Tag
#LLM
ServiceNow
Now Assist Token Budgets: Capping LLM Spend Per Skill
Stop Now Assist token bills from drifting. Patterns for per-skill budgets, cost-per-resolution tracking, and the kill switch you should have wired yesterday.
Open Source
Open-Source LLMs in CRM with Ollama
Running open-source models (Llama, Mistral, Qwen) on your infrastructure for CRM use cases. When it makes sense.
Self-Hosted
Self-Hosted LLM Inference for CRM
Running open-source models on your infrastructure — hardware, orchestration, scaling, when the math works.