Answers from your documents, and says nothing when they do not answer
Asking questions of your own documents is one of the largest demands in this whole market, and almost every implementation shares one silent failure: when the documents do not contain the answer, the model answers anyway — from what it knows about the world, in exactly the confident voice it uses when quoting your own contract. The reader cannot tell which is which, which makes it worse than a search box, because a search box that finds nothing says so.
This answers only from what it retrieved, and quotes it. Every claim carries the passage and the document it came from, so an answer can be checked in seconds rather than trusted.
When your documents do not answer the question, it says so and stops. It also says when they answer it in two different places with two different answers, rather than silently picking one — because in a company that has been running for a few years, contradictory documents are not an edge case, they are the normal state, and choosing between them is not a machine's job.
Because each one is traceable to a line in a real document.
Whoever asks, and whoever is on holiday.
The questions nothing answers are the documents you are missing.
An answer you can check in seconds rather than one you have to trust.
The whole product. Every other implementation answers from general knowledge in the same confident voice.
Two documents with two answers is the normal state of any company a few years old. Picking one is not a machine's job.
A superseded policy cannot be quoted back at you, because it is never retrieved.
It can only reach documents the person asking is allowed to open. That is enforced outside the agent.
When nothing covers the question, it names the document that would.
Why Customer support in particular. Every other implementation answers from general knowledge when your documents are silent, in the same confident voice it uses to quote your contract — and the reader cannot tell the difference.
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
Document Q&A Agent 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.
{
"question": "How long do we have to approve an invoice before it goes overdue?"
}{
"answer": "Your documents give two different answers, so I cannot tell you which applies. Both are below.",
"answered": false,
"escalate": true,
"citations": [],
"unanswered": "Which of the two governs, and whether the handbook was superseded.",
"contradictions": [
{
"document": "Finance Procedure v7 — section 2.3",
"position": "Approval within 5 working days of receipt."
},
{
"document": "Supplier Handbook 2025 — page 4",
"position": "Invoices are approved within 10 working days."
}
],
"escalationReason": "Two of your own documents give different answers to this question.",
"whatWouldAnswerIt": "A dated statement of which document takes precedence, or a withdrawal of the older one."
}No integrations required.
Policy and process questions, answered from the policy.
New starters ask the documents instead of interrupting someone.
What does our agreement actually say about this.
$179/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 says so and names what would answer it. It will not fall back on general knowledge — that is the failure this exists to avoid, and it is invisible to the person reading.
No. Retrieval is scoped to what the person asking may open, and that is enforced in the retrieval layer rather than by instructing the agent. An instruction can be talked around; a permission check cannot.
Superseded versions are never retrieved, so a withdrawn policy cannot be quoted back at you. The old text is kept, so an answer given last month can still be explained.
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