Examples of categorizing data with AI

• Take a list of product names and categorize them by department: clothing, home goods, grocery, other
• Take a list of email addresses and sort them by type into these categories: work, personal, school, nonprofit, government, other
• Take a list of news headlines and categorize them by section: politics, business, world news, science, etc.

After running the step, it’s normal to modify your categories and re-run it as you see how the AI responds to your requests.

How to use this step

Selecting what to evaluate

You start by selecting which columns you want the AI to evaluate to produce a result.

• All columns: the AI looks at every data column to find and extract the item it’s looking for
• These columns: choose which column(s) the AI should try to extract data from
• All columns except: the AI looks at all columns except the ones you define

Note that even when the AI is looking at multiple (or all) columns, it’s still only evaluating and generating a result per row.

Setting the categories

This step is designed to assign categories to rows, so it needs to know what the desired categories are. The step provides spaces to write in as many categories as you need (it starts with three blank ones only as an example). Add one category per space.

Fine tuning

Open the "Fine tuning" drawer to see extra configuration options. Using this field, you can provide additional context or explanation to help the AI deliver the result you want.

For example, if you gave this step a list of animals and asked it to categorize them as “Animal I like” vs. “Animal I don’t like,” it might not give you an accurate result! But you could then use this field to say:

“I tend to like furry animals that are friendly to humans, like dogs and horses and dolphins, and not others”

This step would then better understand the categorization you’re looking for.

Helpful tips

• Currently, the AI can only run a few thousand rows at once. Choose and trim your data accordingly
• Sometimes you’ll see a response or error back instead of a result. Those responses are often generated by the AI, and can help you modify the prompt to get what you need.
• Still having trouble getting the response you expect? Often, adding more context in the "Fine tuning" section solves the problem.

‍

With our Artificial Intelligence (AI) steps, Parabola lets you process your data with OpenAI’s GPT AI in specific, useful, and reliable ways. But working with AI comes with important considerations.

AI has natural limitations

AI is a new field in technology, and while the results are sometimes exciting, they’re often less dependable than traditional human-built data processes. Consider reading OpenAI’s breakdown of their AI’s limitations, and keep the following in mind when using an AI to process data:

1. Model limitations: Understand GPT's knowledge cutoff. GPT can “hallucinate” or be confidently incorrect, so do not expect results to be perfectly accurate all of the time.
2. Data sharing: When data is processed using Parabola’s AI steps, that data is sent to OpenAI, a 3rd party. Review their policies and practices to understand how they handle your data.
3. Monitoring: Continuously assess GPT performance; take corrective actions as needed.
4. Responsible use: Adhere to regulations; inform stakeholders of limitations and risks.

AI processing is … different

We’ve made data processing with an AI easier than ever before! But when you use AI as part of a Parabola Flow, those steps can be less transparent and reliable than the rules-based transform steps that your Parabola Flows normally use.

Keep this in mind especially when automating processes where exact precision is critical, like financial data. Consider using AI for steps that require “interpretation” — which AI can be quite good at! — rather than precise calculation.

Feedback feeds us!

If you have feedback about the usefulness of these steps, or the AI-generated responses you’re getting from them, please tell us!

‍