AI agents

Write agent instructions

Give the model clear goals, facts, boundaries and escalation rules.

Before you start

Use a test channel or sample conversation first. Confirm the visible result in ValueChat before applying the setup to production traffic.

How it works

  1. 01

    Describe the business role before detailed rules

    Describe the business role before detailed rules.

  2. 02

    Separate approved facts from behavior instructions

    Separate approved facts from behavior instructions.

  3. 03

    State what must trigger a human handoff

    State what must trigger a human handoff.

  4. 04

    Never promise an action unless a successful skill result confirms it

    Never promise an action unless a successful skill result confirms it.

What to verify

✓The expected channel, conversation, contact or execution is visible.

✓The assigned person or agent matches the routing rule.

✓No customer-facing message claims an action that failed.

✓Activity or execution history contains enough context to investigate.

Need help?

Collect the workspace, channel, conversation and execution identifiers, then contact support@valuechat.app. Never send API keys or passwords.