domain · ai-ops
Operate AI systems that actually learn
Running AI in production: monitoring, evals, drift, cost, fallbacks.
Adjacent domains
- product · 2 co-occurrences
- gtm · 2 co-occurrences
- pmm · 2 co-occurrences
- growth-demand · 1 co-occurrences
- content-strategy · 1 co-occurrences
5 insights in ai-ops
- Anthropic is treating Skills and Cookbooks as the unit of vertical agent distribution, not one-off integrations · Anthropic
- GTM automation shifted from triggered batch automations to continuous-monitoring agents in under 18 months. The agent decides when to act. · Kyle Poyar
- 90% of AI content system output quality comes from the knowledge fed in, not from agent sophistication. One canonical artifact, many consumers. · Maja Voje
- Four subagent patterns are settling as standard: Inline Tool, Fan-Out, Agent Pool, and Teams. Each adds control surface at a real debugging cost. · Phil Schmid
- Batch-processing interview transcripts with Claude produces fabrications; reliable output requires a dedicated per-transcript skill at three minutes per file · Anthony Pierri