Getting quality responses to complex customer questions | Community
Skip to main content

Getting quality responses to complex customer questions

  • December 16, 2025
  • 1 reply
  • 141 views
K

Hi folks, I am a product manager on a no-code app building product for manufacturers. We allow process engineers to build apps and deploy them onto a manufacturing shop floor.

Since app building is a creative process, and requires understanding of UI, logic and our no-code database, our customer questions tend to be complex- they are not easily answered by single knowledge base articles, and the possibilities for using our features are essentially endless.

Has anyone come up with prompts that help Fin answer these types of questions?

As an example, I have gotten pretty good results from adding this prompt to the “Other” category under guidance. It took a lot of trial and error.

title: Assume complex answers required

body: If a customer asks a question that spans multiple features in our product, investigate each feature individually before returning a response. Your answers should comment on the review of each individual feature's capabilities. This helps users understand which specific part of the product you are discussing.

      1 reply

      Nico Magbiray
      Innovator ✨
      Forum|alt.badge.img+4
      • Nico Magbiray
      • Innovator ✨
      • February 4, 2026

      Hi Kevin,

      I totally get the challenge. When features are "endless," a single article usually isn't enough. Instead of trying to make Fin answer everything immediately, try a Hybrid Triage Strategy.

      1. Probe with Structured Data Collection Don't let Fin guess. Use the workflow to ask probing questions via reply buttons or data collection blocks before Fin even starts talking.

      Example: "Which part of the app building process are you in? (UI Design / Database / Logic)".

      By collecting these attributes first, you simplify the "context" for both Fin and your human team.

      2. The Human-AI Handover For now, let Fin handle the initial data gathering and basic "How-to" questions. If the question remains complex, use a Handover path to pass the gathered data to a human agent. This saves your team from asking the "basics" and lets them jump straight into the complex problem.

      3. Train for Full Automation (The Flywheel) If you want full automation eventually, use the Analyze stage of the Fin Flywheel.

      Review the complex answers your human agents give.

      Turn those high-quality human responses into specific Snippets.

      Deploy and Test them in Fin's guidance using the logic your agents used.

      Pro-Tip for Guidance: Use the Optimize button to ensure your new complex instructions don't overlap with your general shop info. Keep your guidance specific, concise, and simple.

      Hope that helped!

      Terms & ConditionsAccessibility statement