Skip to main content
Level 3 — Lesson 4 of 5 — Write agent copy that sounds human, not generated.
Copywriting separates an agent that works from one that feels right. This covers brevity, tone, sentence structure, and techniques for natural-sounding speech.

​
Keep it brief

In general, concise responses are clearer, more respectful of the user’s time, and avoid sounding like an advert.
“If you want, I can also sign you up for our rewards program so you can get a free appetizer with your next meal — would you like me to do that?”
Brief, clear, one question.

​
When longer is better

The exception: when the user asks for an explanation. Being more thorough gives them time to process the information. If a user says “Can you explain what the CARE program is?”, be detailed:
“California Alternate Rates for Energy, also known as CARE, is a discount program for lower-income California residents to help with monthly energy costs. You can get a discount of 20% or more on your electric bill if you meet the income requirements or are enrolled in certain public assistance programs. Do you want me to send you a text with more info about CARE and how to apply?”

​
Tone and formality

LLMs default to verbose, overly formal phrasing. Correct this consistently:
AvoidPrefer
”Could you please provide me with your account number?""Could you tell me your account number?"
"How may I assist you today?""How can I help?"
"I apologize for the inconvenience.""Sorry about that."
"Should I proceed with making that booking?""Should I go ahead with that?”
Also use:
  • Contractions — “I’ll”, “we’re”, “that’s”
  • Informal word forms — “alrighty”, “gotcha”
  • Fragments — “Sound good?” instead of “Does that sound good to you?”

​
Avoiding repetitive structure

LLMs overuse this pattern: [explanatory statement] [request that references the explanation]
“In order to check for outages, I’ll need to look up your account. Could you tell me your account number?”
Then on the next turn:
“Okay, I’ve found your account. To verify your identity, I’ll need your birth date. Could you please provide me with that?”
The explanatory statement is usually unnecessary — the user can infer why from context. Combine into a single natural question:
Verbose patternBetter
”In order to check for outages, I’ll need to look up your account. Could you tell me your account number?""No problem, what’s your account number?"
"To verify your identity, I’ll need your birth date. Could you please provide me with that?""Great, and just to verify I have the right account, could you tell me your date of birth?”
Notice that both alternatives also vary from each other — different openings, different structures.

​
Making speech sound human

These techniques make agent speech feel like a real conversation rather than a script. Use them in pre-scripted copy and as examples in style guides.
Some of these techniques are dialect-specific and may not work in all contexts. They are examples and inspiration, not universal rules.

​
Use “I’m looking” instead of “I don’t see”

Saying “I’m not seeing any accounts…” (present progressive) sounds like you’re actively helping. Saying “I don’t see any accounts…” (simple present) sounds final and definitive — it shuts the door.
Less naturalMore natural
”I don’t see any accounts under that phone number.""I’m not seeing any accounts under that phone number…”

​
Reference shared context without restating it

In conversation, people reference what they’ve already discussed implicitly. LLMs tend to repeat the context explicitly:
Over-explicitNatural
”Since you said you prefer weekends, how does Saturday at 2:30 sound?""In that case, how does Saturday at 2:30 sound?"
"How about Wednesday instead of Tuesday?""How about Wednesday instead?”

​
Vary your acknowledgements

Acknowledgements like “Great”, “Okay”, “Perfect” create a sense of flow. But LLMs tend to repeat the same one:
RepetitiveVaried
”Great, … ” “Great, …” “Great, …""Great, …” “Okay, …” “Perfect, …”

​
Use “for me” to sound invested

Adding “for me” to a request makes it feel like the agent is personally involved, not just following a script:
StandardMore personal
”Could you read your account number aloud?""Could you read me your account number?"
"Can you log into your account?""Can you log into your account for me?”

​
Soften references to what the user wants

When referencing the user’s request, past tense sounds more polite than present tense:
DirectSofter
”When are you trying to come in?""When were you trying to come in?” / “When did you want to come in?”

​
Don’t push the conversation forward on every turn

LLMs are biased toward ending every turn with a question. This gets repetitive and unnatural.

​
Step-by-step walkthroughs

Don’t ask for confirmation after every step. In real conversations, the guide gives an instruction and waits — the user will naturally confirm or ask a follow-up.
Agent: “First, scroll down and click ‘Account settings’. Let me know when you’ve done that.” User: “I’ve done that.” Agent: “Then click ‘Contact Details’. Let me know when you’re ready for the next step.” User: “Okay.” Agent: “Great. Then select the address you want to edit. Let me know when you’ve done that.”

​
Don’t immediately ask “anything else?”

After answering a question, don’t immediately ask if there’s anything else. Give the user space to acknowledge or follow up:
Agent: “Yes, we have large vehicle parking on Meridian Street during weekdays. Is there anything else I can help you with?”

​
Try it yourself

1

Challenge: Rewrite these agent responses

Rewrite each response to be more natural:
  1. “Could you please provide me with the phone number associated with your account so that I can look up your information?”
  2. “I apologize for the inconvenience. Let me check on that for you. Could you please hold for a moment?”
  3. “Thank you for providing that information. To verify your identity, I will need your date of birth. Could you please provide me with that?”
  1. “What’s the phone number on your account?”
  2. “Sorry about that — let me take a quick look.”
  3. “Great, and just to check I’ve got the right account, what’s your date of birth?”
Last modified on March 26, 2026