Sub Agents

“So this is only possible now because sub-agents can hold distinct Personas and argue instead of a model agreeing with itself.”

“I also highly recommend using agent teams. So I'll say always use a team of agents of eight sub agents. And I find the answers are just incredible.”

“My prediction is that initially start off as a sub agent. So whatever you need to go like your tax returns, your personal photos, your emails, your calendar, all that stuff, those local apps, your personal notes, very personal notes. You can make sure that the…”

“And then the other reason to use sub-agents is we want, ah, contexts to be sort of summarized, reduced down at a sub-agent level. That's a really neat boundary at which to compress that rollout and testing into a final message that that agent writes that then…”

“I haven't pulled the data on this, but I would bet the majority of agents are actually prompted by quad today in the form of subagents.”

“There's actually a lot of value in having like multi-turn conversations from like the orchestrator or the assistant to like the sub agent, whereas like, you know, a tool call is basically just like one RPC.”

“Having turn limits and limits on the sub-agents checking and validating their work is super important.”

“A skill is like a written guide that tells, you know, Claude or You know, Codex or ChatGPT exactly how to do a specific task. For example, analyze spreadsheets this way, or write emails in this voice, or design you know, design the interface like this. So you …”

“It's very, very difficult when you have the ability to spin up sub-agents where information is segmented. If you guys know the story of sort of like the builders of the, there's a lot of examples of this in history, but you may, maybe you're building like a py…”

“A lot of the features what we see, you know, where people build like elaborate workflows, like I have my custom slash commands and they trigger custom Custom sub-agents and they in turn trigger custom MCP tool calls behind which again another model is doing in…”

“But I think that the models six or 12 months from now, they probably won't need this anymore because they're all going to be pretty good and you won't have to define very rigidly what each one's responsibilities are anymore.”

“As you are, you know, working in that main chat window, Claude will have These multiple other agents kind of working on the background to identify the other opportunities and things that you should update and fix.”

“You wouldn't want An AGI to jam a 100,000 documents into its context window and take an infinite amount of time to, or some very, very large amount of time to process that. You'd rather use and orchestrate a bunch of sub-agents.”

“You can kind of have this like more general reasoning layer and also a bunch of sub-agents where it, that, That general reasoning layer is actually very specific. It's a specific planner. It's not that good at, like, browsing the web and things like that, but …”