> ## Documentation Index
> Fetch the complete documentation index at: https://docs.threetone.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Insights

> Turn saved conversations and available analytics into reviewable findings with a clear sample, source, and follow-up.

An insight is a finding you can trace to evidence and act on. Use existing conversation records and available dashboard measurements to identify a specific improvement, then keep the source and review method with the finding.

## Choose evidence that exists

| Evidence | Current boundary |
| - | - |
| [Saved conversations](/agents-platform/monitor/conversations) | Read transcripts, metadata, and analysis already present in a record. |
| [Workspace analytics](/agents-platform/monitor/analytics) | Dashboard metrics depend on the deployment's analytics configuration and recorded data. |
| [Topics](/agents-platform/monitor/topics) | Automated topic discovery is unavailable; prepare a taxonomy through manual review. |
| [Analysis](/agents-platform/monitor/analysis/overview) | A saved definition or existing result is not proof of a new analysis run. |
| [Real-time insights](/agents-platform/monitor/insights/real-time-insights) | The current public live read is a workspace counter, not a transcript or insight stream. |

Public workspace usage and API-request reports currently return placeholder results. Do not use an empty report to conclude that there was no activity or that a cost is zero.

## Produce a reviewable finding

<Steps>
  <Step title="Define the question">
    Choose one question, such as why users abandon a setup step. Record the agent, time interval, time zone, and selection rule. Follow pagination when gathering saved records.
  </Step>

  <Step title="Review the underlying records">
    Read full details when summaries omit messages. Separate what the user requested, what the agent did, and the observed outcome. Preserve unknown outcomes rather than counting them as failures or successes.
  </Step>

  <Step title="Record evidence and uncertainty">
    Keep safe conversation identifiers, the reviewed sample size, the matching cases, and any missing data. Separate a direct observation from a proposed explanation. A small sample can suggest a change without establishing a population-wide rate.
  </Step>

  <Step title="Assign and recheck the change">
    Give the proposed prompt, source, or configuration change an owner. Record the version used before and after it, then compare the same review criteria when new verified records become available.
  </Step>
</Steps>

Keep customer transcripts in access-controlled review systems. Share only the excerpts needed to explain the finding and follow the workspace's [privacy review](/agents-platform/monitor/privacy/overview).

## Frequently asked questions

<AccordionGroup>
  <Accordion title="Does this page describe an automated insight generator?" id="insights-faq-generator">No. It describes an evidence review workflow using current reads. Automated topic discovery and analysis execution have separate implementation requirements.</Accordion>
  <Accordion title="Can I compare periods with different filters?" id="insights-faq-comparison">Record the difference and account for it. A change in agent, time zone, sampling, or data availability can explain a changed metric without a change in agent quality.</Accordion>
</AccordionGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.