scan_calls
AI-score calls in a date range to identify angry customers, compliance issues, or missed commitments. Returns a ranked list with summaries for review.
Instructions
AI-score answered calls in a date range. Returns one page of scored results.
IMPORTANT: Before calling this tool, briefly tell the user that this analysis takes some time because it processes each call with AI (e.g. "Let me analyze your calls — this involves AI-scoring each conversation, so it may take a moment.").
Fetches a page of calls (default 100), loads their transcripts, scores each with a fast AI model, and returns a compact ranked list with scores, flags, and summaries.
CRITICAL — you MUST scan ALL pages. The first 100 results are NOT representative of the full dataset. Important issues may appear in any page. If the response shows remaining records, you MUST call all remaining pages (in parallel) before presenting results. Never skip pages or stop early — partial analysis gives unreliable results.
Pagination: Each call returns up to take scored records and reports the total.
If total > take, call ALL remaining pages IN PARALLEL:
First call: scan_calls(date_from='2026-02-20') → returns 100 scored + "350 total"
Then IN PARALLEL: scan_calls(..., skip=100), scan_calls(..., skip=200), scan_calls(..., skip=300)
After reviewing scored results, use get_call_transcript to read full dialogue of specific flagged calls.
Args: date_from: Start date (YYYY-MM-DD). Required. date_to: End date (YYYY-MM-DD). Defaults to same as date_from (single day). user: Agent name — display name or login name, resolved automatically. queue: Queue internal name (e.g. '10333'). question: What to analyze for. Be specific about what to flag. skip: Pagination offset (default: 0). Use to fetch subsequent pages. take: Number of calls to score in this page (default: 100, max: 200).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| skip | No | ||
| take | No | ||
| user | No | ||
| queue | No | ||
| date_to | No | ||
| question | No | Flag calls needing management attention: angry customers, escalation requests, compliance issues, lost deals, missed commitments. | |
| date_from | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |