Identifies high-frequency support topics missing from knowledge base articles. Scalability note: For large ticket volumes, adjust `min_occurrences` or `lookback_days` to optimize performance.

How it works 9 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Data fetch

▼ tickets ticket-list-reader-hubspot

Fetch list reader from hubspot

▼ kb_articles kb-article-list-hubspot

Fetch article list from hubspot

▼

Process (7 steps)

■ extract_kb_titles pluck

Extract title from each item

✦ gap_analysis ai-prompt

AI generates a response from a custom prompt (PII auto-protected)

skip: step.tickets is_empty

■ gap_analysis_safe coalesce

Use the first available value from: gap analysis,

■ gap_count count

Count items in gap analysis safe

■ gap_summary switch

Map gap count to one of: 0

■ format_gaps map

Extract from each item

■ gap_table to_table

Format results as a data table

▼

Output

summary gap_summary

table gap_table

Settings 2 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

lookback days number = 90

min occurrences number = 3