AI, customer experience, and the craft of support.
Field notes on running support with people and AI agents on one system — deflection, conversation quality, coaching, and the metrics that move.
Deflection vs. Resolution: Why the Words You Choose Matter
Deflection avoids a person; resolution answers the customer. Buyers should know which they're buying.
AI Support Platform vs. Traditional Ticketing: What Changes
Ticketing tracks work; an AI support platform does the work. Here's the real difference.
Single-Flight Safety: Why Your AI Should Never Refund Twice
Run the same action twice and you've double-refunded a customer. Here's how safe systems prevent it.
AI Governance for Support Leaders Who Aren't Engineers
You don't need to code to govern AI well. Here's what to demand from any AI support system.
Permissions and Limits: Deciding What Your AI Agent Can Do
An AI agent should only do what you've explicitly allowed. Here's how to scope its power.
Preventing AI Hallucinations From Reaching Your Customers
A confident wrong answer erodes trust fast. Here's how to keep hallucinations away from customers.
How to Audit Your AI Support Agent's Decisions
You should be able to replay any AI decision and understand it. Here's how to audit one.
Fail-Closed by Default: Designing AI That Stops When Unsure
When an AI agent isn't sure, the safe default is to stop, not to guess. Here's why that matters.
Data Privacy in AI Support: A Practical Guide for CX Teams
AI support touches sensitive customer data. Here's how to keep it private and compliant.
Grounding AI Support in Real Data (and Never Faking It)
An AI agent should answer from your real systems, never a plausible guess. Here's how grounding works.
Receipts for AI Actions: What Auditable Support Looks Like
Every action an AI takes should leave a receipt you can read later. Here's what one contains.
Why an AI Agent Must Be Checked Before It Acts
A model that can refund, cancel, or email a customer needs a check before it acts. Here's why.
Measuring AI Agent ROI Without Fooling Yourself
AI vendors love big ROI claims. Here's how to measure your real return without the spin.
Reopen Rate: The Quality Metric Hiding in Your Ops Data
A closed ticket isn't a solved one. Reopen rate tells you the difference.
Backlog and Queue Management When Volume Spikes
A growing backlog compounds fast. Here's how to triage and recover when the queue blows up.
The Support Metrics Dashboard Every CX Leader Needs
The handful of numbers that actually tell you if support is healthy, on one screen.
Cost-to-Serve: How to Calculate What Each Conversation Costs
If you don't know your cost per conversation, you can't prove AI's ROI. Here's the calculation.
Staffing and Forecasting for Support: An Erlang-Free Primer
You don't need a math degree to forecast support staffing. Here's a practical approach.