KQL Templates — GenAI Trace Query Reference

Ready-to-use KQL templates for querying GenAI OpenTelemetry traces in Application Insights.

Table of Contents: App Insights Table Mapping · Key GenAI OTel Attributes · Span Correlation · Hosted Agent Attributes · Response ID Formats · Common Query Templates · OTel Reference Links

App Insights Table Mapping

Key GenAI OTel Attributes

Stored in customDimensions on dependencies spans:

Stored in customDimensions on customEvents (name == gen_ai.evaluation.result):

Correlation: Eval results do NOT link via id-parentId. Use gen_ai.conversation.id and/or gen_ai.response.id to join with dependencies spans.

Span Correlation

Operation_Id Join (requests → dependencies)

Use requests as the hosted-agent entry point, then carry operation_Id forward as the trace key when joining into dependencies, traces, or customEvents:

let agentRequests = materialize(
    requests
| where timestamp > ago(7d)
| extend
    foundryAgentName = coalesce(
        tostring(customDimensions["gen_ai.agent.name"]),
        tostring(customDimensions["azure.ai.agentserver.agent_name"])
    ),
    agentId = tostring(customDimensions["gen_ai.agent.id"]),
    agentNameFromId = tostring(split(agentId, ":")[0]),
    agentVersion = iff(agentId contains ":", tostring(split(agentId, ":")[1]), ""),
    conversationId = coalesce(
        tostring(customDimensions["gen_ai.conversation.id"]),
        tostring(customDimensions["azure.ai.agentserver.conversation_id"]),
        operation_Id
    )
| where foundryAgentName == "<foundry-agent-name>"
    or agentNameFromId == "<foundry-agent-name>"
| project operation_Id, conversationId, agentVersion
);
dependencies
| where timestamp > ago(7d)
| where isnotempty(customDimensions["gen_ai.operation.name"])
| join kind=inner agentRequests on operation_Id
| extend
    operation = tostring(customDimensions["gen_ai.operation.name"]),
    model = tostring(customDimensions["gen_ai.request.model"])
| project timestamp, duration, success, operation, model, conversationId, agentVersion, operation_Id
| order by timestamp desc

Hosted Agent Attributes

Stored in customDimensions on both requests and traces tables (NOT on dependencies spans):

Important: Use requests as the preferred entry point for agent-name filtering — it has both azure.ai.agentserver.agent_name and gen_ai.agent.name with the Foundry-level name. To reach downstream spans and related telemetry, carry operation_Id forward from the filtered request set and join other tables on that trace key.

💡 Version enrichment: Some hosted-agent requests telemetry emits gen_ai.agent.id in <foundry-agent-name>:<version> format. When that delimiter is present, split on : to recover agentVersion; if it is absent, keep filtering on the requests-scoped name fields and leave version blank.

⚠️ gen_ai.agent.name means different things on different tables:

• On requests: the Foundry agent name (user-visible) → e.g., hosted-agent-022-001
• On dependencies: the code-level class name → e.g., BingSearchAgent

>

Always start from requests when filtering by the Foundry agent name the user knows.

Response ID Formats

When searching by response ID, use the appropriate prefix to narrow results. The gen_ai.response.id attribute appears on dependencies spans (for chat operations) and in customEvents (for evaluation results).

Common Query Templates

Overview — Conversations in last 24h

dependencies
| where timestamp > ago(24h)
| where isnotempty(customDimensions["gen_ai.operation.name"])
| summarize
    spanCount = count(),
    errorCount = countif(success == false),
    avgDuration = avg(duration),
    totalInputTokens = sum(toint(customDimensions["gen_ai.usage.input_tokens"])),
    totalOutputTokens = sum(toint(customDimensions["gen_ai.usage.output_tokens"]))
  by bin(timestamp, 1h)
| order by timestamp desc

Error Rate by Operation

dependencies
| where timestamp > ago(24h)
| where isnotempty(customDimensions["gen_ai.operation.name"])
| summarize
    total = count(),
    errors = countif(success == false),
    errorRate = round(100.0 * countif(success == false) / count(), 1)
  by operation = tostring(customDimensions["gen_ai.operation.name"])
| order by errorRate desc

Token Usage by Model

dependencies
| where timestamp > ago(24h)
| where customDimensions["gen_ai.operation.name"] == "chat"
| summarize
    calls = count(),
    totalInput = sum(toint(customDimensions["gen_ai.usage.input_tokens"])),
    totalOutput = sum(toint(customDimensions["gen_ai.usage.output_tokens"])),
    avgInput = avg(todouble(customDimensions["gen_ai.usage.input_tokens"])),
    avgOutput = avg(todouble(customDimensions["gen_ai.usage.output_tokens"]))
  by model = tostring(customDimensions["gen_ai.request.model"])
| order by totalInput desc

Tool Call Details

dependencies
| where operation_Id == "<operation_id>"
| where customDimensions["gen_ai.operation.name"] == "execute_tool"
| project timestamp, duration, success,
    toolName = tostring(customDimensions["gen_ai.tool.name"]),
    toolType = tostring(customDimensions["gen_ai.tool.type"]),
    toolCallId = tostring(customDimensions["gen_ai.tool.call.id"]),
    toolArgs = tostring(customDimensions["gen_ai.tool.call.arguments"]),
    toolResult = tostring(customDimensions["gen_ai.tool.call.result"])
| order by timestamp asc

Key tool attributes:

Evaluation Results by Conversation

customEvents
| where timestamp > ago(24h)
| where name == "gen_ai.evaluation.result"
| extend
    evalName = tostring(customDimensions["gen_ai.evaluation.name"]),
    score = todouble(customDimensions["gen_ai.evaluation.score.value"]),
    label = tostring(customDimensions["gen_ai.evaluation.score.label"]),
    conversationId = tostring(customDimensions["gen_ai.conversation.id"])
| summarize
    evalCount = count(),
    avgScore = avg(score),
    failCount = countif(label == "fail" or label == "not_relevant" or label == "incorrect"),
    evaluators = make_set(evalName)
  by conversationId
| order by failCount desc

For detailed eval queries by response ID or conversation ID, see Eval Correlation.

OTel Reference Links

• GenAI Spans
• GenAI Agent Spans
• GenAI Events
• GenAI Metrics