Support that knows your rules
The agent answers from the knowledge base with a source link, checks the order in the CRM and creates a ticket. Anything beyond its authority goes to an operator — with the context.
01Builder
Sketch your AI agent’s architecture
Pick tasks, sources, actions and the autonomy level — the diagram appears on the right: employee, agent, data, approval and actions.
Preliminary architectureNodes: 9
- Employee → Agent runtime
- Customer channel → Agent runtime
- Agent runtime → Guardrails · audit, LLM, Docs · RAG, CRM, Reply to user, Create ticket
- Guardrails · audit
- LLM
- Docs · RAG
- CRM
- Reply to user
- Create ticket
AGENT Support agent CONTEXT Docs · RAG · CRM ACTIONS Reply to user · Create ticket CONTROL Acts within tool permissions · Role-based access to sources · Audit log of every tool call
This is a preliminary outline. The architecture may change once we review the process and the data.
02AI Support
Where the line is
We define upfront what the agent decides itself and what it hands to a person: refunds above a limit, complaints, unusual cases.
- Answers only from the current knowledge base
- Handover to an operator with the conversation history
- A log of every action
Would a scripted FAQ bot be enough?
Support botsBotZone04Contact
What do you want to hand to AI?
Describe the task in your own words, answer five questions and get a preliminary AI agent schema. Or just write to us.
Preliminary AI agent schema
Step 1 of 7