The Chanl Blog
Insights on building, connecting, and monitoring AI agents for customer experience — from the teams shipping them.
All Articles
235 articles · Page 5 of 20
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.
Build a Pharmacy Refill Voice Agent (NCPDP, DEA, 60-Second Refill)
Build a voice AI for prescription refills that respects DEA Schedule II, handles NCPDP refill-too-soon rejections, and routes the right calls to humans.
How to Build a Real Estate Showing Voice Agent (MLS, Lockboxes, TCPA)
Build a real estate voice agent that pulls live MLS data, parses showing instructions, books tours, and sends lockbox codes at the right time.
How to Build a Tier-1 Chat Agent That Resolves (Not Just Deflects)
Bots claim 40% deflection; re-contact data says half is fake. Build the architecture that cuts tickets: auth-gated KB, calibrated confidence, escalation with context.
How to Build an AI Voicemail Agent That Gets a Callback (AMD, TCPA)
Eighty percent of B2B calls hit voicemail. Most AI dialers get blocked. Here's the AMD plus synthesis plus inbound callback pipeline, with TCPA baked in.
When Your Customer's Browser Agent Resolves the Ticket Before Yours Picks Up
Browser Use, Operator, Mariner, Computer Use. Here's what happens to CX volumes when the customer's browser agent resolves the ticket before yours picks up.
Your CX Agent Doesn't Care Who Won SWE-Bench. Here's Who Actually Wins.
SWE-bench crowns a coding king. Customer experience agents answer to a different benchmark, tau-bench, and the rankings flip. The head-to-head that actually predicts production reliability.
Multi-Agent Systems Don't Fail at Reasoning. They Fail at Handoff.
Multi-agent systems don't fail at reasoning. They fail at handoff. Command objects, memory transfer, and the 8-10 handoff cliff, plus the telemetry that catches drift.
Everyone Benchmarks Opus. Your Chatbot Runs on Haiku.
Haiku 4.5, GPT-5 Mini, Gemini Flash at the $1/MTok tier that powers CX. Tool-call accuracy, first-token latency, structured-output reliability, blended cost math.
Learn Agentic AI
Weekly. Patterns for shipping agents that work — MCP, scorecards, regression tests, prompts, model comparisons.
