Analyzes campaign performance by type, calculates ROI and conversion metrics, and generates AI-powered optimization recommendations per campaign type.

How it works 11 steps

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

Data fetch

▼ campaigns campaign-list-reader-hubspot

Fetch list reader from hubspot

▼

Process (10 steps)

⚠ check_data guard

Stop if campaigns is empty

■ valid_campaigns filter

Filter by condition

■ type_stats group_by

Group by campaign_type

■ enriched_types map

Extract from each item

■ metrics_table to_table

Format results as a data table

■ should_ai all

Check if all conditions are true

■ ai_input pick

Keep only specific fields from

skip: step.should_ai equal false

■ hashed_input hash_replace

Anonymize sensitive fields for safe AI processing

skip: step.should_ai equal false

✦ recommendations ai-prompt

AI generates a response from a custom prompt

skip: step.should_ai equal false

■ restored_recommendations hash_restore

Restore anonymized fields back to real values

skip: step.should_ai equal false

▼

Output

table metrics_table

ai_analysis restored_recommendations

Settings 3 configurable

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

enable ai toggle = on

lookback days number = 30

min spend threshold number = 100