Analyze historical data — Run your question against tickets that have already been resolved, not just new ones going forward.

Surface trends — Identify patterns in customer sentiment, agent behavior, or process compliance across large volumes of tickets.

Power dashboard widgets — Use backfillable questions as data sources in your Dynamic Dashboards for reporting and visualization.

QQ Backfills feature is enabled for your account — Ask your Qvasa account manager to enable the QQ Backfills feature on your account. This is a one-time setup step.

Your user account has an Admin or Owner role — Only admins and owners can create and manage backfillable questions.

Your user has the QQ Backfills permission — Have your account admin enable the "QQ Backfills" permission for your user profile.

Your user account is activated — Your account must be in an active state.

Decide what you want to measure. Are you measuring customer sentiment, agent adherence to a script, whether a specific topic was discussed, or something else?

Choose the right question type. If you need a nuanced scale (positive / neutral / negative), use a Basic Score Question. If you need a simple yes/no determination, use a Two-Choice Question.

Draft your response options in advance. Option values become permanently locked once you enable the question for backfill, so plan them carefully before you begin.

Create Basic Score Question (Backfillable)

Create Two-Choice Question (Backfillable)

"Was the customer satisfied with the resolution?"

"How well did the agent handle the customer's complaint?"

"What was the overall tone of the customer during the conversation?"

"Did the agent offer a discount or credit?"

"Was a product return initiated during this conversation?"

"Did the customer mention a competitor by name?"

This is the display name that appears in dashboards and reports.

Maximum 40 characters.

Must be unique within your account — no two questions can share the same name.

Choose something descriptive and concise (e.g., "Customer Satisfaction", "Discount Offered", "Escalation Needed").

This is the prompt that the AI will use to evaluate each ticket conversation.

Be specific and unambiguous. The clearer your question, the more accurate the AI's responses will be.

Good example: "Based on the conversation, was the customer satisfied with the resolution provided by the agent? Consider the customer's final messages and any explicit feedback."

Weak example: "Was the customer happy?"

Use this field to provide extra guidance to the AI.

This is helpful for domain-specific terminology, edge cases, or clarifying what should be considered.

Example: "Consider only the customer's messages, not the agent's. If the customer did not explicitly express satisfaction or dissatisfaction, classify as Neutral."

Positive (Green, Score 3)

Neutral (Blue, Score 2)

Negative (Red, Score 1)

Unknown (Gray, Score 0)

Primary Option (Green)

Fallback Option (Gray)

All option values are required.

Option values must be unique within the question.

Option values must be unique across your entire account.

Option values must contain only lowercase letters, numbers, and underscores.

Basic Score questions must have exactly 4 options.

Two-Choice questions must have exactly 2 options, and they must be different.

Edit the question name, AI prompt, and additional context in the Configuration section.

Edit option values (only while the question has not been enabled for backfill).

Edit option descriptions at any time.

Add context to individual options to improve AI accuracy.

"Options are editable" (blue) — You can still change option values.

"Options are locked" (yellow) — The question has been enabled for backfill and option values can no longer be changed.

Clarity and specificity — Is the question clear enough for consistent AI interpretation?

Mutual exclusivity — Are the options distinct enough that only one should apply per ticket?

Coverage — Do the options cover all likely scenarios?

Description quality — Are the option descriptions helpful and practical?

The review typically takes a few seconds to a couple of minutes.

The page will show real-time progress updates.

Good — Your question is well-structured and ready to go.

Needs Improvement — The AI identified areas to refine. Review the suggestions and consider updating your question, descriptions, or option definitions.

Problematic — Significant issues were found. You should address the feedback before proceeding.

The question becomes available as a selection in dashboard widgets that support QQ backfills.

The question source changes to "Backfillable Custom" in the system.

Option values are permanently locked. You can still edit descriptions, the AI prompt, and additional context, but the option value identifiers cannot be changed.

A success message confirming the backfill was initiated.

A backfill ID for tracking.

Your queue position — backfills are processed one at a time per account in a first-in, first-out (FIFO) order. If another backfill is already running, yours will be queued.

The current status of the backfill.

Cancel — Available for backfills that are Queued or Processing. Cancelling a backfill stops future processing, but any tickets already analyzed will retain their results.

Delete — Available for backfills that are Completed, Errored, or Cancelled. Removes the backfill record from the list.

Be explicit about what to look for. Instead of "Was the customer happy?", try "Based on the customer's messages, did the customer express satisfaction with the resolution? Consider explicit statements of thanks, confirmation that the issue was resolved, or positive sentiment in the final messages."

Define the scope. Specify whether the AI should consider only customer messages, only agent messages, or the entire conversation.

Handle edge cases. Tell the AI what to do when the answer is ambiguous. For example: "If the conversation was cut short or the customer did not respond to the resolution, classify as Unknown."

Each option should represent a clearly distinct outcome. There should be minimal overlap.

Include a fallback option (like "Unknown" or "Not Applicable") for cases that do not fit the other categories.

Bad example: Options satisfied and very_satisfied — too similar, the AI may not distinguish consistently.

Good example: Options satisfied, neutral, dissatisfied, unknown — each covers a distinct range.

The descriptions help the AI understand when to select each option. Treat them as instructions.

Include examples of what each option looks like in a real conversation.

Example description for "negative": "The customer expressed frustration, anger, or dissatisfaction. This includes complaints about wait time, unresolved issues, or requests to speak with a supervisor."

Option values appear in reports and data exports, so make them readable.

Use descriptive, lowercase terms with underscores: agent_offered_discount, no_discount_offered, customer_satisfied.

Avoid generic values like option_1, option_2 — these will be confusing in reports.

Vague questions — "How was the interaction?" is too open-ended. Be specific about what dimension you are measuring.

Overlapping options — If two options could reasonably apply to the same conversation, the AI will be inconsistent.

Missing fallback option — Always include an option for when the answer is unclear or the data is insufficient.

Overly long option values — Keep them concise but descriptive. Remember the 60-character limit.

Forgetting that option values are account-wide unique — If you have another question using the value positive, you cannot reuse that value in a new question. Consider prefixing: csat_positive, quality_positive.

The question display name

The AI prompt (question for the AI)

Additional context

Option descriptions

Option values (permanently locked)