The Chanl Blog
Insights on building, connecting, and monitoring AI agents for customer experience — from the teams shipping them.
All Articles
157 articles · Page 6 of 14
Your AI Agent Has No Guardrails
Air Canada honored a refund its chatbot hallucinated. DPD's bot cursed at customers on camera. One e-commerce agent approved $2.3M in unauthorized refunds at 2:47 AM. Here is the five-layer guardrail architecture that prevents all three.
Every Tool Is an Injection Surface
Prompt injection moved from chat to tool calls. Anthropic, OpenAI, and Arcjet shipped defenses in the same month. Here's what changed, what works, and what your agent architecture needs now.
Why Your AI Bill Is 30x Too High
Small language models match GPT-3.5 at 2% of the size and 95% less cost. Benchmarks, code, and a migration story from $13K/month to $400.
Your AI Agent Costs $13K/Month. Here's the Fix.
A production customer-service agent burned $13,247 in one month. Prompt caching, model routing, batch processing, and plan-and-execute architecture cut it to $1,100. Real pricing math for every technique.
Why Browser Agents Waste 89% of Their Tokens
Browser agents burn 1,500-2,000 tokens per screenshot. Chrome 146's navigator.modelContext API lets websites expose structured tools instead, cutting token usage by 89% and raising task accuracy to 98%. Here's how WebMCP works.
Part 1: Claude's 7 Extension Points — The Mental Model
CLAUDE.md, Skills, Hooks, MCP Servers, Connectors, Claude Apps, Plugins — Claude's extension ecosystem is powerful but confusing. Here's the mental model that makes sense of all 7.
Part 2: CLAUDE.md, Hooks, and Skills — Three Layers
CLAUDE.md sets conventions. Hooks enforce them. Skills teach workflows. Understanding these three layers — and their reliability spectrum — is the key to a Claude Code setup that actually works.
AI Agents Are Great. Until They're Not. When to Put Humans Back in Control
AI agents can handle 80% of your customer interactions with no problem. The other 20% is where your reputation is made or broken. Here's how to design escalation that actually works.
Part 3: MCP Servers vs. Connectors vs. Apps
All Claude Apps are Connectors. All Connectors are MCP Servers. Understanding this hierarchy — and when to build vs. use managed integrations — saves weeks of unnecessary engineering.
Part 4: All 7 Extension Points in One Production Codebase
50+ skills, multiple MCP servers, scoped rules, safety hooks — here's how all 7 Claude extension points compose in a real NestJS monorepo with 17 projects. What works, what fights, and what we'd do differently.
Zero-Shot or Zero Chance? How AI Agents Handle Calls They've Never Seen Before
When a customer calls with a request your AI agent has never encountered, what actually happens? We break down the mechanics of zero-shot handling, and how to test for it before it fails in production.
Your AI Agent Isn't Learning From Production. Here's What That's Costing You.
Most AI agents are deployed and forgotten. The teams winning with AI have a different strategy: closing the loop from every live call back into the agent itself.
Learn Agentic AI
One lesson a week — practical techniques for building, testing, and shipping AI agents. From prompt engineering to production monitoring. Learn by doing.
