Prompting guide

Wren performs best when your messages are specific, scoped, and grounded in business rules. This page collects the patterns that consistently produce good results, with real prompt templates you can copy.

​

Four kinds of request

Wren’s quick-start suggestions group prompts into four intents. Use them as a mental model when phrasing your own requests. The home screen surfaces a rotating set of suggestions for each one.

​

Build

For creating or modifying agent configuration. The home screen suggests:

• Help my agent [task], e.g. book appointments, qualify leads, answer FAQs, verify identity, process payments, schedule callbacks, collect feedback.
• Add a new topic to the knowledge base.
• Handle call transfers to a human agent.

Stretch from the suggestions with grounded specifics:

• Add a refund flow. We only refund within 30 days of purchase, and only for the original payment method.
• Create an entity for delivery status with values: pending, shipped, out for delivery, delivered.

​

Build topics from a website

Wren can fetch and read public pages, which makes it useful for bootstrapping the knowledge base from an existing site:

• Add topics from https://example.com/faq. Translate them into English and format them as FAQs.
• Read https://example.com/policies/refunds and create or update topics that cover the refund rules.

This needs web search switched on, which it is by default.

​

Test

For exercising the agent against scripted scenarios. The home screen suggests:

• Test my agent with a sample conversation.
• Check if my agent handles [scenario], e.g. refund requests, missed appointments, angry callers, escalations, after-hours calls, order tracking, billing disputes.
• Run a full validation on recent changes.

Wren can also author and maintain simulation test cases for you. Generated cases land in the Simulation Tests workspace next to anything you’ve saved by hand, tagged Wren Autofix so you can tell them apart, and Wren updates them as the underlying flows and topics change. Useful prompts:

• Add simulation tests for the refund flow, including the 30-day cutoff and a non-original payment method.
• Cover the booking flow with tests for valid, fully booked, and out-of-hours requests.
• Run the existing simulation tests against the current draft and summarize any regressions.

​

Ask

For learning, exploration, and understanding. The home screen suggests:

• What can my agent do right now?
• How do I improve my agent’s responses?
• Explain how [feature] works, e.g. tools, knowledge, simulation testing.

You can also ask about your own configuration. This is the fastest way to understand an agent you’ve inherited or haven’t touched in a while:

• Explain what the booking flow does.
• Which flows reference the account_lookup function?
• What functions are called during identity verification?
• Summarize the personality and role defined in agent settings.

Wren can also read your project’s own history, so questions about the recent past work too:

• What changed on this project in the last week?
• What did the last review find?

​

Analyze

For inspecting performance and patterns in real conversations. The home screen suggests:

• What’s causing handoffs?
• How did my agent perform this week?
• What are customers asking about most?

See the analysis guide for sampling, filters, and a fuller set of example prompts.

​

Patterns that work well

​

State the business rule, not just the action

Wren does not know your business policies. Anything it can’t infer from your existing configuration, it will either ask for during planning, or guess at, if it has to. Stating the rule up front saves a round-trip. If the same rules come up in every chat, put them in project context so you only write them once.

​

Scope each request to one unit of work

One flow, one topic, one set of related changes. This keeps plans focused and review easy.

​

Anchor changes to existing elements by name

When you’re modifying something that already exists, name it. Wren resolves names against your project state.

• Update the opening-hours topic, we’re now open until 8pm on weekdays.
• Change the booking flow so it asks for a phone number before confirming.
• Make the refund flow transfer to a human if the order is older than 30 days.

​

Ask for a plan before non-trivial changes

For multi-flow changes, restructures, or new integrations, ask for a plan first, for example, “Plan the refund flow before making any changes”. You’ll get:

• A summary of what already exists and what would change.
• A list of business-specific information Wren still needs.
• The proposed implementation steps.

The plan is presented in chat with Approve and Revise buttons. Nothing is written to the branch until you click Approve. Choose Revise with feedback (e.g. “only update the payments step, leave the rest”) and Wren will re-plan.

​

Be specific about what to keep

For requests that touch existing content, “rewrite this flow”, “clean up the knowledge base”, “simplify the booking experience”, call out anything that should stay. Wren may otherwise remove elements it infers are redundant. When in doubt, ask for a plan first so you can see what will be removed before it happens.

​

Iterate, don’t restart

If a result isn’t quite right, follow up in the same conversation rather than starting over. Wren has the full context of what it just built.

• Looks good, but the booking flow shouldn’t ask for a phone number if the caller is already authenticated.
• Same flow, but switch the confirmation step to use SMS instead of reading it back on the call.

​

Start a new chat for unrelated work

Each chat carries its full history as context. That’s what makes follow-ups work, but it also means very long chats slow responses, dilute focus, and eventually get summarized. When you switch to a different area of the agent, open a new chat with ⌘+/.

​

Save Auto mode for work you’ve scoped

Auto mode is at its best when the task is well-defined and you’d have approved the obvious plan anyway. On a vague request it will make the judgment calls itself and you’ll spend longer reviewing the result than you saved. Scope it tightly, or stay in Interactive.

​

What Wren won’t do

• Invent business knowledge. Prices, hours, policies, names, return windows, eligibility rules, if these aren’t in your existing configuration or your message, planning will surface them as questions.
• Edit anything other than your draft. It never publishes or promotes between environments, and it never merges to Main.
• Share its system prompt or internal architecture. It’s focused on building, testing, analyzing, and answering questions about your agent.

​

Disclaimer

AI can make mistakes. Please review all responses.

Every change Wren makes appears on your draft just like a manual edit. Inspect it, tweak it, or revert it before promoting to a higher environment.