Loading
The online Trailblazer Community becomes read-only Oct 30, 2026Read More
Important Advisory: iOS Update Impacting CG Mobile ApplicationRead More
Agentforce and Einstein Generative AI
Improve Agent Performance with Agent Optimizer (Beta)

You are here:

  1. Salesforce Help
  2. Docs
  3. Quickstart Your Einstein Generative AI Solution

Improve Agent Performance with Agent Optimizer (Beta)

Understand agent performance, identify high-impact problems, investigate their causes, and get suggestions for improving sessions in Agentforce Studio.

Required Editions

Available in: Enterprise, Performance, and Unlimited Editions with an Einstein for Sales, Einstein for Platform, Einstein for Service, Einstein 1 Service, or Einstein GPT Service add-on. To purchase add-ons, contact your Salesforce account executive.
Note
Note Agent Optimizer is a pilot or beta service that is subject to the Beta Services Terms at Agreements - Salesforce.com or a written Unified Pilot Agreement if executed by Customer, and applicable terms in the Product Terms Directory. Use of this pilot or beta service is at the Customer's sole discretion.

Considerations

  • Make sure that your org is collecting session tracing data and that you can access the agents and sessions that you want to investigate. Available results depend on your permissions, the selected agent and timeframe, the channels in use, and processed session data.
  • If Agent Optimizer isn't available, in Setup | Einstein Audit, Analytics, and Monitoring Setup, make sure that Agentforce Session Tracing, Agent Optimization, and Agentforce Optimization Agent are enabled.
  • Using Agent Optimizer doesn't consume Agentforce credits.

Enable Agent Optimizer

Einstein Audit, Analytics, and Monitoring Setup with Agentforce Session Tracing, Agent Optimization, and Agentforce Optimization Agent enabled.

Agent Optimizer analyzes session data to help you understand and improve agent performance.

Use Agent Optimizer to:

  • Understand performance at a glance: Explore activity, trends, and comparisons across your agents without building a report.
  • Prioritize high-impact problems: Identify recurring failures and focus on the issues that affect the most users.
  • Investigate possible causes: Move from a high-level pattern to the representative sessions and evidence behind it.
  • Discover unmet customer needs: Find knowledge gaps, missing actions, and unsupported requests that your agents encounter.
  • Decide what to improve: Get evidence-based suggestions for content, configuration, instructions, and agent capabilities.

Need inspiration on how to use Agent Optimizer? Explore these scenarios. The scenarios and prompts are examples, not an exhaustive list of Agent Optimizer capabilities.

  1. In Agentforce Studio, select Analytics.
  2. Select Ask Agentforce to open the Agent Optimizer panel.
    Service Agent Analytics page with Analytics and Ask Agentforce highlighted.
  3. Try a scenario and continue the investigation with follow-up prompts.

    Use Case 1: Investigate an increase in escalations

    An agent's escalation rate increased last week. Use Agent Optimizer to size the increase, investigate why it happened, and decide what to address.

    • Start: Ask How many sessions escalated for [agent name] last week, and how does that compare with the previous week?
    • Follow up: Ask What were the top reasons those sessions escalated?
    • Decide: Ask Show me a session affected by the permission error and explain what happened.
    Agent Optimizer response showing the user's question, selected subagent, knowledge action, insufficient access error, agent recovery, and later turns.

    Use Case 2: Diagnose operational errors

    Users are encountering operational errors. Use Agent Optimizer to determine whether the errors are isolated or sustained and which agent is affected.

    • Start: Ask Which operational errors occurred most often this week?
    • Follow up: Ask Show me more details about the rate limiting errors, including when they occurred and which agents were affected.
    • Decide: Ask Was this an isolated traffic burst or a sustained problem, and what should I investigate next?
    Agent Optimizer response showing the distribution and timing of rate-limiting errors, the affected agent, peak usage context, and key findings.

    Use Case 3: Prioritize knowledge gaps

    Users ask questions that the agent can't answer. Use Agent Optimizer to find recurring knowledge gaps and prioritize new or improved content.

    • Start: Ask What are the best knowledge candidates for FAQ creation?
    • Follow up: Ask Which unanswered questions occurred most often last week?
    • Decide: Ask Show me the sessions behind the most common gap and suggest the content that I should add.
    Agent Optimizer response listing frequently asked questions that have no knowledge coverage.

    Use Case 4: Discover unsupported customer needs

    Customers repeatedly request capabilities that the agent doesn't support. Use Agent Optimizer to group unsupported requests and decide whether to expand the agent's scope.

    • Start: Ask Categorize my session failures into action errors, knowledge gaps, and off-topic queries.
    • Follow up: Ask Cluster the off-topic queries by what users were trying to accomplish.
    • Decide: Ask Show me the sessions for the missing roadside-assistance dispatch action and suggest how the agent could support it.
    Agent Optimizer response explaining sampled action, reasoning, prompt, and content gaps and listing common action-gap patterns.

Use evidence from multiple representative sessions before changing your agent. Test the targeted change, deploy it through your normal process, and compare the same performance signals afterward to confirm that the change helped without causing regressions.

Get Better Results from Agent Optimizer

  • Ask for supporting evidence. Ask how Agent Optimizer reached a conclusion or which sessions are included in a pattern. Review the identified sessions before acting on the response.
  • Include a timeframe. For example, specify in the last 7 days or between May 30 and June 29. Without a timeframe, Agent Optimizer uses a recent default timeframe, which can differ from the period that you want to analyze.
  • Narrow the scope. Specify an agent or subagent when possible. Approximate names are supported and resolved to the corresponding agent or subagent.
  • Go from what or how much to why. Start with an overview or exact count, such as What were the top reasons my agent failed last week? or How many sessions escalated for the refund subagent last week? Then ask Why did those sessions escalate? to analyze the sessions behind the result. Overviews help you size an issue, and follow-up diagnosis helps you understand the cause.
  • Increase the sample when needed. Ask Agent Optimizer to review more sessions or widen the timeframe before reaching a conclusion. A single analysis can sample up to 1,000 sessions.
  • Provide a session ID for one conversation. For example, ask What happened in session [session ID]? or Why did session [session ID] escalate? to get a focused explanation.

Limitations

  • Diagnosis of a group of sessions is based on a sample, not every session in the group. The default sample is approximately 100 sessions, and the maximum is 1,000 sessions per analysis. Use counts when you need an exact total, and use sampled analysis to investigate possible causes.
  • Very recent sessions can be unavailable for detailed analysis. Conversation transcripts can take approximately 15–30 minutes to become available, so sessions that are less than 30 minutes old are excluded from detailed analysis.
  • If a requested metric or analysis is unavailable, the required source data or metric can be disabled for your org. Contact your Salesforce admin to verify that the required Agentforce metrics and session tracing data are enabled.
 
Loading
Salesforce Help | Article