Chatbots that frustrate customers
Scripted chatbots can't handle nuance. Customers get stuck in loops, abandon the chat, and call the support line anyway.
Resolve routine tickets autonomously, surface context instantly, and hand off to humans seamlessly — with full conversation history.
Full conversation history across bot-to-human handoff — no repeating the question, no re-explaining the problem
Refunds and account changes resume only with an identified approver — the agent cannot self-authorize
Tool-call replay for human agents on escalation — see every step the AI took before the handoff
Scripted chatbots can't handle nuance. Customers get stuck in loops, abandon the chat, and call the support line anyway.
Autonomous agents that can't escalate are a liability. One wrong refund, one leaked detail, and trust is gone.
When a bot hands off to a human, the conversation history disappears. The customer repeats everything. CSAT drops.
Three libraries give your support agents superpowers — and your customers a seamless experience.
@threadplane/langgraphLangGraph interrupts let the agent pause before sensitive actions — refunds, account changes, escalations. Thread persistence preserves the full conversation across bot-to-human handoffs.
Explore Agent@threadplane/renderThe agent renders structured UI — order summaries, refund confirmations, knowledge base cards — instead of dumping text. Customers see clean, actionable information.
Explore json-render@threadplane/chatProduction-ready chat UI with streaming messages, tool call visibility, and interrupt panels. When the agent escalates, the human agent sees the full debug overlay with every step the AI took.
Explore ChatA focused Angular example, using the components and agent APIs behind this workflow.
support-chat.component.ts — the escalation gate
export class SupportChatComponent {
protected readonly agent = injectAgent(SUPPORT_AGENT);
// Populated only while the graph is paused on an interrupt.
readonly pendingRefund = computed(() => this.agent.interrupt());
readonly awaitingHuman = computed(() => this.pendingRefund() !== null);
// Resuming carries the approver, so the record shows who authorized it —
// the agent has no path to approve its own refund.
approveRefund(approver: string) {
this.agent.submit({ resume: { approved: true, approver } });
}
denyRefund(reason: string) {
this.agent.submit({ resume: { approved: false, reason } });
}
send(message: string) {
this.agent.submit({ message });
}
}support-chat.component.html
<chat [agent]="agent" />
@if (pendingRefund(); as pending) {
<aside class="approval">
<h3>{{ pending.value.action }} — {{ pending.value.amount | currency }}</h3>
<p>{{ pending.value.reason }}</p>
<button (click)="approveRefund(currentAgentName())">Approve</button>
<button (click)="denyRefund('Outside policy')">Deny</button>
</aside>
}The agent proposes a destructive action, the graph pauses, and nothing runs until a human approves it.
Recorded from the live demo, which you can drive yourself.
Field report
Architecture, trade-offs and failure recovery
practical guidance
Angular and React implementation examples
both frameworks
Primary-source research and explicit API boundaries
free
Download the field report or start a pilot. Resolve routine tickets, escalate the rest with full context, keep your customers happy.