# Tone and fallbacks

> How to write a persona that sounds like your brand and refuses cleanly when the agent doesn't know.

import Screenshot from "../../../components/docs/Screenshot.astro";

Most "the agent is acting weird" reports trace back to the **Instructions** — the system prompt on the agent's **Model** tab in the Playground. Two or three sentences is plenty; long instructions don't make the agent smarter, they just dilute the signal.

## Personality and tone

Be concrete. "Be friendly" is weak; "Be warm and concise — short paragraphs, no exclamation points unless the user uses one first" gives the model something to anchor on. Reference your brand voice the way you'd describe it to a new hire: how formal, how playful, what to never say.

<Screenshot src="/screenshots/playground-model-tab.webp" alt="Playground Model tab with model selector, temperature slider, instructions editor, and widget preview." label="Console · Playground · Model tab" description="The Model tab showing model picker, temperature slider, and Instructions textarea with character counter." />

## Handling unknown questions

The biggest source of hallucinations is an agent that wasn't told it's allowed to say "I don't know." Add a line like:

> If the answer isn't in your knowledge base, say so plainly and offer to connect the visitor to a human. Do not guess.

That single sentence does more than any retrieval tuning. Pair it with [human handoff](/docs/helpdesk/human-handoff) (enabled on the agent's **Skills** page) so refusals turn into productive handoffs rather than dead-ends.

## Refusal patterns

Some questions you want refused even when the agent could technically answer (competitive pricing, internal-only info accidentally crawled). Be explicit in Instructions:

> Never discuss competitor pricing. If asked, redirect to our pricing page.

The agent will follow these rules consistently as long as they're written like rules, not preferences. Adjust the **Temperature** slider on the Model tab toward the lower end (0.2–0.5) to make these refusals more deterministic.

## Next steps

- **[Playground](/docs/agents/playground)** — the right place to test persona changes.
- **[Citations & re-training](/docs/knowledge-base/citations)** — sometimes "the agent is wrong" is a knowledge-base issue, not a persona issue.

---

Source: https://owlish.bot/docs/agents/tone-and-fallbacks