Intermediate About 150 minutes 5 stages

Create a customer FAQ assistant

Plan a bounded FAQ assistant that answers from approved material and escalates uncertain requests.

Create a customer FAQ assistant

What you will produce

A reviewable result, not an automatic answer.

Follow the stages in order. Each stage ends with a tangible deliverable and a review checkpoint, so mistakes are caught before they become the next tool’s input.

Expected tool cost

Use free plans where suitable; confirm current provider limits and prices before starting. Compare the latest verified AI pricing before buying another subscription.

Suggested stack

Tools used in this workflow.

The process matters more than the brand. Use an approved equivalent when it offers the controls and output quality your organisation needs.

Inputs and ownership

Before you start

  • Approved policies and customer-service answers
  • An escalation owner and privacy policy
  • Access to representative support questions and failure examples

Interactive workflow

Complete each stage in order.

Tick a stage only after its deliverable and review checkpoint are complete.

  1. Define allowed questions, prohibited topics and conditions requiring immediate escalation.

    Deliverable

    A scope and escalation matrix

    Review checkpoint

    Never let the assistant invent policy.

  2. Create a maintained source set with owners, effective dates and expiry rules.

    Deliverable

    An owned knowledge set

    Review checkpoint

    Confirm access permissions for every source.

  3. Design answers that cite the source and expose uncertainty rather than improvising.

    Deliverable

    A response and citation standard

    Review checkpoint

    Test prompt injection and requests for personal data.

  4. Test expected, ambiguous, adversarial, outdated and sensitive questions.

    Deliverable

    A red-team test report

    Review checkpoint

    Measure safe resolution and escalation quality, not deflection alone.

  5. Pilot with a limited audience, human hand-off, logging and a rollback plan.

    Deliverable

    A monitored pilot plan

    Review checkpoint

    Pause the assistant when sources become unreliable.

Adapt, do not paste blindly

Working prompts for this recipe.

Replace bracketed placeholders, supply approved sources and remove unnecessary personal or confidential information.

Working prompt

Use this only after replacing every bracketed placeholder and removing unnecessary sensitive information.

Using only the approved FAQ sources below, draft an answer to [CUSTOMER QUESTION]. Cite the source section used. If the answer is missing, outdated, ambiguous or sensitive, do not guess; state that a team member needs to help and provide the approved escalation route.\n\nAPPROVED SOURCES:\n[PASTE OR LINK SOURCES]

Final review prompt

Use as a second-pass checklist, not as approval to publish.

Review the draft against this intended outcome: Plan a bounded FAQ assistant that answers from approved material and escalates uncertain requests. List unsupported claims, missing evidence, ambiguous language, privacy concerns, accessibility issues and actions that still require human approval. Do not rewrite the draft until the issues are listed separately.

Human review required

Verification and cautions

  • Verify names, figures, quotations and source claims before use.
  • Remove confidential or personal information unless the selected service and account are approved for it.
  • Keep a named person responsible for the final decision and published output.

Keep the outcome, change the method

Practical alternatives

Improve searchable human-authored FAQs before introducing an assistant.
Use rules-based routing for high-risk or highly regulated enquiries.