EchoStack Docs
Integration guides API reference Open dashboard

Support triage

Use the Evaluation API with support triage playbooks to score severity, detect escalation signals, and route tickets before an agent reads the queue.

Outcome

P0/P1 or explicit enterprise tier can trigger ESCALATE; routine and underspecified tickets map to GATHER_INFO so automation can request missing priority or account metadata.

Prerequisites

  • Deploy a Support Triage (or similar) evaluation playbook
  • Org key esk_… from Dashboard → API Keys and an evaluation_id from POST /v1/evaluations
  • Ticket or email source (Zendesk, Intercom, forwarded email, n8n webhook)

Architecture

New ticket / email
    → POST /v1/evaluate
    → status + next_action
        → ESCALATE → PagerDuty / Slack #support-urgent
        → QUALIFIED / PARTIAL / FAILED → GATHER_INFO (v1.1.0) — route or ask for missing fields

Recommended header (from your helpdesk before evaluate):

Severity: P2 | Tier: enterprise | SLA: 4h
---
<ticket body>

Request shapes

Ticket (input_type: "ticket")

Use when your playbook expects ticket-shaped input:

{
  "input_type": "ticket",
  "input": [
    {
      "role": "user",
      "content": "Subject: Production API down\n\nWe cannot process payments since 09:00 UTC. Error 503 on all endpoints. Account: acme-prod."
    }
  ],
  "options": { "request_next_action": true }
}

Email (input_type: "email")

{
  "input_type": "email",
  "input": [
    {
      "role": "user",
      "content": "From: customer@example.com\n\nBilling question: can we add 5 seats mid-cycle?"
    }
  ],
  "options": { "request_next_action": true }
}

If unsure which input_type your deployment expects, run a test in the dashboard Test evaluation panel and check the playbook docs, or use transcript with the full message body.

Branching

status Typical handling
ESCALATE P0/P1 or enterprise tier found — urgent path
QUALIFIED All required fields present — normal queue
PARTIAL Some fields found — request missing metadata
FAILED No required fields — request priority/tier/urgency

Connect your helpdesk

Channel Pattern
Webhook Helpdesk → n8n/Zapier → Evaluate → update ticket priority
Email forwarding Inbound parser → HTTP POST with input_type: "email"
API poll Scheduled job → fetch new tickets → evaluate batch

See n8n integration or Zapier & Make for HTTP wiring.

Verify

  1. Dashboard → deployment → Test evaluation with input_type ticket or email.
  2. Confirm status and next_action match expectations for urgent vs routine samples.
  3. Wire automation only after logs look correct in Recent evaluations.

Troubleshooting

Issue Fix
Wrong severity Prepend Severity: Pn and Tier: … from CRM; do not rely on narrative alone.
Slow responses Keep ticket body concise; evaluation is synchronous.
input_type rejected Match playbook manifest; try transcript as fallback.

Related