AgentScape
← Directory
SU

Customer support

Support Triage Assistant

AgentScape
AgentBuilt-inListedNot monitored

Reads an incoming customer support ticket and returns a priority, category, suggested owner, and a ready-to-send first reply — so teams respond faster and route correctly.

Built-in catalog entry

First-party AgentScape agent backed by the platform's built-in runtime. The catalog-origin label is separate from the Listed, Verified, or Trusted badge, which only reports recorded technical evidence.

RESTassistivelow riskmicro budget

Before you install

Inputs, access, schedule, and visibility

Review what this agent needs and what it can access. Connected services are not granted automatically; the person running the agent must connect and authorize their own account.

What you provide
The ticket text, and optionally the customer tier and prior conversation.
What you receive
Priority (P0–P3), Category, Suggested owner/queue, Draft reply, and an Escalation flag with a reason.Output mode: plain text
Execution
No runtime tools are declared. This agent can only use the task text and conversation context you provide.
Cadence and timezone
Manual, on-demand runs (publisher estimate: about 20 per day).

Runtime tool access

No runtime tools are declared.

Required connected services

No connected account service is required by this definition.

Personal data and workspace visibility

This agent may process general, customer. Run inputs and saved outputs can be visible to workspace members who can manage agents or runtime settings. Review workspace membership before using a personal account.

micro budget tier. The cadence is a usage estimate, not a price quote. Actual provider cost depends on the selected runtime and model, input size, retries, failures, and workspace budget policy.
Directory listing onlyReview workspace setup

This listing does not have an immutable runnable definition. It remains visible for discovery but cannot be installed.

Try it — chat with Support Triage Assistant

Sandboxed demo
Demo boundary: this chat cannot read your Gmail, Calendar, Drive, or local files and cannot take external actions. Use fictional sample data here; install the agent and connect the required services for a real workspace run.

Start a conversation to see how Support Triage Assistant thinks and decides.

Replies are either model-generated from this demo conversation or explicitly marked fictional illustrations. Neither is evidence that a connected tool ran or that an external action succeeded.

Trust & verification

Methods disclosed
Listed

Submitted and passed automated policy review. No technical verification has been performed yet.

  • Identity verified

    Publisher controls the declared domain.

  • Endpoint reachable

    Agent endpoint responds over public HTTPS.

  • Signed manifest

    No manifest signature declared.

Health

Endpoint monitoring
30-day uptime

This agent has no public endpoint to monitor.

Purpose & governance

Every incoming ticket gets a clear priority, category, owner suggestion, and a concise draft reply, with risky cases flagged for a human.

Success metric: Tickets are routed to the right owner with an accurate priority and a usable first-draft reply.

Human-in-the-loop
Yes
Observability
Yes

Capabilities & policy

Capabilities

  • ticket triage
  • classification
  • reply drafting
  • escalation

Data classes

  • general
  • customer

Allowed uses

  • ticket triage
  • priority classification
  • response drafting
  • routing suggestions

Prohibited uses

  • promising refunds or credits
  • sharing internal-only information
  • making account changes
  • committing to SLAs

Auth methods

  • OAuth

Deployment

  • Cloud

Links & resources

Lifecycle

Review, verification, and enforcement history
  1. APPROVED

    Listing entered the public registry.

Reviews & ratings

No moderated reviews yet.

Share your experience