Khush I.

Hey Josh, I totally understand the challenge you're facing. Currently, Clay doesn’t support an exact duplication of a table with data intact as it appears in its current state. When you duplicate a table in Clay, it essentially creates a template copy, preserving all column configurations such as prompts, formulas, HTTP API setups, write-to-table actions, and conditions. This saves you the effort of rebuilding the structure from scratch. However, to replicate the data itself, you'll need to manually re-run any data source integrations. For instance, if your original table pulled data from another table or executed a search (e.g., company or people search), you'll need to re-trigger those queries. Similarly, any enrichment or export columns will need to be re-executed to recreate the original table’s contents. I know this requires a few extra steps, but that’s how duplication currently functions in Clay. If this feels limiting, I’d recommend submitting a feature request in the Feedback and Requests channel, I'm sure the team would appreciate your input. Best, Khush

I personally follow the practice of testing my prompt directly with the LLM before setting it up in the enrichment column. When I gave your prompt to ChatGPT, it returned a Python-based explanation instead of the expected output. So, I added an extra line of instruction to your original prompt, and it worked well. Here is the modified prompt: I'm trying but the it return 2-leltter country anyway, here is the prompt I'm using: #CONTEXT# You are tasked with converting 2-letter country codes to their corresponding full country names using the ISO 3166-1 alpha-2 standard. #OBJECTIVE# Convert the value in the 'Country Enriched' column from a 2-letter country code to the full country name. If the input is invalid or empty, return "Unknown Country". #INSTRUCTIONS# 1. Read the value from the 'Country Enriched' column. 2. Check if the value is a valid ISO 3166-1 alpha-2 country code. 3. If valid, return the corresponding full country name (e.g., "US" → "United States"). 4. If the value is invalid or empty, return "Unknown Country". #EXAMPLES# Input: "US" → Output: "United States" Input: "FR" → Output: "France" Input: "DE" → Output: "Germany" Input: "ZZ" → Output: "Unknown Country" Input: "" → Output: "Unknown Country" Don't give me any additional explanations or try to find mistakes with my input and use the above instructions to give me the answer to the below input in the desired format: Input to parse: "AF" Attached to this message is an image of the output received by ChatGPT.

https://clayrunhq.slack.com/archives/C025KSBLPGX/p1749827197996759?thread_ts=1749826340.813069&cid=C025KSBLPGX I can see you haven't declared the input column as /Country within the prompt, try fixing that and check

Hey, I completely understand where you're coming from, I faced similar frustration when I first started using Clay. Over time, I realized that Clay sits somewhere between a spreadsheet and a database, with Postgres as its underlying foundation. Since we're so used to traditional spreadsheets, it’s natural to expect similar behavior from any table interface. But Clay is designed differently. If you’ve ever used Microsoft Access, Clay is quite similar in how it structures data. The constraints you’re encountering are mostly due to the inherent limitations of SQL-based systems, which introduce a learning curve, but one that Clay University does a great job of addressing. To answer your question: a good practice would be to import each sheet as a separate table and then create a third table that pulls data from the other two. Just make sure you're mapping columns of the same data type when merging. If you’re curious to learn more about Clay’s architecture, I found this article insightful: https://refactoring.fm/p/clay

Hey Frank! Clay is designed to apply the same operation across all rows within a column, unlike Excel where each row can have different formulas. This columnar consistency makes Clay highly scalable for bulk operations.

Hey Oleksii! The “Find Jobs” source integration in Clay allows you to search for open roles by specifying the job title, description, location, or type. You can use this data source to create a dynamic table of job openings and identify the companies currently hiring. Helpful Links: Explained by the GOAT Yash: https://www.clay.com/university/lesson/find-jobs-source-enrichment-clay-101

Hey Cristina! You need to configure the output field for the prompt to get the output in a specific format. Are you sure to have configured this?

Currently there isn't an option to just run the rows that haven't run. Consider adding a request for an option to run just the rows that haven't run in the feedback-and-requests channel.

Hello Michael! I don't think the clay linkedin integration has a feature to pull in a list of your personal connections in a table. Reference: https://www.clay.com/university/guide/linkedin-integration Currently this integration only allows you to

Hey Doug, There should be an option to either add the output from the HTTP API as a new column in your table or map it to an existing one. Once the data is available in a column, you can easily reference it in a formula column (see Image 1). I understand your concern about keeping the table clean, if you'd prefer not to display the extra column, you can always hide it (see Image 2). Adding the data to a column and referencing it through a formula also helps maintain provenance, making the table more robust and transparent. If this behavior feels limiting or unexpected, feel free to report it in the #bugs channel so the team can take a closer look.