The Chanl Blog
Insights on building, connecting, and monitoring AI agents for customer experience — from the teams shipping them.
All Articles
303 articles · Page 10 of 26
MCP tool description drift: the silent failure nobody alerts on
Edit an MCP tool description for clarity, lose 8% routing accuracy, and the eval suite stays green. How to detect, gate, and roll back the drift.
Your voice agent's P95 is lying. The real problem is P99.9
Per-stage P95 hides the tail customers feel. How variance compounds across STT, LLM, and TTS, and how to SLO the joint distribution.
How to Eval Agents When There's No Right Answer
Most eval methods assume you know the correct response. CX agents rarely have one. Here's how to score agent quality with criteria-based rubrics and LLM-as-judge, no labeled ground truth required.
Stop Loading All Your MCP Tools at Once
Loading 50 MCP tools burns 72K tokens before your agent says a word. Progressive tool discovery fixes that: smaller context, sharper decisions, real code patterns.
How to Build a Voice BDR That Qualifies (BANT as a State Machine)
Most AI SDRs ask 'tell me about your business' and dump benefits. Here's how to encode BANT as tool calls, score live, write to Salesforce, and exit politely.
Build a Save-Desk Voice Agent That Won't Get You Sued
FTC click-to-cancel was vacated. State laws still bite. The cancel-first architecture, one-shot offers, and audit trail for a save-desk voice agent.
How to Build a Cart Recovery Agent (and When to Send Nothing)
Most cart-recovery flows are three discount emails. A real recovery agent decides why the customer left, picks the right channel, caps the discount to protect margin, and sometimes sends nothing at all. Here is how to build it.
Build a Returns Voice Agent That Can't Refund Itself Broke
Returns are 60% of peak ecommerce contact volume. Most voice agents will refund $4,000 on a prompt injection. Here's how to build one that physically can't.
Build a Nurture Agent That Decides Not to Send
Most nurture sequences are 14 emails on a calendar. The fix is an event-triggered agent whose most valuable action is wait. Here's the worker.
How to Build a Healthcare Appointment Voice Agent (FHIR, 270/271, HIPAA)
Most voice AI tutorials stop after hello. The real build: identity verification, FHIR slots, 270/271 eligibility, A2P SMS, escalation, with HIPAA gates intact.
Building an AI Nurse Line Without Practicing Medicine
Health systems pay $20-30 per nurse-line call. AI is the obvious cost play, but every triage agent raises a malpractice question. Here's the safe architecture.
Build a KYC Voice Agent: 4-Minute Account Open, 5-Year Audit Log
Voice collects name, DOB, SSN. SMS hands the camera the rest. OFAC screens before the next word. Architecture of a KYC voice agent that survives a BSA exam.
Learn Agentic AI
Weekly. Patterns for shipping agents that work. MCP, scorecards, regression tests, prompts, model comparisons.
