how to train an AI agent's tone of voice.
heysteff is an AI platform for customer support and sales across WhatsApp, Instagram, Messenger, Gmail and Shopify; Steff is the AI agent that runs it. This guide is for whoever manages the agent and wants it to sound like the brand — not generic, not robotic — before it ever talks to a real customer.
◆ prerequisites
Admin access to your heysteff workspace, brand material on hand (FAQs, policies, style guides if you have them), and, if you want to use real history, past conversations between your human team and customers.
Step 1: Upload brand material
Start by loading the material that defines how your business talks: FAQs, exchange and return policies, style guides if you have them, and any document your human team already uses to answer. This goes into the agent's trainable knowledge base, so replies lean on real information about your business instead of generalities that could belong to any brand. The richer this base, the less the agent has to improvise.
Step 2: Adjust the formality, humor, proactivity and length sliders
With the material loaded, tune the agent's personality controls: how formal or warm it is, how much humor it allows, how proactive it is about next steps (suggesting a product, proposing a booking), and how long its replies run. There's no single correct combination — it depends on how your brand talks today, and the starting point is to try and adjust, not to guess it all at once.
Step 3: Mark "gold-standard" replies from history
If your human team already handled these channels, go through the conversation history and flag the replies you consider a good example of how the agent should sound — the exact tone, the level of detail, the way a sale gets closed or a complaint gets calmed. These "gold" replies give the agent concrete examples of your brand talking, which carry more weight than an abstract description of personality.
Step 4: Set hard rules the agent never breaks
Beyond tone, define explicit limits: things the agent must never say or promise, such as exact delivery dates you can't guarantee, unauthorized discounts, or medical or legal claims out of place for your category. These hard rules are different from tone — tone is how it sounds, rules are what it won't negotiate, no matter how much the customer pushes.
Step 5: Iterate in the test playground
Before the agent talks to real customers, test it in the internal "test the bot" playground by simulating your typical conversations: a catalog question, a complaint, a return-policy query. Fix what doesn't sound right, test again, and repeat. Tone training isn't a one-off step — it's worth revisiting periodically as you see real conversations land in the inbox.
Tone isn't static
Once the agent is live, the tone work continues: review real conversations in the inbox, mark new gold-standard replies when the human team nails something, and adjust hard rules if a case you hadn't anticipated shows up. A brand's tone also shifts over time — a campaign, a season, a repositioning — and the agent should be able to keep up without being retrained from scratch every time. Treat tone the way you'd treat a style guide for your human team: a living document that gets tighter every time you spot a reply that could have sounded more like you.
FAQ
How long until the agent sounds right?
It varies by business. With complete brand material and a couple of rounds in the playground, most workspaces reach an acceptable tone before going live, then keep refining it with real conversations.
Can hard rules be bypassed if the customer insists?
No. Hard rules exist precisely for that — the agent doesn't break them even under pressure, and instead can escalate to a human when appropriate.
Do I need to code anything to train the tone?
No. It's all configuration from the panel: sliders, knowledge base and text rules. No code required.
◆ next step
Train Steff with your brand's tone before it talks to your customers.