MEDIUM
nordanyan-search-terms
154× FIRED
18h ago
Waste ratio 34.7% — 7 terms spent $2,508 with 0 conversions
▾
Waste ratio 34.7% — 7 terms spent $2,508 with 0 conversions
Waste ratio 34.7% — 7 terms spent $2,508 with 0 conversions
- › Review Nordanyan Law search_terms trend over the past 7 days for pattern
- › Check if any recent changes (bids, budgets, targeting) correlate with this alert
MEDIUM
nordanyan-call-volume
141× FIRED
18h ago
Zero calls during business hours: 11 AM
▾
Zero calls during business hours: 11 AM
Zero calls during business hours: 11 AM
- › Review Nordanyan Law call_volume trend over the past 7 days for pattern
- › Check if any recent changes (bids, budgets, targeting) correlate with this alert
MEDIUM
nordanyan-daily
42× FIRED
18h ago
Spend pacing :arrow_down: 49% under (projected $20,230 vs $40,000 budget)
▾
Spend pacing :arrow_down: 49% under (projected $20,230 vs $40,000 budget)
Spend pacing :arrow_down: 49% under (projected $20,230 vs $40,000 budget)
- › Review Nordanyan Law daily budget caps and campaign-level spend limits
- › Check if any Nordanyan Law campaigns were paused or have limited serving
MEDIUM
ai_ops_weekly_digest
13× FIRED
6d ago
AI Ops Weekly Digest — Week of June 08, 2026
============================================================
COST STATUS: ON TRACK
MTD: $66.39 | Projected: $248.96 | Budget: $1,500.00 (17%)
7-day avg: $9.48/day
MODEL EFFICIENCY:
Opus ratio: 96% | Wasteful sessions: 4 | Est. waste: $52.00
COST ALLOCATION:
RGDM (internal): $6,442.97 (22 sessions)
SESSION QUALITY: HEALTHY
Avg score: 92/100 | Cache hit: 81.6% | Flagged: 0/22
OVERHEAD TREND: GROWING
Latest avg input: 6,744,114 tokens/session | WoW: -15.6% | Consecutive growth: 3 weeks
RECOMMENDATIONS:
1. [HIGH] Route trivial sessions (<5 min) to Sonnet/Haiku instead of Opus (est. $208.00/mo savings)
2. [MEDIUM] Audit CLAUDE.md and memory files — 3+ weeks of growing overhead
3. [MEDIUM] Investigate low cache hit rate — may indicate context management issues
ALERTS:
[MEDIUM] (efficiency) Opus ratio 95% exceeds 25% threshold
[MEDIUM] (efficiency) Estimated $52.00 waste from 4 trivial Opus sessions
[LOW] (allocator) RGDM (internal) accounts for 100% of AI spend — consider cost optimization
[MEDIUM] (overhead) 3 consecutive weeks of overhead growth — review CLAUDE.md and memory
OUTCOME TRACKING:
[-] Opus Ratio: 96% (was 89%, +7.4% — regressed)
[+] Est. Waste: $52.00 (was $119.18, -56.4% — improved)
[+] Avg Quality: 92/100 (was 90/100, +2.8% — improved)
[+] Cache Hit: 81.6% (was 75.0%, +8.8% — improved)
[+] Overhead: 6,744,114 tok (was 7,988,556 tok, -15.6% — improved)
4-week trends:
Budget Pacing: 17% → 18% → 19% (worsening)
Opus Ratio: 100% → 100% → 100% → 89% (improving)
▾
AI Ops Weekly Digest — Week of June 08, 2026 ============================================================ COST STATUS: ON TRACK MTD: $66.39 | Projected: $248.96 | Budget: $1,500.00 (17%) 7-day avg: $9.48/day MODEL EFFICIENCY: Opus ratio: 96% | Wasteful sessions: 4 | Est. waste: $52.00 COST ALLOCATION: RGDM (internal): $6,442.97 (22 sessions) SESSION QUALITY: HEALTHY Avg score: 92/100 | Cache hit: 81.6% | Flagged: 0/22 OVERHEAD TREND: GROWING Latest avg input: 6,744,114 tokens/session | WoW: -15.6% | Consecutive growth: 3 weeks RECOMMENDATIONS: 1. [HIGH] Route trivial sessions (<5 min) to Sonnet/Haiku instead of Opus (est. $208.00/mo savings) 2. [MEDIUM] Audit CLAUDE.md and memory files — 3+ weeks of growing overhead 3. [MEDIUM] Investigate low cache hit rate — may indicate context management issues ALERTS: [MEDIUM] (efficiency) Opus ratio 95% exceeds 25% threshold [MEDIUM] (efficiency) Estimated $52.00 waste from 4 trivial Opus sessions [LOW] (allocator) RGDM (internal) accounts for 100% of AI spend — consider cost optimization [MEDIUM] (overhead) 3 consecutive weeks of overhead growth — review CLAUDE.md and memory OUTCOME TRACKING: [-] Opus Ratio: 96% (was 89%, +7.4% — regressed) [+] Est. Waste: $52.00 (was $119.18, -56.4% — improved) [+] Avg Quality: 92/100 (was 90/100, +2.8% — improved) [+] Cache Hit: 81.6% (was 75.0%, +8.8% — improved) [+] Overhead: 6,744,114 tok (was 7,988,556 tok, -15.6% — improved) 4-week trends: Budget Pacing: 17% → 18% → 19% (worsening) Opus Ratio: 100% → 100% → 100% → 89% (improving)
AI Ops Weekly Digest — Week of June 08, 2026 ============================================================ COST STATUS: ON TRACK MTD: $66.39 | Projected: $248.96 | Budget: $1,500.00 (17%) 7-day avg: $9.48/day MODEL EFFICIENCY: Opus ratio: 96% | Wasteful sessions: 4 | Est. waste: $52.00 COST ALLOCATION: RGDM (internal): $6,442.97 (22 sessions) SESSION QUALITY: HEALTHY Avg score: 92/100 | Cache hit: 81.6% | Flagged: 0/22 OVERHEAD TREND: GROWING Latest avg input: 6,744,114 tokens/session | WoW: -15.6% | Consecutive growth: 3 weeks RECOMMENDATIONS: 1. [HIGH] Route trivial sessions (<5 min) to Sonnet/Haiku instead of Opus (est. $208.00/mo savings) 2. [MEDIUM] Audit CLAUDE.md and memory files — 3+ weeks of growing overhead 3. [MEDIUM] Investigate low cache hit rate — may indicate context management issues ALERTS: [MEDIUM] (efficiency) Opus ratio 95% exceeds 25% threshold [MEDIUM] (efficiency) Estimated $52.00 waste from 4 trivial Opus sessions [LOW] (allocator) RGDM (internal) accounts for 100% of AI spend — consider cost optimization [MEDIUM] (overhead) 3 consecutive weeks of overhead growth — review CLAUDE.md and memory OUTCOME TRACKING: [-] Opus Ratio: 96% (was 89%, +7.4% — regressed) [+] Est. Waste: $52.00 (was $119.18, -56.4% — improved) [+] Avg Quality: 92/100 (was 90/100, +2.8% — improved) [+] Cache Hit: 81.6% (was 75.0%, +8.8% — improved) [+] Overhead: 6,744,114 tok (was 7,988,556 tok, -15.6% — improved) 4-week trends: Budget Pacing: 17% → 18% → 19% (worsening) Opus Ratio: 100% → 100% → 100% → 89% (improving)
- › Route trivial sessions (<5 min) to Sonnet/Haiku instead of Opus
- › Audit CLAUDE.md and memory files — 3+ weeks of growing overhead