--- schema_version: "1" id: 8883fe065b9ae407bb1869b95de269f2eefb2a7b51a7094dea0c99d732617512 title: Troubleshoot Agentforce Multi-Agent Solutions collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/agent_multi_orch_troubleshoot.md canonical_url: https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch_troubleshoot.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: b9679080bdd6ca7c1587a517341dc137a859032b5903f30c0e59e7f583b0965f description: Solve common issues with AI solutions involving Multi-agent Orchestration for Agentforce. products: - Agentforce - Cross Cloud release: "264" --- # Troubleshoot Agentforce Multi-Agent Solutions Solve common issues with AI solutions involving Multi-agent Orchestration for Agentforce. ## How can I reduce latency in my Multi-agent Orchestration solution? - Start by implementing the recommendations in "Ways to Minimize Latency in Multi-Agent Solutions" in [Multi-Agent Orchestration](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch.htm&release=264.0.0&type=5 "Extend your agent’s capabilities with Multi-Agent Orchestration for Agentforce. Connect your Agentforce agents with other specialized Agentforce agents in your Salesforce org so that they can collaborate securely on complex tasks. With multi-agent orchestration, businesses can deploy a single agent across their channels with shared context and without customer friction."). - Isolate where high latency and timeouts occur in your Agentforce solution. Use debugging tools described in "Troubleshooting Resources." For example: - In [Agent Analytics](https://help.salesforce.com/s/articleView?id=ai.generative_ai_agent_analytics.htm&release=264.0.0&type=5 "Analyze your AI agents’ performance within user and agent sessions. Agent Analytics is built on the unified Session Tracing Data Model (STDM), which captures every event and interaction within a session and logs it as individual events. You can query the logged ‌events to gain insights and optimize the Agent."), monitor "duration" metrics for your solution. In [Agent Health Monitoring](https://help.salesforce.com/s/articleView?id=ai.agent_monitor_health.htm&release=264.0.0&type=5 "Agent Health Monitoring detects and notifies you of silent agent failures—like spiking error rates or high latency—in near-real time across your AI agents. Rapidly respond to agent performance issues to mitigate customer impact."), set alert thresholds for relevant metrics and scores to trigger notifications when latency breaches threshold levels. - Investigate traces to identify which step takes how much time. Investigate logs for timeout errors (for example, see [Monitor Agentforce Session Log Events](https://help.salesforce.com/s/articleView?id=ai.agentforce_diagnostic_data_model.htm&release=264.0.0&type=5 "Monitor log events captured during AI agent sessions in the AI Agent Session Log data model object (DMO).")). The timeout limit for orchestrator agents is 120 seconds, which includes the elapsed time spent by the orchestrator agent doing overhead tasks, such as delegating and (in supervisor mode) synthesizing the results. In supervisor mode, the orchestrator agent synthesizes timeout errors. The timeout limit for connected subagents is 30 seconds.Use these symptoms to uncover latency root causes that you can remedy in your AI solution. ## How can I resolve issues with passing variables? Keep in mind that: - Custom (mutable) variables can be specified during the session. - Context (linked) variables are immutable and can’t be updated after the session has started. See [Agent Script Reference: Variables (Custom and Linked)](https://developer.salesforce.com/docs/ai/agentforce/guide/ascript-ref-variables.html) in the _Agentforce Developer Guide_. In Multi-agent Orchestration, there are two ways in which to pass variables: - From an orchestrator agent to a connected subagent. For connected subagents, input variables can be mapped. In both handoff and supervisor mode, you can map these input variables to either context or custom variables. See "Handoff and Supervisor Modes" in [Multi-Agent Orchestration](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch.htm&release=264.0.0&type=5 "Extend your agent’s capabilities with Multi-Agent Orchestration for Agentforce. Connect your Agentforce agents with other specialized Agentforce agents in your Salesforce org so that they can collaborate securely on complex tasks. With multi-agent orchestration, businesses can deploy a single agent across their channels with shared context and without customer friction."). ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png) Note In this release, variables are passed in one direction only: from the orchestrator agent to the connected subagent. Variables aren’t passed from a connected subagent back to the orchestrator agent. - Between connected subagents. In handoff mode, if a connected subagent has an After Response section, you can set variables before transitioning to another connected subagent. Because the next connected subagent receives these values only through its `inputs` block, any variables you set require mapping in the inputs block of the target connected subagent. Context doesn’t flow automatically. See [Connect an Agent as a Subagent](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch_connect.htm&release=264.0.0&type=5 "Add an agent as a connected subagent to