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

# Knowledge Retrieval During Live Calls

> Understand how Callaro grounds live conversations in approved knowledge instead of relying on static model memory.

# Retrieval keeps live answers current and accountable.

Callaro can retrieve knowledge during a live call so the AI answers with current, approved information rather than guessing from stale model memory.

<Steps>
  <Step title="Detect an information need">The runtime identifies that the current turn requires factual grounding or tenant-specific data.</Step>
  <Step title="Query the approved knowledge source">Only the configured knowledge base or allowed retrieval surfaces are queried.</Step>
  <Step title="Return a grounded response">The model uses the retrieved evidence to answer directly and concisely.</Step>
  <Step title="Log the outcome">Retrieval-backed behavior can be inspected through transcript and trace data for QA and continuous improvement.</Step>
</Steps>

## Knowledge quality checklist

* Keep sources scoped by tenant/domain and publish state.
* Remove stale or duplicate documents that compete for the same intent.
* Include versioned process documents for policy-sensitive answers.
* Audit retrieval-backed transcripts to identify missing knowledge coverage.

<Warning>
  Do not give the runtime unrestricted access to large, noisy document sets. Retrieval quality depends on disciplined knowledge curation and publication review.
</Warning>