Support automation and the AI front desk
Help center for agents
Building the help center an agent reads
- How to Write a Knowledge Base an AI Assistant Can Use
- How to Map the Questions Your AI Front Desk Will Get
- How to Write a Help Article an AI Can Answer
- Mapping the Questions Your Front Desk Agent Will Get
- A Help Article an Agent Can Retrieve and Quote: Structure First
- How to Keep a Help Center in Sync with the Product It Describes
- How to Structure a Help Center So Retrieval Finds Articles
- How to Write a Help Article an Agent Can Retrieve and Quote
- All of Help center for agents
Retrieval and chunking
Retrieval quality and chunking
- Chunking and Overlap: Passage Size and Retrieval
- How to Write a Retrieval Test Set from Real Questions
- What to Store with Each Passage So Retrieval Can Be Audited
- When a Passage Is Stale: Versioning and TTL for Retrieved Context
- Access Scopes for Retrieved Context: Filtering Before the Prompt
- How to Choose a Chunk Size Without a Query Set
- How to Write a Topic Taxonomy Your Team and Your Rules Both Use
- Hybrid Search: Combining Keywords and Embeddings for Recall
- All of Retrieval and chunking
Retrieval and deflection metrics
Measuring retrieval and deflection
- Deflection Metrics for Support Automation
- From Recurring Questions to a Product Change
- How to Classify a Support Question as Content Gap or Flow Defect
- How to Turn Routing Logs into a Product Feedback Loop
- Measuring Help Center Retrieval: Recall and Precision
- A Retrieval Eval Harness: Golden Set, Runner and Sign-Off
- A Weekly Dashboard for Fallback and Miss Rates
- Building a Retrieval Test Set from Real Support Tickets
- All of Retrieval and deflection metrics
Designing the handoff
Designing the handoff to a human
- AI for Customer Support: What to Automate and What Not To
- An AI Front Desk for Service Businesses: What It Handles
- Escalation Rules for Support Agents
- Front Desk Escalation Rules: Triggers, Owners and Times
- The Response-Time Budget: Setting a Target Before You Measure
- What a Handoff Recipient Needs in the First Ten Seconds
- What to Log for Every AI Support Turn
- When to Fix a Bad AI Answer Yourself vs. Escalate to the Vendor
- All of Designing the handoff
Confidence and clarifications
Confidence thresholds and clarifications
- Confidence Thresholds for Support Answers
- Logging the Absence of Clarification Before an Approval
- Refusal and Handoff Rules for a Front Desk Agent
- Setting the Re-ask Limit for a Support Agent Before It Deflects
- The Question Budget: How Much Agent Talk a Customer Tolerates
- What a Support Agent's Confidence Score Should Trigger
- A Decision Log for Questions You Defer
- A Drift Check for Clarification Gaps Without New Labels
- All of Confidence and clarifications
Refund and exception handling
Refund and exception handling
- How to Test a Refund Agent's Decisions Against Real Tickets
- Writing a Support Agent's Refund Policy into Its Prompt
- A Decision Table for Refund Exceptions an Agent Cannot Resolve
- A Refund Limit Table an Agent Can Enforce
- Detecting Split Transactions an Agent Made to Stay Under a Limit
- Handling Refund Exceptions That Fall Outside the Prompt
- How to Write a Refund Decision Log That Supports an Audit
- The Refund Agent's Audit Trail: Logging Decisions and Reasons
- All of Refund and exception handling