2 posts tagged with "bmad"

How I Built a UX Team with Claude Code Agent Teams

February 24, 2026 · 16 min read

Senior Software Engineer

TL;DR

Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in .claude/settings.json. Write a command file in .claude/commands/ and spawn prompts in .claude/team-roles/. Type /ux-team and three agents — UX Lead, UX Researcher, UI Designer — run in parallel: researcher defines personas and journeys, designer builds the component system, lead synthesizes into a spec. File ownership is enforced by persona, not by filesystem. BMAD Method v6 provides the Sally persona and a quality-gate checklist that runs before the spec is marked complete.

BMAD Method + Langfuse + Claude Code Agent Teams in Production

February 23, 2026 · 16 min read

Vadim Nicolai

Senior Software Engineer

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.