Run a simulation immediately

Learn about best practices.

1. On the left navigation bar, click Simulation workshop, and then click New simulation.

2. Simulation type: Choose the type of simulation. While this field doesn't currently affect simulation behavior, make an accurate selection, so your data is meaningful when options based on this value are introduced. Types include:

   • Test AI agents - This is for testing AI agents or conventional bots.
   • Train live agents - The process is transparent and for skill-building and practice.
   • Audit live agents - You're discreetly evaluating agents' performance without their knowledge.
3. Synthetic customer: Do either of the following:
   • Select Use existing to use an existing synthetic customer profile. This is fastest. In this case, select the profile from the dropdown.
   • Select Choose scenarios and personas to manually select the ones you want to use for only this simulation. Then select the relevant scenarios and personas from the dropdowns.

4. Customer identity: Choose the type of identity to use:

   • Generate random identity: The identities of all synthetic customers in the simulation are generated randomly. This is the case even if you have predefined identities specified in the scenarios; those predefined identities are not used.
   • Make customer anonymous: The synthetic customer is assigned only a random consumer ID.
   • Use predefined identity: The synthetic customer is assigned one of the predefined identities that's specified in the scenario. (Learn how and why identities are synchronized automatically to ensure each predefined identity is used in only one active conversation at a time.)

   If any selected scenario has no predefined identity at all, a dialog appears when you click Run simulation asking whether to proceed using a random identity for that scenario instead, or go back and add one.

5. Routing details: Choose how to route the conversations:

   • Start each conversation on scenario's skill: This keeps the initial routing more targeted.
   • Start all conversations on same skill: This overrides the scenario's setup. It's useful for end-to-end testing or training, where conversations should start on an initial skill.

6. Name: Enter a name for the simulation.

   We recommend you surface in the name a short descriptor for the target AI agent or live agent group. Also consider including your team or line of business, the specific use case, and a version or date. This makes it easy to identify your simulations at a glance and avoid confusion when multiple teams are working in the same environment. Strategies like these help you to remember why you ran the simulation.

7. Description: Optionally enter a short description of the simulation's objective or purpose.
8. Total conversations: Specify the total number of conversations in the simulation.

9. Max. concurrent conversations: Specify the maximum number of concurrent conversations overall in the simulation, not per agent. The upper limit is determined by the Total conversations setting or the predefined system maximum, whichever is lower.

   If the number of unique identities available across the selected scenarios is smaller than the value that you set for Max. concurrent conversations, then actual parallel execution will be limited to the number of available identities, since each simultaneous conversation needs its own identity. Unlike the identity dialog back in step 4, this appears as an inline note and doesn't block you from running the simulation. Add more identities to your scenarios, or lower your concurrency expectation to match available identities.

   To assign one concurrent conversation to every active agent, set this value to match your active agent count.

10. Max. conversation turns: Specify the maximum number of turns in each conversation. If this limit is reached, the conversation is closed by the system.

    A turn is a series of responses by the same participant; it ends when the participant changes.

11. Click Run simulation.

    After a simulation is completed, it takes a few minutes for the assessment to appear.

Stop a simulation

You can stop a simulation for any reason. For example, you might realize there's a mistake in the configuration, and you don't want the simulation to continue to run. Stopping a simulation closes all in-progress simulations in the agent workspace.

Transcripts: When you stop a simulation, you have access to the conversation transcripts for all conversations that were completed before the simulation was stopped. However, transcripts for any conversations that were in progress at the time of the stop are discarded and are not available.

Assessments: No overall summary, simulation assessment, or agent assessment results are available for a stopped simulation, as these are only generated once a simulation has reached its natural completion. While conversation assessments are provided, they are only available for the specific conversations that were completed before the simulation was stopped.

To stop a simulation

1. On the left navigation bar, click Simulation workshop.
2. Highlight the row for the simulation that you want to stop, and click the stop icon that appears.
3. Click Stop again to confirm the action.

Archive a simulation

Archiving a simulation merely labels it as "Archived" (not "Active"), so you can use the available filters to show or hide the simulation based on this state.

You can archive any simulation that isn't in progress.

To archive a simulation

1. On the left navigation bar, click Simulation workshop.
2. Highlight the row for the simulation that you want to archive, and click the (Archive simulation) icon that appears.

To unarchive, highlight the row and click the unarchive icon that appears.