Run Overview

Date: 2026-05-09 | Run time: 05:37 UTC | Queries tested: 18 (15 P1, 3 P2) | Providers live: ChatGPT (gpt-4o), Claude (claude-sonnet-4-6) | Providers offline: Perplexity (401), Gemini (invalid key) | Prior successful run: 2026-04-28

First run to return citation data since April 28. April 30 and May 8 sessions had complete failures or incomplete execution.

API Status and Self-Heal

Gemini panel replaced with Claude via Anthropic API (claude-sonnet-4-6). Perplexity remains offline. No destructive changes.

Critical note from April 28 run: a valid Perplexity key was found in Repos/sail-marketing/Marketing_project/ai-visibility/api-keys.env when vault.env key was stale. Check that file before concluding Perplexity is unreachable on next run.

Citation Results

Overall citation rate: 11.1% (2 of 18 queries) | Severity: CRITICAL

Queries where we ARE cited:

• "motorcycle accident lawyer Louisville KY" -- ChatGPT only (score 2)
• "Sam Aguiar Injury Lawyers reviews" -- ChatGPT + Claude (score 2 each)

All 16 other queries: zero citations on both platforms.

Week-over-Week vs April 28

April 28: 13% named rate (12/93 provider-query runs, 4 providers, 31 queries). Today: 8% provider-query rate (3/36 runs, 2 providers, 18 queries). Not directly comparable because Perplexity and Gemini carried most April 28 citations. Trend direction inconclusive until Perplexity is restored.

Competitor Leaderboard

1. Morgan & Morgan -- 21 cross-platform mentions