Running AI agents in a real codebase means solving three intertwined problems at once: planning and quality gates (so agents don't drift), observability (so you know what's working), and orchestration (so multiple agents divide work without clobbering each other). In nomadically.work — a remote EU job board with an AI classification and skill-extraction pipeline — these problems are solved by three complementary systems: BMAD v6, Langfuse, and Claude Code Agent Teams. This article explains how each works and how they compose.

Trigger.dev is a serverless background job platform that lets you run long-running tasks with no timeouts, automatic retries, queue-based concurrency control, and full observability. Unlike traditional job queues (BullMQ, Celery, Sidekiq), Trigger.dev manages the infrastructure — you write TypeScript tasks and deploy them like functions.

This article covers the platform end-to-end: architecture, task authoring, the queue fan-out pattern, MCP server integration for AI assistants, agent skills/rules, and a production case study of a TTS audio pipeline.

We built an Architect agent — a fully autonomous code reviewer powered by Claude Opus 4.6 — that explores a repository, runs audits, and produces a comprehensive architecture report. One command, zero human intervention, a professional-grade review in under 10 minutes.

This article covers how the agent is structured, how it leverages Anthropic's agentic tool-use loop, and what we learned shipping it.

We needed a pipeline that ingests hundreds of job postings from ATS platforms (Greenhouse, Lever, Ashby), enriches each posting with structured data from their public APIs, and then classifies whether a job is a fully remote EU position — all running on Cloudflare's edge with zero GPU costs.

This article walks through the architecture and implementation of process-jobs, a Cloudflare Python Worker that combines langchain-cloudflare with Cloudflare Workers AI, D1, and Queues to build a production classification pipeline.

Introduction​

This article documents a production implementation of OpenAI's Text-to-Speech (TTS) API with automatic chunking for long-form content and seamless upload to Cloudflare R2 storage.

In the rapidly evolving landscape of Large Language Model (LLM) applications, prompt engineering has emerged as a critical discipline. As teams scale their AI applications, managing prompts across different versions, environments, and use cases becomes increasingly complex. This is where LangSmith's prompt management capabilities shine.