Agent operations

Frontier lab agent command center

Operational state for run now: scrape runs, source health, the analysis queue, and model provenance.

last scrape 1h46/56 sources healthy18 analysesdeepseek · deepseek-v4-pro

Agent answer

Frontier lab agent operations show 16 queued organizations in run now: 16 runnable analyses, 0 page-capture targets, 0 scrape-repair targets, and 0 fresh monitors. DeepSeek v4 pro via deepagents is the dominant standing analysis path across 18 generated analysis rows. 10 of 56 sources need attention. Next dispatch: run_analysis_agent for Cohere because new captured evidence is fresher than the stored analysis. Top signal inspection: OpenAI - Perplexity trusts GPT-6 Astra with end-to-end systems with watch priority.

Cohere

npm run agent:analysis -- --url <app-url> --org <org-slug> --limit 1 --web-limit 10

Analysis queue

json16 shown

Scrape runs

8 of 12snapshot
Sep 13, 2026
ok
duration 1m 52s · sources 32events 3,673 · HN 0failures clear
Sep 13, 2026
ok
duration 1m 42s · sources 32events 3,673 · HN 0failures clear
Sep 12, 2026
ok
duration 1m 44s · sources 32events 3,673 · HN 0failures clear
Sep 12, 2026
ok
duration 1m 56s · sources 32events 3,673 · HN 0failures clear
Sep 12, 2026
ok
duration 1m 41s · sources 32events 3,673 · HN 0failures clear
Sep 12, 2026
ok
duration 1m 23s · sources 32events 3,673 · HN 0failures clear
Sep 12, 2026
ok
duration 20s · sources 33events 823 · HN 0failures clear
Sep 12, 2026
failed
duration 3m 46s · sources 39events 1,493 · HN 0failures 4 · cerebras/careers, google-deepmind/careers, fireworks-ai/careers
4 older runs in snapshot

Source health

46 ok · 1 dead · 5 stale · 4 emptycoverage