Finds where work waits, not where people work
Ask a team how long their process takes and they will add up the work: an hour to review, twenty minutes to approve, half a day to prepare. Measure it end to end and it takes eleven days. The difference is queue time — work sitting in an inbox, waiting for a batch run, waiting for a meeting that happens on Tuesdays, waiting for the one person who can do that step.
Almost every improvement effort targets touch time, because that is what people can see themselves doing. It is usually under a tenth of the total, so halving it changes end-to-end time by almost nothing, and everyone concludes the process is simply complicated.
Queue time is visible in timestamps every workflow system already records, and it is rarely spread evenly. It concentrates at one step, usually for a structural reason: a single approver, a step that only runs with a batch, a handover between teams in different time zones, or a rejection loop where work goes backwards and rejoins the queue at the end.
That last one is the finding people miss most, because rework is invisible in a throughput number — the item eventually completes.
This agent reports where the time actually goes, names the structural cause of each queue, and says what removing it would change. It alters no workflow and never assesses an individual.
Rather than at the part everyone can see themselves doing.
Because the queue is where the days are.
It is usually the second largest cost and it appears in no report.
Touch time is usually under a tenth of the total. Halving it changes nothing, and that is why improvement efforts disappoint.
A single approver, a batch window, a time-zone handover. Not "this step is slow".
Work that goes backwards and rejoins the queue. Invisible in throughput, because the item eventually completes.
One person who can do a step, and what the process does the week they are away.
In days off the end-to-end time, so the fixes can be compared.
A queue at one person's step is a capacity and design finding. Measuring people's speed changes what gets recorded, not what happens.
Why Operations in particular. Touch time is usually under a tenth of the total, so every improvement effort targets the visible part and changes almost nothing. And rework is invisible in throughput, because the item eventually completes.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Process Bottleneck Analyst has no path to sending, spending or committing. That limit is why its output is safe to act on.
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
Read-only by design. This agent has no path to sending, spending, publishing or committing anything. Where that limit is the product, removing it would remove the reason to trust the output.
Demo dataIllustrative sample output, abridged.
{
"items": [],
"period": "H1 2026",
"process": "Customer onboarding"
}{
"rework": {
"commonestLoop": "Credit approval returns items to document check for a missing signature, and they rejoin the queue at the end rather than where they left. None of this appears in throughput, because every one of them eventually completes.",
"addedElapsedHours": 96,
"itemsAffectedPercent": 22
},
"endToEnd": {
"p90Hours": 812,
"medianHours": 264,
"queueTimeHours": 245,
"touchTimeHours": 19,
"queueSharePercent": 92.8
},
"escalate": true,
"disclaimer": "An analysis of your own workflow timestamps. No workflow or assignment has been changed, no individual's speed has been measured or compared, no approval or control is recommended for removal without stating what it prevents, and distributions are reported rather than averages.",
"workingWell": [
"Account setup completes in a median of 40 minutes with no queue. Nothing here should touch it."
],
"queuesByStep": [
{
"step": "Credit approval",
"structuralCause": "One approver holds this step and it waits for the Tuesday credit meeting. An item arriving Wednesday morning waits six days before anyone looks at it.",
"medianQueueHours": 118,
"shareOfTotalQueue": 48.2,
"removingItWouldSave": "Roughly 4.5 days off the median, more than every other fix combined."
},
{
"step": "Document check",
"structuralCause": "A handover between two teams whose working hours overlap by three hours a day.",
"medianQueueHours": 46,
"shareOfTotalQueue": 18.8,
"removingItWouldSave": "About 1.5 days."
}
],
"couldNotMeasure": [
"Started timestamps are missing on one step, so its touch time is excluded and queue time is overstated for it."
],
"distributionNote": "Median 11 days, 90th percentile 34 days. The average of 14 describes almost nothing and is the number currently reported.",
"escalationReason": "One step holds 48.2% of all queue time, depends on a single approver with no cover, and rework affects 22% of items.",
"singleDependencies": [
"Credit approval has one approver and no cover. In the two weeks they were away, median elapsed time went from 11 days to 19."
]
}No integrations required.
Where the time actually goes.
Whether that step is the constraint or the visible one.
Which queue is causing the breaches.
Whether the queue moved rather than disappeared.
$299/month
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits.
No, and it must not. A queue at one person's step is a capacity and design finding. Measuring people's speed changes what gets recorded rather than what happens, and it destroys the data this depends on.
No. It has no access to any workflow system and alters nothing. It reports where the time goes.
Timestamps: when each item entered and left each step, and who or what handled it. Every workflow, ticketing and case system already records this, and almost nobody reads it end to end.
No reviews yet. Reviews open once customers have run this agent.
Tell us what to change and our team will scope a customised version for your business.
Customize this agent