Skip to main content
The fastest support team isn’t the one with the most agents — it’s the one whose agents don’t start replies from a blank page. A response Agent drafts the first reply for every ticket, pulling the right KB articles, the right account context, the right tone. The agent edits, sends, and moves on.

​
When this pays off

Repetitive tickets eat hours

The same 20 question types make up 70% of inbound. Agents type the same answer with slight variation, all day.

KB underused

You’ve got a knowledge base but tickets get answered from agent memory — and the KB grows stale.

Tone drift across agents

Tone varies wildly between new hires and tenured agents — customer experience is uneven.

Onboarding takes too long

New agents take weeks to become productive because there’s no fast path to “right answer + right voice”.

​
The shape of this use case

A response Agent takes a ticket and returns a drafted reply with citations.

Inputs

Ticket body, customer record, prior tickets, channel-specific format hints.

Sources

Knowledge base, prior resolutions, tone-of-voice guide, product status / changelog, account history.

Output

A drafted reply with cited KB articles and a confidence indicator — ready for agent review and send.

Delivery

Inserted as a draft in Zendesk / Intercom for agent review, posted in a comment for visibility, attached as a macro suggestion.

​
Where to start

Two ways in, depending on whether you want something running today or built to your exact spec.

Clone a pre-built Agent

Open the Customer Query Handler. More in the Marketplace.

Build your own

Start from scratch in the builder, or by describing it in Claude Code or Cursor with Programmatic GTM.
Either way, these are prompts your team can use on day one:
  • “Draft a reply to this ticket — the customer can’t activate their account and we’ve seen this before with their email domain.”
  • “What’s our standard response when someone asks about the new billing cycle? Cite the KB articles.”
  • “Customer is asking for a refund — what’s the playbook and what should I check first?”

​
Where to take it

Once it’s running, deepen it in three moves:

Give it a playbook

Shape it with a prompt, your KB in Knowledge, and Tools for KB and CRM search.

Automate it on signals

Wrap it in a workflow that fires on a trigger.

Let it improve

Feed back which drafts shipped untouched, plus CSAT, into the Agent’s evals so it matches what your team sends.

​
Common pitfalls

If agents are rewriting every draft, the Agent isn’t actually saving time — it’s adding a step. Watch the edit-rate; rebuild the prompt or Knowledge if it climbs.
The Agent cites articles that don’t exist or fabricates policy. Force citations to KB IDs from your actual catalog and fail visibly when there’s no match.
Without a strong tone-of-voice doc, every draft sounds like the same chatbot. Upload your best past replies as examples in Knowledge.
Auto-sending replies before you’ve watched the Agent on real tickets for a month is how you ship a bad answer at scale. Start with drafts only.