Insights
The customer support field guide
Analysis, data notes, and how-tos across the whole craft — metrics, quality, people, ops, knowledge, tooling, trust, and AI. Key figures link to their sources; no vendor is paying for the verdict.
83dispatches in the archive20269
- Analysis
The AI support stack, decoded for non-engineers
LLMs, RAG, agents, guardrails: the four-layer stack behind every AI support pitch, in plain language — plus the one question that reveals which layer you're actually buying.
Oct 22, 20264 min - Analysis
Fine-Tuning vs Retrieval: Where Your Support Answers Live
Fine-tuning and RAG are pitched as rival ways to make a support bot "know your product." They do different jobs — and for grounding answers in your knowledge, the evidence points one way.
Sep 2, 20263 min - Analysis
Chatbot, Conversational AI, AI Agent: Three Words, Three Different Machines
Vendors use the three terms interchangeably. They describe genuinely different systems — and the difference is exactly what decides what you're buying and what it's allowed to do when no one is watching.
Aug 11, 20264 min - Analysis
Agentic AI in support: what "agents that take actions" actually do
The pitch is an agent that looks things up, issues the refund, and reschedules the delivery on its own. The reality in most support operations is narrower, more supervised, and more honest. Here is the gap, with the numbers.