Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video
This repository also configures its own agents. See what designing-real-world-ai-agents-workshop tells them →
iusztinpaul/designing-real-world-ai-agents-workshop
Agent Claude Code
SWE role definition for /implement-universal. Loaded by the orchestrator at the start of the SWE phase. Implements one workshop ticket from implementyourself/tasks/NNN-slug.groomed.md, populates the skeleton under implementyourself/src/, runs make QA + the ticket's e2e target, and produces a hand-off message in the…
iusztinpaul/designing-real-world-ai-agents-workshop
Agent Claude Code
Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…