Transcripts #492
Transcripts #492
Conversation
- Fix period usage in numbered steps and bold labels across all AI agent docs - Add descriptive link text to xref anchor links for better accessibility - Redesign monitor-agents.adoc reducing lists from 9 to 2, converting to prose and tables - Create observability index page - Fix broken xref from billing.adoc to observability/concepts.adoc
- Change negative headings to positive action-oriented headings - Add explicit 'Enter this query' instructions for each test scenario - Add guidance on what to watch for in the conversation panel - Specify when to start new sessions for context clearing
Moved monitoring how-tos into context where users need them: - Monitor Agents now in agents section - Monitor MCP Servers now in mcp/remote section - Observability concepts remain centralized as single source of truth This follows the "procedures in context, concepts centralized" pattern, reducing navigation overhead and improving task completion. Also removed unnecessary observability index page since only one page remains in that section. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Sessions and tasks topics are being soft-hidden with __ prefix as they are internal implementation details. Updated documentation to focus on user-facing monitoring features (transcripts and inspector). Changes: - Remove "Agent data topics" section from concepts.adoc with schemas - Remove "Consume agent data topics" section from monitor-agents.adoc - Update troubleshooting.adoc to reference transcripts instead of topics - Update learning objective to "Track token usage and performance metrics" - Fix xref anchor links to include descriptive text - Fix shipping carrier name to comply with Google style guide Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the
Comment |
| :learning-objective-2: Navigate between detail views to inspect span information at different levels | ||
| :learning-objective-3: Use the timeline interactively to navigate to specific time periods | ||
|
|
||
| The Transcripts view provides filtering, searching, and navigation capabilities for investigating agent and MCP server execution transcripts. Use these features to efficiently locate specific operations, analyze performance patterns, and debug issues across tool invocations, LLM calls, and agent reasoning steps. |
There was a problem hiding this comment.
Also anything that goes through the ai gateway should become visible through transcripts. Eventually also knowledgebase query operations - generally everything in the ADP that is being requested/queried should emit those traces/transcripts.
|
|
||
| === Use the interactive timeline | ||
|
|
||
| Use the timeline visualization to quickly identify when errors began or patterns changed, and navigate directly to transcripts from particular timestamps. |
There was a problem hiding this comment.
Also: If we have many traces (e.g. hundreds or thousands) we can only show a subset of the traces. We have the timeline bar indicate what data is being shown currently. It may be just 5 minutes worth of data evne though you selected "Last 24h". Not sure if worth clarifying, should be intuitive hopefully
|
|
||
| === Search and filter for transcripts | ||
|
|
||
| Use search and filters together to narrow down transcripts and quickly locate specific executions. |
There was a problem hiding this comment.
I need to clarify and follow-up what the search field and the filter targets. It's not clear at the moment. I'll try to have the search field compare against all span attributes in the selected time range (possibly exact matches only). Let's talk again by mid of next week, then I should have an answer for package 1
There was a problem hiding this comment.
@weeco got it, I'll check in shortly! Also, does it make sense to filter (instead of search) based on scope/layer? Would there be actual use cases for that
|
|
||
| == Inspect span details | ||
|
|
||
| Each row in the transcript table represents a high-level agent or MCP server request flow. Expand each parent span to see the xref:ai-agents:observability/concepts.adoc#agent-transcript-hierarchy[hierarchical structure] of nested operations, including tool calls, LLM interactions, and internal processing steps. Parent-child spans show how operations relate: for example, an agent invocation (parent) triggers LLM calls and tool executions (children). |
There was a problem hiding this comment.
Technically they will fold under the same trace. So for example if the declarative agent uses our remote mcp platform we will create a trace id on the very first touchpoint of the request and this trace id is passed around across services (such as the MCP server) and they will emit traces that belong to this trace id. That's why we can build this tree view for a single agent invocation.
If someone uses their own agents and just invokes the MCP servers directly on our platform then they may see a parent trace just for the MCP server invocation (unless they also pass around the trace id and emit traces from their agents to our platform)
There was a problem hiding this comment.
Updated for detail
|
Worth having some content around using the new connectors to add your own traces or export them? 15292de |
Description
Resolves https://github.com/redpanda-data/documentation-private/issues/
Review deadline:
Page previews
Checks