The Chanl Blog
Insights on building, connecting, and monitoring AI agents for customer experience — from the teams shipping them.
All Articles
307 articles · Page 2 of 26
How LLM Routing Cuts Agent Costs 40-85% in Production
Most CX agents send every request to their priciest model. Routing simple queries to a cheap model cuts costs 40-85%, at 90-95% of single-model quality.
9 in 10 MCP Servers Skip OAuth. The July 28 Spec Just Landed.
Only 8.5% of MCP servers use OAuth. The July 28 spec landed, and it doesn't make auth mandatory. Here's what it actually requires and what to fix first.
LLM judges grade your agents wrong. Here's how to fix them.
LLM judges are the only practical way to evaluate agents at production scale, but they have predictable biases that give you false confidence. Here's how to calibrate them so the scores you see reflect the quality you actually have.
Your MCP tool descriptions are failing your agent
97% of real-world MCP tool descriptions contain quality problems that hurt agent accuracy and inflate token costs. Here's what the research found and how to fix it.
The Six Agent Observability Platforms That Matter in 2026
Most observability platforms were built for LLM apps, not agentic CX systems. Here's how the six that matter in 2026 hold up against the criteria that count.
The Five Eyes Published an Unusually Specific AI Agent Advisory
The Five Eyes published the first joint guidance on agentic AI security. For CX builders it's specific: tool permissions, schema injection, and human oversight.
Testing AI agent handoffs before they break in production
Multi-agent CX systems fail at the seam between agents. Here's how to build handoff tests that catch context loss, duplicate actions, and loop failures before your customers feel them.
The trace-to-dataset loop: turning live conversations into eval cases
Your best eval cases are already in your production traces. Here's how to automatically curate the interesting ones into a test suite that gets better every week without manual effort.
How to rescue a stuck CX agent conversation
Conversations get stuck in four predictable patterns: clarification spirals, topic drift, assumption deadlocks, and initiative mismatches. Here's how to detect each one mid-flight and apply the repair move that actually works.
Agentjacking: how attackers hijack production AI agents
Agentjacking is a new attack class that targets the data your agent trusts, not the model itself. Learn how attackers exploit CRM notes, tool responses, and knowledge bases to hijack production CX agents, and how to stop them.
Most of your agent traffic doesn't need your best model
Routing 100% of agent traffic to your most capable model is costing you 6-10x what it should. Here's how to build a cascade router that handles simple tasks cheaply and escalates to stronger models only when the task demands it.
When your LLM provider goes down, your agent shouldn't
LLM providers go down. Anthropic's 90-day uptime is 98.95% -- that's 44 hours of potential outage per year. Here's how to build provider failover into production AI agents so a cloud incident doesn't become a customer experience incident.
Learn Agentic AI
Weekly. Patterns for shipping agents that work. MCP, scorecards, regression tests, prompts, model comparisons.
