← Back to Grand Jury Labs
Grand Jury Gavelly

Grand Jury Gavelly

Live

Overview

Gavelly is an AI-powered drafting aid for California Grand Jury draft reports. A juror uploads a draft before publication, and Gavelly checks it against the Civil Grand Jurors' Association of California style guide and the requirements of Penal Code § 933.05.

It reviews each finding and recommendation for proper formatting, checks that recommendations are addressed to the correct responding parties, flags passive voice and vague language, and surfaces issues that might cause a report to be challenged or returned. Jurors get actionable feedback, not just a pass/fail score.

Your draft stays confidential

A grand jury draft is confidential until the jury publishes it, and Gavelly is built for that. An uploaded draft is processed in memory only. It is never stored, never logged, and never used to train any model, consistent with the secrecy requirements of California Penal Code § 911 and § 924. Gavelly is an UnGovr drafting aid, not legal advice, and it does not replace counsel or judicial review under Penal Code § 933.05. It is not endorsed by or affiliated with the Civil Grand Jurors' Association of California.

→ How Gavelly protects your draft

What Gavelly Checks

# Compliance checks performed
Finding structure (evidence basis, clear statement)
Recommendation format (imperative, specific, measurable)
Responding party identification and role verification
Response deadline requirements (90-day rule)
Passive voice detection and rewrite suggestions
Tone and neutrality (no editorial language)
Cross-reference consistency (finding ↔ recommendation links)

How It Works

# Step 1: Upload draft report
upload county-2024-2025-draft.pdf
parse Extracted 42 pages, 8 findings, 12 recommendations

# Step 2: Compliance checks
check Finding F-1: PASS — properly supported by evidence
check Finding F-3: WARN — passive voice in key sentence
check Rec R-4: FLAG — responding agency not identified
check Rec R-7: WARN — no measurable outcome specified

# Step 3: Detailed feedback
report 7 issues found (2 flags, 5 warnings)
suggest Inline revision suggestions for each issue
✓ Report ready for review

Tech Stack

Claude (Anthropic) PDF parsing Surya OCR FastAPI Python PostgreSQL