News for hackers. Stuff that matters.
Re:Ask HN: What's your current AI agentic setup? by kuboble on Thursday November 05, 2026 @02:03AM (#50376058)
> I do not like terminal tui much as I think it's a poor fit for a coding agent

I recently moved away from using tui to directly interact with claude code.

I still start a session in the terminal but then ask to start a simple jira- like ticketing system.

When I have a request I start a new ticket and claude decides to either do it or launch a sub agent to do it.

When claude is done or has questions- he replies in the ticket. When claude has a side-findings he creates a new ticket for me.

Re:Ask HN: What's your current AI agentic setup? by mickeyp on Thursday November 05, 2026 @03:21AM (#50376582)
That's a really interesting workflow.

I also do orchestrator like work that way. The key difference is I'll have a master chat and let it delegate work as needed to sub agents.

I have skills, MCP etc for things that need it, and custom-designed sub agents for a couple of very specific, niche tasks. The rest use generic delegator, explorer, worker sub agents that just take normal instructions.

Re:Ask HN: What's your current AI agentic setup? by aspect0545 on Thursday November 05, 2026 @05:16AM (#50377422)
So does it develop a new ticket system every time? I'm not sure I can follow, could you explain?
Re:Ask HN: What's your current AI agentic setup? by kuboble on Thursday November 05, 2026 @04:32PM (#50384746)
Yes, I have one instance of it per project. And there run only one claude code session that is only supposed to manage "jiraude" and run the actual work in subagents. I published it at https://github.com/kuba97531/jiraude