Monitor your agents with signals

Use W&B Weave signals to score agent turns, apply tags, and surface quality and safety issues in production.

In W&B Weave’s Agents view, the Signals tab shows tags and ratings for your agent’s conversations. Signals surface quality and safety issues to flag problems, find patterns, and highlight the traces that need your attention. Use signals to automatically score the quality of your agent’s responses, notice when a user is frustrated, or flag NSFW content.

Get started

To view signals for your project:

1. Navigate to https://wandb.ai and select your project.
2. In the sidebar menu, select Agents to view all agent conversations saved for your project.
3. In the tab bar, select Signals.

Key terms

• Turn: One back-and-forth exchange between the user and the agent.
• Rating: A numeric score between 0.0 and 1.0 assigned to a matching span.
• Tags: Labels assigned to matching spans, such as “user-frustration” or “nsfw”.

Signals table

The Signals tab displays a table of scored turns from your agent. Each row represents the output of one of your signal monitors. The following columns appear by default.

Column	Description
Type	The part of the conversation that gets scored. Only turn is supported.
Scorer	The name of the signal that produced this score.
Last message	A preview of the last message in the scored turn, with the role shown below.
Agent	The agent associated with the scored turn.
Scores	The numeric rating from 0.0 to 1.0, or a tag if matched. We recommend using consistent ratings where 1 indicates good and 0 indicates bad, but your scorers can use any scale you define.
Trend	Displays an inline chart that shows how this signal trends over time. Shows either the average value (for ratings) or the count (for tags).
When	When the signal was scored.

Use the time window selector and Filter bar to narrow results by scorer, agent, score range, or time period. The Score volume timeline shows counts of signals that Weave evaluated for ratings or tagged. It reflects the rows shown in the table and supports drag-to-filter on the timeline.

Create a new signal

To start scoring your agent’s turns, create one or more signals. Select + New signal to open the Create signals drawer.

The drawer groups available signals into two categories:

• Tags: Apply a label automatically to matching spans, such as user-frustration or nsfw. Use tags to categorize spans or flag unwanted behavior. The signals UI only displays rows for spans that matched at least one tag, so a tag signal might run successfully even if you don’t see any output.
• Ratings: Assign a score from 0 to 1 to matching spans. Use ratings to rate agent performance and measure improvements over time.

Preset signals

Each category offers preset templates that you can select directly. Select any combination of presets across both categories, then select Create [N] signals to create them all at once with default settings.

Tags presets

Template	What it detects
User Frustration	User shows signs of frustration, anger, confusion, or dissatisfaction.
Malicious Intent (Jailbreaking)	User attempts to jailbreak the system, extract restricted content, perform prompt injection, use role-play exploits, or otherwise manipulate the agent into ignoring its guardrails.
NSFW	User input or agent output contains explicit sexual content, graphic violence, or other material inappropriate for a workplace setting.
Low Quality Response	Agent output that is factually wrong, off-topic, evasive, repetitive, lacks justification when refusing, or otherwise fails to address the user’s request.

Ratings presets

Template	What it evaluates
User Satisfaction	Whether the user is satisfied (positive feedback, follow-up engagement, task completion) or dissatisfied (complaints, repeated rephrasing, abandonment).
User Good Intent	Whether the user’s intent is benign and legitimate, versus jailbreak attempts, harmful requests, or prompt injection.
Safe-for-Work	Whether the conversation is appropriate for any professional setting, versus explicit, violent, or otherwise inappropriate workplace content.
Response Quality	Whether the agent’s response is accurate, complete, and directly addresses the user’s request.

Custom signals

In the Create signals drawer, at the bottom of each of the Tags and Ratings categories, there is an option to create a custom signal.

To define your own signal, select Custom Tags or Custom Rating. This opens a configuration screen with the following fields.

• Prompt template: Optionally base your scorer on one or more preset templates. Selecting templates populates the Scorer prompt; you can combine multiple templates or write a prompt from scratch.
• Scorer prompt: The prompt sent to the inference model at score time. Weave resolves template variables, such as {input_messages}, {output_messages}, {system_instructions}, and {agent_name}, during scoring.
• Scorer name: The display name for this signal.
• Inference model: The LLM to use for scoring. Serverless Inference is the default; CoreWeave Serverless Inference consumes credits from your W&B account.
• Advanced: Expand to configure additional options:
  • Only score turns matching: Add one or more filters to restrict which turns the signal scores, for example by agent, operation, tool, or model. Leave empty to score every agent turn. Weave combines multiple filters with AND logic.
  • Sample rate: For high-traffic agents, lower the sample rate to score a fraction of matching turns instead of every turn and reduce cost.

Select Create signal to save.

Manage and edit signals

If you have at least one created signal, select the active signals button in the toolbar—labeled with the number of active signals, such as 1 active signals—to open a drawer that lists all active signals for the project. From there you can toggle signals on or off, delete them, or edit any signal. The editor shows the same configuration fields as a custom signal.

Troubleshoot signals

Signal activity appears under Traces in the project sidebar. If you don’t see the expected signal matches, debug using the Traces table. For example, check the scorer name and the Status column for error conditions. Scorer execution errors show a red indicator for Status and include error details.