Feedback

The Feedbacks page in the admin console (Feedbacks List) is where every user-submitted comment about your Digital Twin shows up. It is the qualitative signal layer on top of Histories — Histories tells you what was said, Feedback tells you what users thought of it.

​

What feedback collects

The Feedbacks page collects written comments people submit through the feedback form (Submit Feedback; Send feedback in the Studio UI). Each feedback row is associated with the submitting user, the Digital Twin, and a timestamp, plus any response you record.

​

Where to find it

Open Admin → Feedbacks from the side menu. The page lists every comment for the Digital Twins where you hold feedbacks.list, newest first. Each new comment is also emailed to the Digital Twin’s Contact Emails (“New User Feedback Received”, with the sender’s address and the text).

​

Filtering and sorting

The filter bar lets you narrow the list to exactly the feedback you need to act on:

• Instance — restrict to a single Digital Twin instance
• Account — when you administer several Digital Twins, scope to a whole account at once
• User search — by email, first name, or last name
• Column filters — filter the list in place by Digital Twin, user, or feedback text

Filters persist as you scroll so you can review a large window without losing your place.

​

Drilling into a feedback row

Click the pencil icon on any row (needs feedbacks.edit) to open the detail panel. You will see:

• User — name, email, and account type
• Instance — the Digital Twin instance the feedback is about
• Submitted — exact timestamp
• Feedback — the full text the user submitted, with a one-click copy button
• Response — a text area for your reply. The person sees it in their own feedback list as Response from followed by your Digital Twin’s AI name (no email is sent). The Respondent Email field next to it is not kept.

To read what the user and the Digital Twin actually said around the time of the feedback, filter Histories to the same user and window.

​

Responding to feedback

You have several options once you have read a piece of feedback:

• Reach out to the user — the panel surfaces the user’s email so you can reply directly. For sensitive or complex issues, a personal email beats anything automated.
• Record your response — save your reply on the row; the person sees it the next time they open the feedback form, and your team can see which items have been handled.
• Delete — removes the comment from the list when it is spam, abusive, or sent by mistake; it cannot be undone from the admin console.

When the issue is operational rather than product-level (an outage, an upstream provider failure), escalate to the Praxis AI team at humans@praxis-ai.com.

​

Patterns to look for

Single complaints are noise. The value of feedback is in patterns. Things to watch for:

• Sudden drop in ratings — a wave of thumbs-down (visible in Histories) within a few hours usually signals a configuration drift: a new instruction, a model change, or a retrieval source that has gone stale.
• Same complaint, multiple users — three users in a day all reporting “it forgot what we were talking about” is a memory or compaction signal, not three coincidences.
• Model regression — if you switched the Digital Twin’s model recently and negative ratings climbed afterwards, the rollback is your first move.
• Prompt drift — when the Digital Twin starts answering off-topic, the Instructions field is the place to look; small edits sometimes have outsized behavioural effects.
• Topic clusters — if multiple users complain about the same subject (a specific course, policy, or feature), feed that back into your Onboarding Questions or Assistants.

​

Using feedback to refine Instructions and Assistants

Feedback is most valuable when it changes behaviour. Two tight loops:

1. Instructions tuning — when feedback consistently shows the Digital Twin missing a constraint (“don’t recommend third-party tools”, “always cite the source”), add a line to the Instructions field in Configuration. Re-test with a fresh conversation.
2. Assistant scope refinement — if users keep complaining that the wrong assistant answered their question, tighten the assistant’s description so Pria is more likely to pick the right one. See Assistants.

Tie each change back to the feedback that prompted it (commit notes, a shared doc) so you can measure whether the next week of feedback improves.

​

Privacy considerations

Feedback rows always include the submitting user — there is no anonymous channel inside Pria today. Consider the following when reviewing:

• Treat comments as personal data. FERPA / GDPR principles apply: don’t paste raw feedback into public channels.
• Identified by default. Feedback carries the sender’s account; they should expect a human to read it.
• Consent for outreach. If you plan to email a user about their feedback, it is courteous to keep the reply scoped to the issue they raised.
• Scope. You see feedback for the Digital Twins where you hold feedbacks.list; the Account filter narrows to one account’s Digital Twins.

​

Bulk export for analysis

For longitudinal analysis, use CSV (the loaded rows with the visible columns) or Export all (the whole filtered list, emailed to you as a download link). The export includes the comment, any recorded response, the person’s name and email, the Digital Twin, and the date. Common downstream uses:

• Pivot tables in a spreadsheet (positive vs negative split by week)
• Sentiment classification in your analytics pipeline
• Sharing a redacted slice with the product team during weekly reviews

For richer analyses (linking feedback to retrieval sources, joining across several Digital Twins, slicing by model version), open conversations directly in Histories and use its export there.

​

Related

• Histories — the conversations around the time of a comment (a feedback row is not linked to a conversation)
• Sessions — who was active when the feedback arrived
• Configuration — where you tune the Instructions feedback most often calls out
• Assistants — refining assistant scope based on feedback patterns
• Entitlements — the feedbacks.list, feedbacks.edit, and feedbacks.delete permissions that gate this page