Publishing an AI agent

Publishing puts it in front of customers. What to do in the first week decides whether it stays there.

Publishing puts it in front of customers. What to do in the first week decides whether it stays there.

Publish it

1. Confirm the handover works and goes somewhere staffed.
2. Check which channels and brands it covers.
3. Publish.
4. Tell your agents it is live and what it handles.
5. Read transcripts the same day.

Start where the risk is lowest

One channel, ideally messaging, during hours when people are around to pick up handovers. A launch on every channel at once removes your ability to tell what is working.

Tell the team first

Agents will receive conversations that started with the AI. They should know that is expected, that the transcript comes with it, and where to report a bad answer.

An agent who thinks the AI is broken will tell customers so.

Read transcripts on day one

Not the dashboard. Twenty actual conversations, in full. Every deployment produces surprises in the first fifty exchanges, and they are the cheapest ones you will ever fix.

Fix articles, not the agent

Most bad answers trace to content: a missing article, or one that does not state the answer plainly. Changing the article fixes the AI agent and helps every reader.

Widen slowly

Add subjects and channels when the transcripts on the current ones are consistently good. Each addition is a new set of failure modes, and adding them one at a time is how you keep knowing which change did what.

See also

• Testing an AI agent before you publish it
• Reviewing conversation transcripts
• My AI agent solves very little: where to start