Human support team
People who answer like your brand would.
Our agents take every conversation that involves money, a problem or judgement, starting from an AI draft with the order and the right policy, for brands worldwide.
Who does what
A small team around your brand.
- Support agents
- Answer customers, edit and send AI drafts, handle returns and refunds within the limits you set.
- Team lead
- Reviews a sample of replies every week, coaches agents and updates your playbook with you.
- Your approvers
- People on your side who decide on refunds and compensations above the agents’ limits, in one click from the portal.
How agents work
Faster with AI, accountable as people.
- They start from a draft
- The AI prepares the reply with the order and the policy; the agent checks the sources and decides.
- They follow your limits
- Refund and compensation limits are enforced by the platform, not by memory.
- They are measured
- Service levels, quality scores and customer ratings for every agent and every conversation.
- Damaged item 12 minPerson
- Missing item 41 minDraft ready for the agent
- Refund request 1 h 05Approval
Copilot draft · for the agent
The carrier marked it delivered yesterday at 14:10. Could you check with neighbours or your building’s mailroom? If it has not turned up by tomorrow, we will open an investigation with the carrier.
- Verified order data · delivered, carrier scan
- Verified knowledge · delivery FAQ
- Customer-provided · “I have nothing”
Illustration of the agent inbox with sample data.
Coverage
Languages and hours.
- Languages
- French, English, Spanish, Arabic
- Hours
- Seven days a week; your hours depend on your plan.
Pricing
AI + Human Support: €349 / month
Essentials · 150 conversations included, then €0.85 per AI resolution · €2.20 per agent resolution. A conversation reopened within 72 hours is billed once.
Are the agents shared between brands?
Yes: on the AI + Human Support plans agents work for several brands, each with its own playbook, and follow your policies and limits on every reply.
How are agents trained on our brand?
Before go-live we write your knowledge base and playbook with you: policies, brand voice, agent limits and escalation rules. Agents learn from it and from your real past tickets.
How do we check their work?
You can read every conversation in the portal. Each reply has a quality score, and you can rate conversations yourself.
Can external agents see all our customers?
No. External agents only see the open queue and their own conversations, and only the customers and orders behind those conversations. This is enforced by the database.
Book a free demo
Let’s look at your real tickets.
In 30 minutes we go through a sample of your conversations, show which ones the AI could answer and which need a person, and give you a price.