your orchestrator agent. Your orchestrator agent can coordinate efforts among connected subagents, such as delegating tasks and synthesizing results.") in Salesforce Help and [Connected Subagent Block](https://developer.salesforce.com/docs/ai/agentforce/guide/ascript-blocks.html#connected-subagent-block) in the _Agentforce Developer Guide_. ## How can I resolve authentication issues? Your authentication approach varies by agent type and by the combination of orchestrator agent and connected subagent. - Agentforce Service Agent (ASA) connected subagents run as the orchestrator agent's session user (the digital user), not as its own agent user. ASA also supports unauthenticated guest users. - Agentforce Employee Agent (AEA) connected subagents run in the logged-in user's context. Assign the logged-in user the permissions required for any operation the connected subagent requests. To learn more, see: - [User-Level Authentication in Multi-Agent Solutions](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch_auth.htm&release=264.0.0&type=5 "Agentforce multi-agent solutions support user-level authentication. Authentication varies by agent type and by the combination of orchestrator agent and connected subagent.") - [Configure Service Agent Access](https://help.salesforce.com/s/articleView?id=ai.agent_user.htm&release=264.0.0&type=5 "Learn how Agentforce Service agents control data access. Set up an agent user for your Agentforce Service agent and assign permissions, so your agent has everything it needs to do its job.") - [Manage Employee Agent Access](https://help.salesforce.com/s/articleView?id=ai.agent_manage_aea_access.htm&release=264.0.0&type=5 "Control user access to specific Agentforce Employee agents with permission sets or profiles. In Agentforce Builder, use the Agent Access page. In the legacy Agentforce Builder, use the Agent Access tab.") ## What limitations can I consider for my Multi-agent Orchestration solution? - Review supported and unsupported functionality in [Considerations and Limitations in Multi-Agent Solutions](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch_consider.htm&release=264.0.0&type=5 "Review these considerations and limitations for Multi-Agent Orchestration for Agentforce."). - Multi-agent Orchestration enforces no limit on the number of connected subagents. Experiment with different combinations to come up with the optimal design that scales for your use case and environment. - For design recommendations, see "Tips for Designing Your Agent-to-Agent Solution" in [Multi-Agent Orchestration](https://help.salesforce.com/s/articleView?id=ai.agent_multi_orch.htm&release=264.0.0&type=5 "Extend your agent’s capabilities with Multi-Agent Orchestration for Agentforce. Connect your Agentforce agents with other specialized Agentforce agents in your Salesforce org so that they can collaborate securely on complex tasks. With multi-agent orchestration, businesses can deploy a single agent across their channels with shared context and without customer friction."). ## Troubleshooting Resources Agentforce provides tools and features that help you identify patterns, investigate root causes, and take corrective action. - In Agent Builder, use the Plan Tracer in the Conversation Preview Panel to investigate issues in your multi-agent solution. Inspect the detailed, step-by-step decisions and actions your orchestrator agent and connected subagents take during a conversation or workflow test. - Use [enhanced event logs](https://help.salesforce.com/s/articleView?id=ai.copilot_setup_enhanced_event_logs.htm&release=264.0.0&type=5 "Event logs capture the events and user messages in an agent session to help you test and troubleshoot your agent. In supported agent types, enable enhanced event logs to store conversation data and view all session activity in one place. When enhanced event logs aren't enabled, events associated with agent and user messages (such as Message sent: and User response:) are logged, but the messages themselves aren't included in the event.") to provide granular details about agent conversations. - Use [Agent Analytics](https://help.salesforce.com/s/articleView?id=ai.generative_ai_agent_analytics.htm&release=264.0.0&type=5 "Analyze your AI agents’ performance within user and agent sessions. Agent Analytics is built on the unified Session Tracing Data Model (STDM), which captures every event and interaction within a session and logs it as individual events. You can query the logged ‌events to gain insights and optimize the Agent.") to monitor agent performance and detect error trends. Investigate patterns and root causes at the session level (see [Analyze Data with Agent Optimization](https://help.salesforce.com/s/articleView?id=ai.generative_ai_optimize_use.htm&release=264.0.0&type=5 "Use Agent Optimization to drill into sessions, analyze quality scores, and identify patterns to improve your agent's performance.")). - In [Agent Health Monitoring](https://help.salesforce.com/s/articleView?id=ai.agent_monitor_health.htm&release=264.0.0&type=5 "Agent Health Monitoring detects and notifies you of silent agent failures—like spiking error rates or high latency—in near-real time across your AI agents. Rapidly respond to agent performance issues to mitigate customer impact."), set alert thresholds to trigger notifications when agent performance breaches threshold levels.