Field notes on agentic support
Product updates, playbooks, and lessons from teams running AI on the front line of every conversation.
Latest posts
One inbox for WhatsApp, Instagram, and your website
Customers don't think in channels. Here's how a single agent keeps context across every surface — and why a shared inbox beats three disconnected bots.
RAG for support — grounding answers in your catalog
Retrieval keeps an agent's answers tied to your real products, policies, and docs. A practical look at building retrieval that support teams can trust.
Agentic AI vs. scripted bots — what actually changes
Scripted bots match keywords; agentic AI reasons, calls tools, and finishes the job. Here's where the difference shows up in real conversations.
Designing safe AI handoffs to humans
The best agentic systems know their limits. A playbook for handing a conversation to a person at the right moment — with full context, not a cold restart.
Measuring deflection without hurting CSAT
Deflection rate is easy to game and easy to misread. How to track automated resolution honestly — alongside the satisfaction signal that keeps it humane.
Guardrails that build trust, not friction
Guardrails shouldn't make an agent feel robotic. How to set boundaries that keep answers safe and on-brand while staying genuinely helpful.