AI Customer Support Agent
Drafts the answer, never sends it behind your back
- 7output fields
- A structured result, not a paragraph you have to re-read
- ≤7steps per run
- Bounded work: at most 6 tool calls, enforced by the runtime
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.
Overview
Reads an incoming ticket, classifies it, retrieves the relevant knowledge from the sources you provide, and drafts a reply grounded in that knowledge.
When the knowledge base does not cover the question, it says so and escalates rather than improvising — which is the failure mode that makes support automation dangerous.
Benefits
Draft ready
Faster first response
A drafted reply waiting when the agent opens the ticket.
No invented policy
Refuses to answer beyond the knowledge it was given.
Cites the article it answered from
Each draft carries the knowledge it drew on, so an agent approving a reply can check the source in seconds instead of rereading the base.
What it does
Ticket classification
Category, urgency and sentiment on every ticket.
Grounded answers
Replies cite the article they came from.
Honest escalation
Says when the knowledge base does not cover it.
Approval before send
Sending is a write action and stays gated.
What this changes
What this changes about your week
- It takes over
- Answering the repetitive half of the support queue.
- Done today by
- Support, or the owner, all day.
- How often
- Continuously.
- Typical manual effort
- The routine tickets are most of a person's day.
Why Customer support in particular. Your team keeps the tickets that need a person, and the customer stops waiting overnight for an answer that was always going to be the same.
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
AI Customer Support Agent has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
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.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsfetch_web_page, summarize_text, send_email
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Demo
Demo dataIllustrative sample output.
Input
{
"ticket": "I was charged twice this month, can you refund one?",
"knowledgeSources": [
"https://example.com/billing-policy"
]
}Output
{
"urgency": "high",
"category": "Billing",
"canAnswer": true,
"citations": [
"https://example.com/billing-policy"
],
"sentiment": "frustrated",
"draftReply": "Thanks for flagging this…"
}Requirements
Integrations
Before you start
- Knowledge base URLs or article text
- Connect an email provider if you want the approved reply sent from PROMIVO
- Requires the All-Access plan or higher
Use cases
First-line triage
Classify and draft across the inbox.
Knowledge gap detection
Escalations reveal what the docs are missing.
Pricing
All-Access
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
What if it does not know the answer?
It escalates and states what was missing. It is explicitly instructed never to invent policy, pricing or a commitment.
How do I give it our knowledge base?
Point it at the article URLs, paste the text, or attach the document — a PDF or DOCX handbook is read on upload and never stored. It answers only from what you gave it.
Who pays for the AI usage?
You do, on your own provider key. It runs once per ticket, so the cost follows ticket volume; the knowledge you attach is the other half of what you are charged for.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent