Fair Housing Steering Detector
Detects potential FHA steering violations by analyzing zip code distribution patterns across inferred buyer demographic groups. Cites 24 CFR §100.70 when risk detected. Note: Buyer names are transmitted unhashed to AI provider solely for in-memory demographic inference required by FHA analysis. Confirm your AI provider's data handling compliance.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Data fetch
deals
?
▼
Process (12 steps)
agent_deals
filter
Filter by condition
valid_showings
filter
Filter by condition
total_showings
count
Count items in valid showings
check_data
guard
Stop if valid showings is empty
showing_data
map
Extract from each item
ai_analysis
?
skip: config.enable_ai equal false
zip_clusters_used_safe
coalesce
Use the first available value from: ai analysis zip clusters used, N/A
steering_score_safe
coalesce
Use the first available value from: ai analysis steering score, N/A
risk_level_safe
coalesce
Use the first available value from: ai analysis risk level, N/A
agent_summary
pick
Keep only specific fields from
results_table
to_table
Format results as a data table
compliance_checklist
to_checklist
Format results as an actionable checklist
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
hubspot
setting
=
enable ai
toggle
=
on
lookback days
number
=
90
steering threshold
number
=
2
low medium boundary
number
=
1
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.