in a friendly sentence that broke the columns. Once the rows line up, switch the scenario on.

After that, your inbox keeps a running ledger of itself. You stop scrolling to count and start sorting and filtering a real list, which for sign-ups, applications, or quotes is the whole job made easy.

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	A short extraction on Sonnet costs a fraction of a cent
Gmail	Free	Free
Google Sheets	Free	Free

Each email uses three Make operations and a sliver of Claude. Even a few hundred emails a month sit well inside the free plan. More on tiers in our Make guide.

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

• The columns misalign. Tell Claude to return only the delimited fields, no greeting or preamble. This was the one I fixed in testing.
• It logs newsletters and receipts. Filter the Gmail trigger by label so only the mail you care about is logged.
• A long summary breaks the row. Cap the summary length in the prompt, as the example does.
• Duplicate rows on the first run. Normal. Clear the test rows and let it settle on new mail only.

This extract-then-store pattern adapts to many jobs. More in Make AI scenarios.

How do you build this in Zapier or n8n instead?

Same three jobs, different names.

Job	Make	Zapier	n8n
Catch an email	Watch emails	New Email trigger	Gmail Trigger node
Pull out fields	Claude module	Claude (Anthropic) action	Anthropic node
Write the row	Add a Row	Create Spreadsheet Row	Google Sheets node

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

Common questions

How does Make split the fields into columns?

You map Claude’s reply, then split it on the pipe character in Make and drop each part into its column. Keeping the output to just the delimited line makes this clean.

Can it log to Airtable or Notion instead?

Yes. Swap the Google Sheets module for an Airtable or Notion one; the Gmail and Claude steps stay the same.

What if an email is missing a field?

Tell Claude in the prompt to write “unknown” for any field it cannot find, so the column never goes blank and the row stays aligned.

Will it overwrite existing rows?

No. Add a Row only ever appends to the bottom. Your earlier rows are safe.

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 to bookmark

• Creating a scenario (Make Help)
• Claude API overview (Anthropic)
• Google Sheets basics (Google)
• Claude on Make (integrations)
• Google Sheets — Grokipedia

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

You may also like

• Draft WordPress posts from a spreadsheet with Claude + Make
• Turn a YouTube video into a WordPress draft with Claude
• Turn a blog post into LinkedIn and X posts with Claude
• Make.com Complete Beginner’s Guide
• How to use Claude AI
• n8n Complete Beginner’s Guide
• The AI Tools Directory