Documentation Grafana Cloud AI and machine learning Grafana AI Observability Guides Browse conversations

Browse and debug conversations

The Conversations view in the AI Observability plugin lets you search, filter, and inspect full conversation threads. Use it to understand what happened during an agent interaction, identify failures, and analyze performance.

Search conversations

Navigate to Conversations in the AI Observability plugin. Use the search bar and filters to find conversations by:

• Time range.
• Agent name or version.
• Model provider or name.
• Conversation content.
• Error status.
• Tags or metadata values.
• Evaluation results (pass, fail, or specific evaluator scores).

Conversations display a summary showing the agent, model, token count, cost, duration, and any evaluation scores. The metrics bar shows evaluation pass, fail, and neutral counts for each conversation.

Inspect a conversation

Click a conversation to open the detail view. The conversation detail shows:

• A timeline of all generations in the conversation.
• Each generation’s input messages, output messages, tool calls, and tool results.
• Token usage breakdown (input, output, cache read, cache write, reasoning).
• Timing data (start, first token, end).
• Evaluation scores attached to each generation.

Tool calls within a generation are grouped together, and thinking/reasoning content is collapsible. Generations with no captured content show an inline placeholder.

Click the error badge in the metrics bar to jump directly to the first errored generation in the conversation.

Understand the Dependencies and Workflow tabs

Conversation detail has two graph views for agent structure: Dependencies and Workflow. They represent different layers of your agent and aren’t mutually exclusive — you can use both together.

Dependencies — the generation DAG

Use Dependencies to inspect relationships between LLM calls. Each node is one generation, and edges come from parent_generation_ids. You set these parent IDs explicitly in your code — no SDK layer fills them automatically.

This tab is always available. If no generation declares parents, it still shows independent nodes and an inline hint that no dependencies were instrumented. Dependencies work across processes and services because the IDs are just strings you forward over the wire.

Workflow — the agent execution graph

Use Workflow to see the full orchestration around your LLM calls. Each node is an agent execution step, for example, routing, planning, retrieval, validation, or tool orchestration. A step can wrap zero, one, or many generations — a retrieval step with no LLM call still appears in the graph with its state, duration, and errors.

Steps link to each other with parent_step_ids and link to the LLM calls that happened inside them with linked_generation_ids. You can build this graph in two ways: supported framework adapters fill both fields automatically when workflow-step capture is enabled, or the core SDK can send workflow steps manually to represent your own custom orchestration. The Workflow tab appears only when the conversation includes workflow-step telemetry.

Choose the right view

You can combine both: Workflow gives the high-level execution path, while Dependencies gives the generation-level DAG for debugging multi-agent handoffs and downstream quality signals.

Trace drilldown

Each generation links to its OpenTelemetry trace. Click the trace link to open the trace view in Tempo, where you can see the full span tree including:

• LLM call duration and error status.
• Tool execution spans.
• Nested agent invocations.

Use trace drilldown to identify latency bottlenecks, understand tool call sequences, and diagnose timeout or error scenarios.

Provide feedback

Use feedback to capture human judgment about a conversation. Users with the Feedback Writer or Admin role can add ratings and annotations from the conversation detail view.

Click the feedback controls in the conversation header to mark a conversation as good or bad and optionally add context. Ratings appear in the conversation list and detail header so reviewers can quickly find conversations that need attention.

Annotate conversations

Open the Annotations panel from the conversation detail view to add threaded notes. Annotations support key-value tags and are visible to all team members with the Feedback Writer or Admin role. Use annotations to:

• Flag conversations for review.
• Add context about specific agent behaviors.
• Track investigation notes alongside the conversation data.

The conversation list shows an annotation count badge, and you can browse annotated conversations from a dedicated pane in the conversation browser.

Save conversations

Save conversations that you want to review later or reuse in evaluation workflows. Saved conversations appear in the Saved tab in the conversation browser.

When collections are enabled, organize saved conversations into collections. Collections let you group representative examples, failure cases, or review sets and then run offline evaluation experiments against the group.

Next steps

• Use the agent catalog
• Use built-in dashboards