AI Columns vs. Filters | Maven Bio Help Center

In the Maven Bio platform, Filters and AI Columns are two powerful tools that work together, helping you move from a massive dataset to specific, actionable insights. Understanding the difference is key to using them effectively.

At its core, the distinction is simple:

Filters decide which rows you see.
AI Columns decide what information you see in those rows.

Let's break that down.

Filters: Narrowing Your Universe

Think of Filters as an eligibility gate for your data. Their only job is to control which rows appear in your table by including or excluding them based on criteria you set. You aren't creating new information; you are simply selecting a subset of the existing rows.

Primary Job: To select which rows are included in your view.
How It Works: You apply rules to existing fields, such as including items from a list, setting a date range, or matching specific text.
The Result: The number of rows in your table changes, leaving you with a more focused and relevant dataset.

AI Columns: Enriching Your Data

If filters build your guest list, AI Columns create detailed name tags for each guest. They enrich the rows you've selected by performing research to find and structure new information. AI Columns never remove rows; they only add new columns of data.

Primary Job: To populate new fields (columns) with researched findings for each row.
How It Works: You instruct the AI, either with a natural language prompt or a pre-built Blueprint to find specific data points. The agent then populates new columns with that information, complete with evidence, sources, and confidence scores.
The Result: Your table has new columns filled with structured, evidence-backed insights.

The Best Practice Workflow: Filter First, Then Enrich

For the fastest and most efficient results, always apply your tools in this order:

Filter Tightly: First, use Filters to narrow your universe to only the most relevant rows. This ensures you aren't wasting time researching items you don't care about.
Enrich Deeply: Second, add AI Columns to research and extract the specific data points you need for that filtered set.

This two-step process: Filter, then Enrich—is the quickest path from broad data to specific, evidence-ready insights.

Quick Comparison

Feature	Filters	AI Columns
What It Does	Chooses which rows are included.	Populates what fields are shown per row.
Where to Find It	In the Filter menu.	In the AI Column menu.
What You Provide	Selections from lists, date ranges, text operators.	A natural language goal or a pre-built Blueprint.
What You Get	A smaller table with fewer rows.	New columns populated with cited findings.
Evidence & Sources?	No, because no research is performed.	Yes, every cell includes source links and evidence.
How to Reuse It	Filters are typically set for a specific search.	Save your setup as a Blueprint to reuse anytime.

Frequently Asked Questions & Troubleshooting

Q: I added an AI Column, but my number of rows didn't change. Why?

A: That's the correct behavior! AI Columns enrich rows, they don't remove them. Their job is to add new information. To reduce the number of rows, use Filters.

Q: Why did I get zero results when I selected "Double Masking" and "Triple Masking" in the same filter?

A: Inside a single list filter, selecting multiple items creates an AND condition. A trial can't be both Double and Triple masked.

Solution: Create two separate Masking filters -one for "Double" and one for "Triple." Then, group them together and switch the logic from AND to OR.

Q: My AI Column values updated after I changed my filters. Is that normal?

A: Yes. AI Columns run on the rows currently visible in your table. When you change the filters, the set of rows changes, so the AI re-runs the research for the new set.

Q: How do I pull specific values, like OS/PFS data, into my table?

A: That's a job for AI Columns. Filters can narrow your search based on OS/PFS values (e.g., OS > 24 months), but only AI Columns can extract and display those values in a new column.

Q: How can I reuse a set of AI Columns I created?

A: Save your column setup as a Blueprint. Give it a name, and you can instantly apply the same research configuration to other projects.Quick FAQs

Q: Do Filters and AI Columns live in the same place?

A: No, each has its own overlay with three panes.

Q: Can Filters pull OS/PFS values into the table?

A: No, use AI Columns for extracting values.

Q: Can AI Columns change which rows I see?

A: No, use Filters for that

Q: Narrow the set?

A: Filters.

Q: Add structured findings?

A: AI Columns.