USE-CASES

Customer feedback tagging that your team can explain

Classify feedback by the product question you need to answer. Start with one main theme per message, then review mixed or uncertain feedback separately.

JEV / DECISION LABYOUR RULES. YOUR LABELS.
Remove passwords, payment details, and unnecessary personal information. 85%
OUTPUT / JSON

Your decision

Run a decision or open the labeled sample to see the result here.

A high score is not a guarantee. Keep a person in control of consequential actions.

View API example →
A customer message enters your label rules, becomes a typed category, and reaches a queue with a review path.
A customer message enters your label rules, becomes a typed category, and reaches a queue with a review path.

Try a concrete feedback rule

For “The CSV export works well, but I need a date filter,” decide whether you need the feedback type or the product area. Type labels could be feature request, bug report, praise and other. Product-area labels could be reporting, integrations, pricing and other. These are separate questions; mixing them into one list makes the result hard to compare.

The playground link loads a feedback-type example. To measure product themes, replace its labels with your product-area taxonomy and update the instruction. Keep the same rule throughout a batch so exported rows remain comparable. The example below is an input, not an observed model result.

{
  "text": "The CSV export works well, but I need a date filter.",
  "instructions": "Choose the product area affected by the requested change. Use other when no listed area fits.",
  "labels": [
    "reporting",
    "integrations",
    "pricing",
    "other"
  ],
  "threshold": 0.9
}

Handle mixed feedback and report the denominator

A message can praise one feature and report a bug in another. For a single primary tag, define which need takes priority; for independent themes, use separate typed questions. Send ambiguous rows to review instead of forcing them into the most popular label.

When reporting “30% mention reporting,” state the time window, number of distinct records and how duplicates and mixed comments were counted. Tag frequency is evidence about your sample, not a promise of revenue. Pair it with conversations about the specific problem before changing the roadmap.

Typed questions · Evaluate labels

Build a useful taxonomy

Choose themes that help a decision: onboarding, reliability, integrations, pricing, reporting, and other. Keep a short definition for each tag. A broad taxonomy is easier to label consistently than dozens of overlapping feature names.

Try tagging feedback in the playground

Keep the original context in your own system

Jev API Pro does not retain the submitted message in decision history. Keep the original feedback and its source in your own customer system if you need to investigate a result. The exported classification should be linked using your own row identifier.

Request contract

Separate frequency from importance

A frequently mentioned request is not automatically the highest-value roadmap item. Combine the tags with your own account context, business priorities, and customer interviews. Inspect a sample in every theme and revisit the taxonomy as the product changes.

Batch classification and exports

Try a decision ↗

Continue your workflow

Ask about plans & usage

Find a product answer

Answers come from the published product guide. For account-specific questions, contact support.

Contact
DAILY BONUS

2 free credits, every day

Claim 2 free credits each UTC day — 14 across seven claims. No purchase needed. Credits do not expire.

    Resets at 00:00 UTC. No streak required.

    Try a decision →

    Take the next decision into your workspace.

    1 anonymous attempt per day · 20 signup credits · No card for the trial

    Sign in ↗

    Tell us what you need

    Describe the workflow you want to classify, the volume you expect, and the outcome you need. We reply by email.

    10–2,000 characters. Never include passwords, API keys, or payment details.