S2:E10

Building an AI Agent with Subagents and Skills

AI
32 min

Host

Jonny DaenenJonny Daenen

Guest

Jesús García RamírezJesús García Ramírez

Every time you ask AI for help, it agrees. Fast, confident, and it never tells you your plan has holes. That's the problem Arete is built to fix.

Jesus built a brainstorm agent on Claude Code skills that guides you through five phases -- Ground, Explore, Decide, Stress, Ship -- before you commit to anything. The output is an architectural decision record and an implementation plan you actually own.

In this episode he demos it live, shows how parallel subagents work without polluting your main context, and answers the honest questions: tokens burned, vendor lock-in, debugging subagents, and whether this works with a team.

Read transcript →

Chapters

  1. 00:00Intro & meeting Arete
  2. 01:38The 5-step brainstorm workflow
  3. 04:05Meta: This video was made with an AI skill
  4. 06:02The demo: ground, explore, decide, stress, ship
  5. 14:56Example results: ADR and Plan
  6. 17:23Subagents and context engineering
  7. 21:12Demo: the Researcher Agent
  8. 22:48Practical concerns: vendor, files, big projects
  9. 25:30How many tokens does it burn?
  10. 26:51Control, agents vs skills, multi-human
  11. 29:44How to install Arete
  12. 30:44Wrap-up

Tags

Claude CodeAreteAI AgentsSubagentsBrainstormingArchitectural Decision RecordADRContext EngineeringClaude Code SkillsAI Workflow