Ask most data chatbots why revenue fell and they will tell you why. The data almost never knows. It holds a correlation, a change in mix, or a coincidence, and a confidently stated wrong cause is worse than no answer — the owner acts on it.
This agent answers in three parts. What the numbers show, stated as arithmetic anyone can check. What they suggest, labelled as a hypothesis with what would confirm it. And what this data cannot answer, with what you would need to collect.
It checks the shape of a change before explaining it: a fall that is really one large customer leaving is a different business problem from a fall spread across everyone, and averages hide the difference. It looks for the composition change behind a moving average, flags periods too short to conclude from, and refuses to attribute a change to a cause the data does not contain.
You can tell a fact from a hypothesis at a glance.
Composition and cohort checks nobody has time to run.
The most valuable output is often 'this data cannot tell you that'.
Three separate sections. Mixing them is how a correlation becomes a decision.
One large customer leaving is not the same problem as a fall across everyone. Averages hide it.
The average moved because the mix moved, not because anything got better or worse.
Every figure shows how it was computed, from which rows.
Rather than reading a trend into three weeks of noise.
The unanswerable questions come with what data would answer them.
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.
Demo dataIllustrative sample output, abridged.
{
"data": "…",
"question": "Why did revenue fall 14% last month?"
}{
"shows": [
{
"finding": "Revenue fell 14.2%, from 84,100 to 72,150.",
"arithmetic": "Sum of order value, March vs February, all 412 orders.",
"population": "All completed orders. Refunds excluded — 6 rows."
},
{
"finding": "Two accounts explain 11 points of the 14.",
"arithmetic": "Those accounts fell 9,240 of the 11,950 total decline.",
"population": "Same set."
}
],
"escalate": false,
"suggests": [
{
"hypothesis": "This is an account-retention problem, not a demand problem.",
"whyPlausible": "The decline is concentrated in two accounts; the remaining 47 fell 3% combined.",
"whatWouldConfirm": "Whether those two accounts renewed, churned, or simply ordered later."
}
],
"cannotAnswer": [
{
"question": "Why those two accounts reduced their spend.",
"whatYouWouldNeed": "Account notes, support history, or a conversation. It is not in transaction data."
}
],
"shapeOfChange": "Concentrated, not broad. An average would have shown a 14% fall across the board, which is not what happened.",
"filtersApplied": [
"Refunded orders excluded",
"Test accounts excluded"
]
}No integrations required.
Find out what actually changed underneath it.
What genuinely changed, separated from noise.
Check whether the data supports what everyone is assuming.
$199/month
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits.
It will tell you what changed — which segments, which customers, which mix. Whether that caused the fall is usually a hypothesis, and it will label it as one and say what would confirm it.
Not yet. You supply the data — a table, an export, a summary. Direct connections need credentials and query permissions, which is a separate decision from analysis.
Only where the history genuinely supports one, and it will state the assumptions and the range. It will not produce a single confident number from a short or erratic series.
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