Custom instructions for feedback auto-replies
Tune automatic feedback acknowledgements with product context, tone rules, and canned answers so the first response buys trust instead of sounding generic.
Why this can grow a startup
Auto-replies often fail because they are technically prompt but emotionally vacant. Canny's Smart Replies update matters because teams can set their own instructions, give the system approved context, and preview the response before turning it on. That means the first answer can explain what the team already knows, avoid tone-deaf replies to frustrated users, and stop asking questions that the product or help center already answers. A cleaner first response keeps the request thread alive long enough for the real follow-up to matter.
Company example
Canny lets admins add custom instructions for Smart Replies, replacing the default behavior so replies can follow the team's own tone, canned answers, and contextual guidance.
Source and metric
Source: Canny Changelog · Browse Canny Changelog tactics
Admins can test generated responses before enabling custom Smart Replies, and the system now skips replies when the knowledge hub confirms the feature already exists.
Source discovered: May 29, 2026
When to use it
Use this when Email, Support, Product is relevant to support ux, close-the-loop, ai ops and you can run a bounded test with a low budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read Canny Changelog and identify what is directly supported.
- Choose one channel context: Email, Support, Product.
- Define the test around Admins can test generated responses before enabling custom Smart Replies, and the system now skips replies when the knowledge hub confirms the feature already exists..
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Connect activation, customer value, retention, and referral into one measurable loop.