> For the complete documentation index, see [llms.txt](https://ask.birdie.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ask.birdie.ai/voice-of-customer/exploration-and-analysis/using-filters-in-birdie.md).
# Using filters in Birdie
## How to use Filters?
Filters in Birdie are essential tools that allow users to create [areas](/core-concepts-and-entities/areas.md) and [segments](/core-concepts-and-entities/segments.md), analyze specific areas and [opportunities](/core-concepts-and-entities/understanding-and-creating-opportunities-in-birdie.md), and define the context in which [Skye](/voice-of-customer/exploration-and-analysis/understanding-and-using-skye-in-birdie.md) operates. Understanding how to apply both simple and advanced filters enhances data analysis and decision-making processes.
## Filtering Criteria
Regardless of the filter type, the following predefined fields are available for filtering:
* Feedback Intention: Categorizes the purpose behind the feedback.
* Sentiment: Indicates the emotional tone of the feedback.
* Source: Identifies where the feedback was submitted.
* Feedback Details: Provides specific content of the feedback.
* Custom Fields: Allows filtering based on user-defined criteria.
Within "Feedback Details," in addition to organization-specific fields, there are two standard filtering options:
* Signal: This filter identifies whether the feedback contains interpretable text. Options are "Yes" (the feedback includes text) or "No" (the feedback does not include text).
* Yes: Detailed customer service interactions where customers provide comprehensive explanations.
* No: Blank responses or extremely brief comments lacking context, such as an empty feedback form or a single character input.
While most tickets, like in-depth customer service conversations, will have a "Yes" signal due to their structured sentences, feedback from app reviews, CSAT (Customer Satisfaction) surveys, and NPS (Net Promoter Score) surveys may not, especially if they lack substantive comments.
* Has Aspect: This filter determines whether the comment contains actionable and relevant content. Options are "Yes" (the comment has actionable content) or "No" (the comment lacks actionable content).
* Yes: "The app crashes when I try to upload a photo."
* No: Generic remarks like "Great!" or "Didn't like it," which don't provide specific insights.
For detailed information on sentiments and intentions, please refer to the dedicated [documentation](/core-concepts-and-entities/signal-sentiments-and-intentions.md) on these topics.
Please note that "Feedback Details," "Source," and "Custom Fields" are specific to each organization. If you have any questions or need clarification regarding these fields, please consult our internal team for assistance.
### Keyword Filters
For targeted searches, especially when dealing with specific subjects, keyword filters are highly effective. By utilizing the search icon on the upper right corner within the exploration page, you can filter feedback containing specific keywords.
**Example of search:**
```
card AND (request OR delivery OR receiving) AND -(limit)
```
* Using "OR" for Multiple Keywords: To filter feedback containing any of several keywords, separate them with "OR".
* Example: "Zelle OR credit OR debit"
* This filters feedback containing "Zelle," "credit," or "debit".
* Using "AND" for Combined Keywords: To filter feedback containing all specified keywords, use "AND".
* Example: "card AND credit"
* This filters feedback containing both "card" and "credit".
* Combining "AND" and "OR" for Specific Searches: For more refined searches, combine both operators.
* Example: "card AND (credit OR debit)"
* This filters feedback containing "card" and either "credit" or "debit".
### Advanced Search Capabilities
Birdie’s search also supports the complete set of options available in [Elasticsearch’s Query String Syntax](https://www.elastic.co/docs/reference/query-languages/query-dsl/query-dsl-query-string-query#query-string-query-notes), including proximity operators and other advanced parameters.
For example, you can use proximity search to find terms that appear close to each other, regardless of order:
```
"suspended account"~3
```
This finds results where suspended and account appear within three words of each other in any order (e.g., "account is currently suspended", "suspended due to account issues").
## Types of Filters
### Simple Filters
These are cumulative filters connected by an "AND" relationship. When multiple simple filters are applied, Birdie displays data that meets all specified criteria simultaneously.
### Advanced Filters
Advanced filters enable more complex data segmentation through the use of "AND" and "OR" operators. This functionality allows for nuanced data queries, facilitating precise analysis. For a comprehensive understanding of advanced filter clauses, refer to Birdie's documentation on filter clauses.
## Getting Started with Filters
Mastering the use of simple and advanced filters in Birdie empowers users to conduct precise analyses and tailor the feedback environment to their needs. By effectively utilizing these filtering options, you can enhance the relevance of insights and optimize the use of Skye within the platform.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://ask.birdie.ai/voice-of-customer/exploration-and-analysis/using-filters-in-birdie.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.