The Chanl Blog

Insights on building, connecting, and monitoring AI agents for customer experience — from the teams shipping them.

All Articles

235 articles · Page 8 of 20

An engineer at a wide desk with two monitors showing warm and cool waveform visualizations, a headset between the screens, amber cityscape through floor-to-ceiling windows

Pipecat vs LiveKit: the trade-offs that lock you in

An opinionated comparison of Pipecat and LiveKit for production voice agents, covering architecture, deployment, cost, and the trade-offs that lock you in.

Illustration of an AI judge holding a checklist while reviewing a conversation transcript on a monitor

Technical Guide·22 min read

LLM-as-a-Judge: Build a Production Eval Pipeline

Build a production LLM-as-a-judge eval pipeline step by step. Covers judge selection, rubric design, CI integration, and sampling strategies that scale.

Illustration of distributed trace spans connecting an AI agent to MCP tool servers with observability signals flowing through

Technical Guide·20 min read

MCP Servers in Production: Observability from Day One

Instrument your MCP servers with OpenTelemetry for production-grade observability. Covers tracing tool calls, detecting loops, cost attribution, and alerting.

Person connecting protocol cables between two glowing devices with diagrams on a whiteboard

Learning AI·22 min read

Build the MCP + A2A agent protocol stack from scratch

Wire an MCP server to an A2A agent that delegates tasks and calls tools. TypeScript and Python examples, Streamable HTTP transport, Agent Cards, and auth.

Person sorting through stacks of documents, crossing out wrong ones, with a magnifying glass on the desk

Learning AI·22 min read

Agentic RAG: from dumb retrieval to self-correcting agents

Your RAG pipeline retrieves wrong documents and nobody catches it. Build a self-correcting agent that grades results, rewrites queries, and knows when to stop.

Open-source AI agent testing engine with conversation simulation and scorecard evaluation

Testing & Evaluation·14 min read

We open-sourced our AI agent testing engine

chanl-eval is an open-source engine for stress-testing AI agents with simulated conversations, adaptive personas, and per-criteria scorecards. MIT licensed.

Watercolor illustration of a colorful workspace with a main monitor surrounded by floating screens showing different code, warm plum tones

Learning AI·18 min read read

Claude Code subagents and the orchestrator pattern

How to structure Claude Code subagents, write dispatch prompts, and coordinate parallel work across services, SDKs, and frontends in a monorepo.

Person drawing a web of connected nodes on a glass wall with colorful sticky notes around the edges

Learning AI·22 min read read

Graph memory for AI agents: when vector search isn't enough

Build graph memory for AI agents in TypeScript and Python. Extract entities, track relationships over time, and compare Mem0, Zep, and Letta in production.

Person wearing a headset at a desk with sound waveforms visible on screen, golden amber atmosphere

Learning AI·22 min read

Voice AI pipeline: STT, LLM, TTS and the 300ms budget

Build a real-time voice pipeline with Pipecat. How STT, LLM, and TTS stream concurrently under a 300ms latency budget, with turn detection and interruptions.

Developer comparing AI agent framework options on a split-screen monitor

Agent Architecture·18 min read read

AI Agent Frameworks Compared: Which Ones Ship?

An honest comparison of 9 AI agent frameworks (LangGraph, CrewAI, Vercel AI SDK, Mastra, OpenAI Agents SDK, Google ADK, Microsoft Agent Framework, Pydantic AI, AutoGen) based on what developers actually ship to production in 2026.

Engineering team reviewing real-time AI agent monitoring dashboards with metrics and conversation traces

Learning AI·22 min read read

Build an AI Agent Observability Pipeline from Scratch

Build a production observability pipeline for AI agents using TypeScript and the Chanl SDK. Covers metrics, traces, quality scoring, drift detection, and alerting.

Visualization of an AI agent context window filling up with system prompts, tool definitions, and conversation history

Learning AI·20 min read read

Your AI Agent's Context Window Is Already Half Full

System prompts, tool schemas, MCP descriptions, memory injection, conversation history. They all eat tokens before the user says a word. Learn where your context budget goes and how to manage it.

1...7 8 9...20

Learn Agentic AI

Weekly. Patterns for shipping agents that work — MCP, scorecards, regression tests, prompts, model comparisons.

500+ builders subscribed