WhaTap AI

WhaTap AI is an AI chatbot that lets you ask about APM and infrastructure status in natural language and get answers within the WhaTap screen. Without dashboard search or query learning, it retrieves metrics and builds charts and dashboards based on the context of the screen you are viewing. For tasks that require configuration, such as alert rules, it suggests an appropriate rule and settings that you can register right from the response. Even users unfamiliar with monitoring tools can leverage WhaTap data with minimal learning.

Value of WhaTap AI

Reach data without memorizing screens, filters, or queries

WhaTap collects various observability data such as transactions, infrastructure, databases, and Kubernetes. To find the metrics you want, you need to know screen locations, filters, and how to use queries. WhaTap AI retrieves data with a natural language question alone, such as "Show me the transactions with the slowest response times in the past hour." It reduces the time users spend learning the screens and lets you quickly check the information you need.

Recognizes the screen you are currently viewing

Even for the same question, the answer should differ depending on which screen you are viewing. WhaTap AI automatically recognizes the screen you currently have open, the widgets shown on it, and the time range you selected, and provides answers that match that context. You can keep asking based on what you are viewing, without closing the screen and re-explaining the conditions from scratch.

Automatically creates dashboards aligned with analysis intent

Visualizing operational data normally requires steps such as choosing a widget type, selecting metrics, and configuring the chart. WhaTap AI directly picks charts that match the intent of your question and attaches them to the response, and when needed, automatically assembles a dashboard layout that groups multiple widgets. When you want to view the status of multiple projects on one screen, it creates an integrated Flex Board (a dashboard that combines multiple projects on a single screen). The output can be saved and reused as is.

Suggests alert rules and registers them on the spot

A monitoring tool is both a tool for viewing data and a tool for configuring operational behavior. For a request such as "I want a Critical alert when server disk usage exceeds 90%," WhaTap AI suggests an appropriate alert rule and settings and lets you register it right from the response. You do not have to look up the metric name and threshold yourself, which reduces the time spent figuring out how to configure the rule.

Supports Korean, English, and Japanese

WhaTap AI automatically detects the user's language and responds in Korean, English, or Japanese. Teams in multilingual environments can use WhaTap AI together, asking and receiving answers in their preferred language, without needing separate tools or translation steps.

Automatically explains metric units and meaning

It is sometimes unclear what unit or meaning a number shown on a dashboard represents. WhaTap AI automatically shows the name of the metric used in the answer along with its unit, type, and a brief description. This reduces situations where numbers are misinterpreted or decisions are misaligned due to unit differences.

Key features of WhaTap AI

Natural language queries and real-time responses

Enter your question in the chat input in your everyday language, and receive the response in a streaming format. You can read the content as it is being written, without waiting for the full response to complete.

Current screen awareness

It automatically recognizes the currently open screen, widgets, and time range, and provides answers that match the context. The same question yields different answers depending on the screen you are viewing, and you do not need to separately describe conditions such as "on this screen" or "with the current time range."

Data analysis

Based on the metrics shown on the screen, it analyzes trends, anomalies, and even suggested improvements. The response also displays the name, unit, and a brief description of the metrics used, reducing situations where you guess the meaning from numbers alone.

Dashboard creation

It picks charts that match the analysis intent of the question and attaches them to the response, and when needed, automatically assembles a dashboard layout that groups multiple widgets. You can receive visualizations aligned with the analysis flow without placing widgets yourself.

Integrated Flex Board creation

When you want to view the status of multiple projects or multiple products on a single screen, WhaTap AI automatically creates an integrated Flex Board. You can grasp the overall operational status in one place without opening each project-level dashboard one by one.

Suggesting and applying alert rules

For items that require configuration within WhaTap, such as alert rules, it suggests a rule and settings that match your intent. You can register a suggested rule by clicking the [ Apply ] button on the rule card in the response. Until you click the button it remains a proposal, and to not register it you can click the [ Cancel ] button. When the applied result differs from your intent, you can revert the most recent application and restore the state before it was applied.

Screen and event analysis

When you enter the target you want to analyze in the input box at the top of the console, WhaTap AI analyzes the cause and suggests next steps based on the context of the screen you are currently viewing and the events that occurred.

AI Analysis entry points on each screen

Screens that show query results, such as Statistics, Stack, and Hitmap, have an AI Analysis button. Clicking the button returns an analysis result that uses the conditions and data the screen queried, as they are. The result appears in the drawer on the right side of the screen, or as the first response in the WhaTap AI chat so that you can continue with follow-up questions. For details, see the Screen AI Analysis document.

Multilingual responses

It recognizes the user's input language and responds in Korean, English, or Japanese. It can be used as is, with no separate configuration, to match the team's language environment.

Response feedback

You can send feedback by clicking the Like or Dislike button on a response. Selecting Dislike lets you also choose a reason such as accuracy, relevance, or length, and the feedback you provide is used to improve WhaTap AI response quality.

Next steps

• Getting started: Check the flow and prerequisites for using WhaTap AI for the first time.
• UI guide: Check each area of the WhaTap AI screen and how to use it.
• Usage guide: Check question examples and usage by scenario.