E-commerce
Support agent
A support agent that resolves the routine tickets end-to-end and hands the rest to a human with full context — scoped tightly enough to be trusted with real customer conversations.
- LangGraph
- Anthropic
- River
tickets auto-resolved
first-response time
In short
- Routine tickets resolve end-to-end; only what needs judgement reaches a human.
- Every escalation arrives with the full thread and order context — no repeating.
- Agent runs are durable, so a campaign spike queues instead of dropping customers.
The engagement
- Sector
- Consumer e-commerce
- Company shape
- Scale-up, high ticket volume
- Engagement
- Agent build + handoff design
Anonymised by policy
The challenge
The support queue grew with every campaign, and hiring couldn't keep pace. Most tickets were routine and repetitive, but the long tail needed a human — so a blunt 'automate everything' bot would have made the experience worse.
The approach
- 1Scope to what's safe to automate
We mapped the ticket taxonomy and automated only the categories the agent could resolve reliably, with tools scoped to safe actions.
- 2Context-rich handoff
When the agent hands off, the human inherits the full conversation, the attempted resolution, and the relevant order context — no repeating themselves.
- 3Durable, observable runs
Agent runs are durable jobs (River) so a slow tool call or retry never drops a customer, and every run is traceable.
The solution
A LangGraph agent handles the routine categories with tools scoped to safe actions, resolves what it can end-to-end, and escalates the rest with full context attached. Runs are durable background jobs so nothing is lost to a timeout, and the whole thing is observable per conversation.
The system we built
- Classifyticket → category
- Resolvescoped tools
- Confidence checkcan we close it?
- Escalatecontext-rich handoff
The results
tickets auto-resolved
of incoming tickets, end-to-end
first-response time
vs. the pre-agent baseline
Data & safety
- Guardrails
- Tools are scoped to safe actions; anything outside the automatable envelope escalates to a human.
- Evaluation
- Per-category resolution and escalation quality are tracked so the safe-to-automate set stays honest.
- Data handling
- Customer data stays within the support stack; every run is durable and auditable.
The stack
- LangGraph
- Anthropic
- River