Ask Anthropic/Claude AI

Step-by-Step Guide

Part 1: Get your Anthropic API key

Follow Anthropic's own instructions: Get your Claude API key.

Step 1: Sign In and Add Credits

Sign in to the Claude Console at platform.claude.com.

Open Settings, then Billing, and buy prepaid credits. API usage is paid with these credits, and requests fail once they run out.

Anthropic accounts without billing set up will not work with this enrichment.

Step 2: Create and Copy Your Key

Open Settings, then API keys and click Create key.

Name the key, choose an expiration and create it. Copy the full key, which starts with sk-ant-. The Console shows it only once.

Part 2: Run the enrichment in Datablist

Step 3: Sign Up & Upload Your Data

First, sign up for Datablist.com

Then, upload your CSV or Excel file with the rows you want to run the prompt on. Create a new collection and import your file with the CSV editor.

Step 4: Navigate to the Enrichment

Click Enrich in the top menu and search for Ask Anthropic/Claude AI.

Step 5: Paste Your API Key

In the drawer that opens, paste your Anthropic API key in the Anthropic API Key field.

Datablist sends the key with your run to call Claude. Do not share it with others.

Step 6: Write Your Prompt

Write one prompt for all your rows. Type a slash and choose a property to insert its value, for example the company name.

The prompt must include at least one row variable. Type {{ or / and select a property; Datablist inserts its value for each row.

Optionally add a system prompt to guide the answer, for example: Return just the result. No instruction, no comment.

You can add a System Prompt to help Claude understand its role or format its response consistently.

Step 7: Choose the Output Columns

Claude returns the answer in a Result column. To get several fields from one prompt, switch on Define outputs format and name each output. Then choose where to store each result: create new properties or map existing ones.

Click Continue to outputs configuration, then click the ⊕ icons to add the output properties to your collection.

Each structured output has a name, description and type: Text, Long Text, URL, Number, DateTime or Checkbox. Define an output for each field your prompt requests. This option is available on compatible models.

Step 8: Test on a Few Rows, Then Run

Run a sample first. Click the chevron on the right side of the run button to choose how many items to process:

• Run on first 10 items: Good for checking results before committing

• Run on first 100 items: Useful for validating larger samples

• Run on all view items: Process your entire list (or view if you've enabled filters)

Check the results, adjust your prompt, then run the full list. Switch on Run in Async in the Run Settings to let Datablist handle automatic background retries.

Review the run-status column, filter failed rows, fix the input or settings, and rerun those rows. You can filter and export the resulting collection.

Use cases

Email intro for cold emailing

Generate initial drafts for emails. Use personal info (like {{Company}}, {{Job Title}}) from each contact profile to write a personalized email intro using Claude's writing style.

Language Translation

Claude is proficient at translating text. Use it to translate content from one column to another language in a new column.

Data Cleaning & Standardization

Use Claude to clean your Excel or CSV files. It can correct text cases, fix grammar and typos, standardize formats (like addresses or names), or extract structured information from messy text.

Social Media Posts

Draft targeted social media posts based on product details or event information listed row by row in your spreadsheet.

Product Catalog processing

Generate summaries from long product descriptions, create compelling descriptions from technical specs ({{Feature 1}}, {{Feature 2}}), or classify products based on their attributes using Claude's understanding.

Advanced Text Analysis

Perform sentiment analysis on customer feedback ({{Feedback Text}}), categorize user comments, or extract key themes from unstructured text fields across your dataset. Claude's large context window helps with understanding complex inputs.