I Escondido·In 8 weeks (June 2026)
ForaCity Developer Portal
Back to AI Engine Overview

AI Audit Trail

Decision logging, data retention, and accountability for all AI operations

Every AI decision that affects compliance, finances, or public records is logged and traceable. This page documents what data is retained, how long it's kept, and how to trace any AI-generated output back to its source inputs and reasoning.

Audit Principle

For any AI-generated output visible to users, an auditor should be able to answer: What data went in? What model produced it? What rules constrained it? What human approved it? If any of these questions can't be answered, the AI function needs additional logging.

Audit Categories

Compliance AI Audit

Every conflict analysis, prediction, and compliance assessment is fully traceable.

Traceable Fields
conflictAnalysis.reasoning
Full AI reasoning chain for each conflict identified
Permanent
conflictAnalysis.severity
AI-assigned severity level with justification
Permanent
conflictAnalysis.confidence
Confidence score for the analysis
Permanent
conflictPrediction.predictedConflicts
Pre-meeting conflict predictions with reasoning
Until meeting date + 90 days
conflictPrediction.officerContributions
Contribution data used for prediction (snapshot)
Permanent
Available Audit Actions
View full reasoning chain for any conflict analysis
Compare AI prediction vs. actual meeting outcomes
Trace which contributions triggered which conflict flags
Export compliance audit reports for FPPC review

Sample Audit Log

TimestampFunctionUserInputOutputStatus
2:23:17 PMconflictAnalysissystemContribution #4821 vs Agenda Item #312severity: medium, confidence: 0.78
2:15:42 PMsuggestFundingSourcescitizen_1847Solution #156 (Park Renovation)4 suggestions, max confidence: 0.85
1:58:03 PMrefineArgumentcitizen_2341Argument #892 (Housing Density)credibility: 72, tags: [housing, zoning]
1:45:19 PMgenerateCommunityReportcitizen_1204Proposal #67 (Water Conservation)voiceScore: 81, evidence: moderate
1:22:55 PMconflictPredictionsystemMeeting 2026-04-08 (5 agenda items)2 potential conflicts identified
12:58:11 PMreshapeToProposalcitizen_3102Raw input (287 chars)Structured proposal contribution
12:34:28 PMmeetingAnalysisadminMeeting 2026-03-25 transcript12 topics, 3 compliance flags
11:47:03 AMfindCollaborationscitizen_1847Proposal #71 (Transit)3 collaboration matches

Data Retention Policy

Compliance analysis results
Legal audit requirements — FPPC may review at any time
Permanent
Conflict predictions
Predictions expire after meeting; retained for accuracy calibration
Meeting date + 90 days
Funding suggestions
Financial advisory accountability — track suggestion accuracy over time
Permanent
Proposal AI refinements
Citizen content integrity — always show original alongside AI version
Permanent
Community Reports
Community intelligence is a public good — preserved for historical reference
Permanent
Meeting analysis
Government accountability — supplements official records
Permanent
AI invocation logs
Operational monitoring — older logs archived to cold storage
1 year rolling
Raw LLM responses
Debugging and quality assurance — not needed long-term
30 days

Pre-Deployment Audit Checklist

All AI functions have system prompts that constrain output format
Financial functions use JSON Schema response_format (strict mode)
Compliance analysis includes full reasoning chain
Community Report stats are overridden with real database counts
AI-refined content stored alongside citizen originals (never overwrites)
Funding suggestions include confidence scores and risk factors
No AI function can auto-publish, auto-file, or auto-apply
Rate limiting configured for all AI endpoints
AI-generated content labeled in UI
Audit log captures timestamp, user, function, input hash, output hashplanned
Cold storage archival configured for logs older than 1 yearplanned
Automated accuracy calibration for conflict predictionsplanned