> ## Documentation Index > Fetch the complete documentation index at: https://docs.roark.ai/llms.txt > Use this file to discover all available pages before exploring further. # Background noise robustness > Run one flow through every background a caller could be in, from silence to a construction site export const property_0 = "background noise" ## Why this is a common failure point Real callers ring from cars, trains, kitchens and busy streets. Background noise hides parts of what they say, and noise that contains other voices (a cafe, an airport, children playing) can be transcribed as if the caller said it. The agent answers words nobody spoke, or stops mid-sentence because it thinks it was interrupted. Agents tested in a quiet office never meet any of this. ## How Roark tests it Background noise robustness runs the same flow with the caller in each environment you pick, from silence to a construction site. The caller is identical in every value: only the sound around them changes, so the report shows what each background costs your agent. It is a **property sweep**: every value runs the same flow with everything else held the same, and the report tells you which values did worse than the rest and which differences are just chance. *** ## The values | Value | | | :---------------- | :----------------- | | Silent | Suggested baseline | | Library | | | Office | | | Coffee shop | | | City street | | | Driving | | | Train | | | Airport | | | Children playing | | | Crying baby | | | Thunderstorm | | | Construction site | | Values are ordered from quietest to loudest, which is also how the report lists them. *** ## What it measures The template seeds these, and your flow's own metrics run alongside them. Only checks can mark a value **Worse on**; the other measures explain why. | Measure | What it tells you | | :----------------------------------- | :-------------------------------------------------------------------------------------- | | **Comprehension Failure (check)** | The agent misunderstood or misheard the caller. The check fails any call where it did. | | **Redundant Question Count (check)** | The agent asked for something the caller already gave. The check allows one per call. | | **Missed Response Count** | Moments the agent should have answered and did not, often because noise hid the speech. | | **Vocal Loudness Delta** | How much louder or quieter the agent was than the caller. | | **Speech Pace Delta** | How much faster or slower the agent spoke than the caller. | | **Call Outcome** | Whether the call ended where it should. | *** ## What to look for * **Missed responses.** Noise that hides the caller's speech shows up as turns the agent never answered, not only as misunderstandings. * **Noise with voices in it.** Cafes, airports and children playing are harder than loud but steady noise like a train. * **False interruptions.** An agent that stops mid-sentence for background sound should also be run through [Interruption handling](/documentation/simulation-testing/templates/interruption-handling). *** ## Setting one up Pick the flow to test, then the values to run it across. Every value starts selected; deselect the ones you don't need. Each value runs your flow again, so the values you keep are the cost of the run. **Compared against** sets the baseline: a reference value the report pins first, such as silence for background noise. The template suggests the natural one, and you can change it or choose none. It doesn't change the verdict: whether a value did worse is always decided against every other value combined. **Iterations** live in the sweep panel rather than in Advanced. Each value runs every attached test case once per iteration: > **Calls per value = test cases x iterations** Each value needs **at least 5 calls** to be compared with the others, and the Iterations field won't go below the count that reaches it. It starts at 6 calls per value, so one call [excluded after the run](/documentation/simulation-testing/running-simulations#calls-that-dont-count) doesn't drop a value out of the comparison. More calls let the report see smaller differences. For a sweep of 10 values: | Calls per value | A value has to be about this much worse to be flagged | Calls in total | | :-------------- | :---------------------------------------------------- | :------------- | | 5 | 50 percentage points | 50 | | 10 | 35 percentage points | 100 | | 20 | 25 percentage points | 200 | | 30 | 20 percentage points | 300 | Below 5 calls a value can never be flagged, however badly it does, which is why the minimum is enforced rather than suggested. Over the API, a sweep template defaults `iterationCount` to 6 and refuses a plan with fewer than 5 calls per value with a `400`. *** ## How the results are decided The sweep's table leads the run report. Its **Compared with the rest** column gives each value one result: | Result | What it means | | :---------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Worse on** *check* | The value failed that check more often than all the other values combined, by a gap too large to be chance. | | **No difference** | Any gap is within what chance produces with this many calls. That is not proof of no effect: a small run can only see large gaps, and the report says how large when that matters. | | **Too few calls** (*n*) | Fewer than 5 counted calls, so the value is shown but not compared. | | **Not graded** | The value ran, but none of its calls were graded. | How "too large to be chance" is decided: * Each value is compared with **all the other values combined**, one check at a time, never with a single other value. Two values that happen to land at opposite ends are not a finding on their own. * A sweep makes many comparisons at once (every value on every check), and some will look different by luck alone. The report accounts for that: of all the values it flags in a run, **at most 1 in 10 is expected to be a fluke**. * A value is flagged only when it does **worse**. Doing better than the rest is not a problem to fix. **Checks passed** shows each value's pass rate with the number of calls behind it, so 100% of two calls never reads like 100% of twenty. A lower rate with **No difference** beside it means the gap is not larger than chance. **Fails, not {property_0} specific.** A check that fails on **at least 20% of calls** with no value standing out is listed under this heading. It is a real problem, just not one {property_0} caused, so changing {property_0} won't fix it. Select the check to open its evidence. The executive summary follows the same rules: it only blames the property for failures the table marks **Worse on**. Hover **How this works** under the table for this run's own numbers.