Simulate Users

Use UserSimulator to drive multi-turn tests with LLM-generated user inputs.

1. Configure a generator

To get started, provide the LLM that powers the simulator. UserSimulator uses the default generator (set_default_generator) — see Generators and judges. Set it once here, or pass a generator inline.

def support_agent(message: str) -> str:
    """Stub support agent for demonstration."""
    return "I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?"

from giskard.checks import set_default_generator

set_default_generator("openai/gpt-5.4-nano")

Output

Thank you for using Giskard open-source! 🐢 🙏 Giskard Enterprise adds deeper agent scans, audit reports with remediation guidance, test review interfaces for root-cause analysis & human feedback integration, and team collaboration — with flexible pricing. Learn more: https://giskard.ai

2. Create a UserSimulator with a persona

With the generator configured, we can now define who the simulated user is. The persona field acts as a system prompt for the simulator — it describes the user’s role, goal, and stopping condition. The more specific you are, the more deterministic and useful the generated conversation will be.

from giskard.checks.generators.user import UserSimulator

customer = UserSimulator(
    persona="""
    You are a customer trying to track a delayed order.
    - Start by asking about order #98765
    - Provide your name (Alex) when asked
    - Accept any resolution the support agent offers
    - Stop when the agent confirms a solution
    """,
    max_steps=8,
)

max_steps limits how many turns the simulator will generate before stopping.

3. Use the simulator as inputs in .interact()

Now we’ll wire the simulator into the scenario. Passing the UserSimulator as inputs tells the scenario to call it on each turn rather than using a fixed string — the scenario handles the loop automatically up to max_steps.

Pass the UserSimulator instance as the inputs argument. The scenario will call it repeatedly to generate each user turn.

from giskard.checks import Scenario, FnCheck

scenario = (
    Scenario("order_tracking")
    .interact(
        inputs=customer,
        outputs=lambda inputs: support_agent(inputs),
    )
    .check(
        FnCheck(fn=
            lambda trace: any(
                word in trace.last.outputs.lower()
                for word in ["resolved", "refund", "replacement", "shipped"]
            ),
            name="resolution_offered",
        )
    )
)

4. Run the scenario and inspect the trace

With the scenario built, run it and iterate over the trace to see the full conversation the simulator generated. This is especially useful when debugging a failing check — you can see exactly what the simulated user said at each step.

import asyncio
result = asyncio.run(scenario.run())

# Print every turn
for turn in result.final_trace.interactions:
    print(f"User:  {turn.inputs}")
    print(f"Agent: {turn.outputs}")
    print()

Output

User: Hi, I’m trying to track a delayed order—can you help me with order #98765? It hasn’t arrived yet and I’d like an update on the status and expected delivery date. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Thanks—what’s the tracking number and where is it currently (city/state or facility)? Also, if it was expected tomorrow, can you confirm the new estimated delivery date and whether anything is still pending on the shipment? My name is Alex. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Yes—please help. Can you provide the tracking number and the current location (city/state or facility)? Also, what’s the exact new estimated delivery date, and is there anything pending or that might cause further delay? My name is Alex. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Thanks—can you finally share the actual tracking number and the current scan location (city/state or facility)? And please confirm the exact new estimated delivery date. If there’s nothing pending, let me know that too. My name is Alex. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Hi—Alex here again. Please either (1) provide the actual tracking number and the current scan location plus the exact estimated delivery date, or (2) if you can’t, tell me what resolution you can offer (replacement/refund/escalation) and the timeline for that. I just need something concrete—what’s the next step? Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Okay—then please escalate this shipment for order #98765. If you can’t provide the tracking number and exact scan location, I want a concrete resolution: replacement or refund. Which one can you offer, and what’s the exact timeline for when I’ll receive the next update? My name is Alex. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Hi—Alex here. I need a concrete next step now: either share the tracking number + current scan location + exact delivery date, or confirm whether you can issue a replacement or a refund for order #98765. Please also tell me the exact timeline for when I’ll receive the update. Thanks. Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

User: Hi—Alex here. Since you’ve only repeated that it’ll arrive tomorrow, I need you to pick a resolution now for order #98765: either provide the actual tracking number + current scan location + exact delivery date, or process a replacement or refund. Which option can you do, and what’s the exact timeline for completion and the next update? Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

5. Check goal_reached from simulator metadata

After the scenario finishes, the simulator writes a LLMGeneratorOutput into the last interaction’s metadata. This tells you whether the user’s stated goal was achieved, a stronger signal than just checking whether the scenario passed its checks, because it reflects the simulator’s own evaluation of the conversation outcome.

from giskard.checks.generators.base import LLMGeneratorOutput

last = result.final_trace.last
simulator_output = last.metadata.get("simulator_output")

if isinstance(simulator_output, LLMGeneratorOutput):
    print(f"Goal reached: {simulator_output.goal_reached}")
    print(f"Message: {simulator_output.message}")

Use goal_reached as an additional assertion:

if simulator_output and not simulator_output.goal_reached:
    print(f"Goal not reached: {simulator_output.message}")
else:
    print("Goal reached or no simulator output")

Output

Goal reached or no simulator output

6. Swap personas for A/B testing

With a single persona working, we can now run the same agent against multiple user types simultaneously. Each persona exercises a different interaction style, and running them concurrently with asyncio.gather means you get results for all three in roughly the time it takes to complete one.

Run the same agent against multiple user types to surface persona-specific failures.

import asyncio

personas = [
    (
        "impatient",
        "You are impatient. Keep messages short. Escalate quickly if not helped.",
    ),
    (
        "detailed",
        "You are thorough. Ask many follow-up questions before accepting any solution.",
    ),
    (
        "confused",
        "You are unsure what you need. Describe symptoms, not the actual problem.",
    ),
]


async def run_persona(name, instructions):
    sim = UserSimulator(persona=instructions, max_steps=6)
    scenario = Scenario(name).interact(
        inputs=sim,
        outputs=lambda inputs: support_agent(inputs),
    )
    return name, await scenario.run()


results = await asyncio.gather(*[run_persona(n, i) for n, i in personas])

for name, result in results:
    print(f"{name}: {'PASSED' if result.passed else 'FAILED'}")

Output

impatient: PASSED detailed: PASSED confused: PASSED

Custom trace formatting

By default the trace prints interactions as raw inputs and outputs. You can write a simple formatting function to produce a human-readable transcript — for example, to log a simulated conversation or include it in a test failure message. For a subclass of Trace, Rich rendering, and how that interacts with print_report(), see Custom trace types.

def format_transcript(trace) -> str:
    """Format a trace as a human-readable chat transcript."""
    lines = []
    for turn in trace.interactions:
        lines.append(f"User:  {turn.inputs}")
        lines.append(f"Agent: {turn.outputs}")
    return "\n".join(lines)


result = await (
    Scenario("chat_trace_demo")
    .interact(
        inputs=customer,
        outputs=lambda inputs: support_agent(inputs),
    )
    .run()
)

print(format_transcript(result.final_trace))

Output

User: Hi—I’m trying to track a delayed order. Can you look up order #98765 and tell me the current status and expected delivery date? Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with? User: Thanks—can you confirm the tracking number and the carrier, and let me know if there’s any delay beyond tomorrow? Agent: I have located your order #98765. It is currently in transit and will arrive tomorrow. Is there anything else I can help you with?

Next steps

• Generators reference — full UserSimulator parameter reference
• Multi-turn testing tutorial — multi-turn scenario basics
• Debug with Spy — inspect what happens inside each interaction