Order status & tracking
"Where is my order?" "When will it ship?" "Why is my tracking not updating?", Orion pulls real-time status from your order DB and explains it in your brand voice.
Operational tier · Customer support
Orion, your AI tier-1 support agent.
Orion reads incoming support tickets, resolves routine tier-1 tickets autonomously, and escalates the rest to a human with full context attached. Your support team stops drowning in "where is my order" and starts handling the tickets that actually need them.
ModelWorkers AI models in your own Cloudflare account, routed per task
Price€0.05–€0.15 per resolution, €50–€300/month, +€500 per language
Connects toZendeskIntercomGorgiasShopifyStripeWhatsApp
Autonomy
- Suggests
- Acts with approval
- Acts on its own
Resolves routine tier-1 tickets on its own. Refunds stay within your limits; everything else goes to a person with full context. How autonomy works
What does Orion do?
Orion is an AI customer support agent. He reads inbound tickets from email, Zendesk, or Intercom, classifies them, retrieves the right answer from your knowledge base, resolves tier-1 questions autonomously (order status, account access, basic troubleshooting, refund eligibility, FAQ), and escalates everything else to a human with full context attached, the ticket, his reasoning, the customer's history, and a suggested response. Runs on Workers AI in your own Cloudflare account. Operational tier. Price: €0.05–€0.15 per resolution, €50–€300/month, +€500 per language.
theagency47 · Updated October 2026 The spec sheet
How Orion actually works.
| Job-to-be-done | Resolve tier-1 support tickets autonomously, escalate the rest with full context |
| Tier | Operational (departmental flow) |
| Underlying model | Workers AI models in your own Cloudflare account: a fast model for classification, a stronger one for resolution |
| Trigger | Event-driven on incoming ticket (webhook from Zendesk/Intercom or new email) |
| Inputs | Ticket content, customer profile, order/account history, knowledge base, brand voice document |
| Tools available | Knowledge-base retrieval, customer database read, order database read, refund tool (bounded amount), Slack escalation, draft response |
| Autonomous decisions | Ticket classification, knowledge-base citation, response drafting, refund within policy (typically < €50 or category-bounded), escalation when uncertain |
| Escalation rules | No matching KB article → human · Confidence score < 0.7 → human · Sentiment negative + repeat customer → human · Refund > policy → human · Legal/compliance flag detected → human |
| KPIs measured | Autonomous resolution rate, time to first response, time to resolution, customer-satisfaction (CSAT) score, escalation accuracy, cost per ticket |
| Eval suite | 30 test cases (60% common-case, 25% edge, 15% adversarial including prompt-injection). |
| Audit trail | Every action logged with KB citations used, confidence score, and decision reasoning |
What he handles autonomously
The repetitive part of your tier-1 volume.
Account access
Password reset triggers, login issue diagnostics, account merge requests for duplicate signups. Handled inside policy with audit logging.
Basic troubleshooting
Standard product-knowledge questions resolved from the KB. "How do I export X?" "Does feature Y support Z?" "Why is the dashboard showing N?"
Refunds within policy
Orion can issue bounded refunds (typical limit: under €50, certain categories). Anything outside policy escalates with refund recommendation.
FAQ resolution
"Do you ship internationally?" "What is your return policy?" "Is there a free trial?", all resolved from the KB with full citation.
Smart escalation
When something is outside scope, Orion writes a perfect handoff message, ticket summary, customer context, reasoning trace, suggested next steps. Human picks up where he left off.
Configuration deep-dive
The two design choices that make Orion reliable.
1. Strict retrieval-augmented generation
Every claim Orion makes must be traceable to a source in your knowledge base. If a customer asks "what is your return policy?" and the answer is not in the KB, Orion does not guess from training data, he escalates. This is the single biggest design choice in his architecture. It eliminates the hallucination class of failures entirely.
Practical consequence: your knowledge base becomes the single source of truth. We document this dependency in the engagement and build a 5-day KB ingestion phase into every deployment.
2. Bounded action authority
Orion can read most things but write very few. Specifically: he can draft a response (always reviewed in first 14 days, sampled thereafter), issue a refund within a configurable limit, update a ticket status. He cannot change customer account details, modify billing terms, contact other customers, send marketing communications, or alter the knowledge base itself (KB updates are a separate human-approved flow).
Practical consequence: the worst-case bug is a confused response, not a corrupted database or a leaked customer record.
FAQ
Questions about Orion.
What does Orion do?
AI customer support agent. Reads tickets, retrieves answers from KB, resolves tier-1 (order, account, troubleshooting, FAQ, bounded refunds) autonomously, escalates the rest with full context. Operational tier, multi-model.
How much support volume can he handle autonomously?
The routine tier-1 tickets: order status, account access, basic troubleshooting, bounded refunds and FAQ. How much of your volume that is depends on your ticket mix and on how complete your knowledge base is. Everything else escalates to a person with full context, so your team handles fewer but more meaningful tickets.
Will Orion hallucinate?
No, when configured correctly. Strict retrieval-augmented generation: every claim must be sourced in the KB. If not in KB, escalates. Eval suite specifically tests for hallucination with adversarial inputs.
How is Orion different from Intercom Fin or Zendesk AI?
Those are SaaS chatbots configured in-product. Orion is custom-built for you: trained on full KB (not just site crawl), integrates with internal systems (order DB, billing), tuned escalation policy, owned by you. Price: €0.05–€0.15 per resolution, €50–€300/month, +€500 per language.
How much does customizing Orion cost?
Orion template customized to your business: deployable as Spark (€2,500, 14 days) or part of Workforce engagement. Price: €0.05–€0.15 per resolution, €50–€300/month, +€500 per language.
Will Orion replace our support team?
No. He takes over routine tier-1 tickets, freeing the team to handle complex tickets, build deeper customer relationships, and improve the KB. Most clients keep team size flat and grow business with it.
What about angry customers and edge cases?
Both escalate. Sentiment-detection flags negative emotion → human. Out-of-scope topics → human. Ambiguous tickets → human with confidence score and recommendation. Orion handles the routine tickets; people handle the hard ones.
Does Orion handle multiple languages?
Yes, given a KB in the target language. Standard configuration handles English; multi-language support adds 1 day of setup per additional language (+€500 per language).
New to AI in support? Read how an AI agent for customer support works.
