On day two I said something that I thought was probably too ambitious:

Me: "I want to setup research swarm"

I'd seen the term somewhere online — the idea of multiple AI agents working in parallel on a task. I wasn't sure exactly what I was asking for, but I knew I wanted to stop manually checking financial news every morning before the market opened.

By the end of that session, I had five named agents, a message pipeline, and a scheduled 6 AM delivery. Here's what got built.

The Five Agents

My AI assistant spun up the following agents, each with a distinct role:

  • AIResearcher — monitors AI and tech news overnight, surfaces anything relevant to markets
  • TechResearcher — digs into specific tech stories (zero-days, product launches, regulatory news)
  • FinanceCrawler — scrapes pre-market data, earnings reports, Fed statements
  • OvernightAnalyst — synthesizes what FinanceCrawler and TechResearcher found into a coherent picture
  • StockPicker — reads the OvernightAnalyst's output and produces 3-5 specific trade ideas with rationale

These aren't chatbots you have to prompt. They're persistent agents that wake up on a schedule, do their job, hand off to the next agent in the chain, and send the final output to me — automatically.

The Pipeline

The message flow runs like this: FinanceCrawler and TechResearcher work in parallel overnight, both feeding into OvernightAnalyst. OvernightAnalyst synthesizes and sends to StockPicker. StockPicker sends me the morning brief.

It's a hand-off chain. Each agent has a specific job and passes its output downstream. No one agent has to do everything, so each can do its part well.

What surprised me
Each agent builds its own memory over time. After a week, StockPicker had learned which sectors I was most interested in, which news sources tended to produce actionable signals, and which types of picks I'd followed up on. The briefings got noticeably sharper.

What a Morning Brief Actually Looks Like

A typical 6 AM delivery includes: overnight macro developments (Fed speakers, international market closes, commodity moves), 2-3 tech/AI stories with market implications, and 3-5 stock picks with a one-paragraph rationale for each. The whole thing takes about two minutes to read.

Is it perfect? No. But it's better than starting my morning cold with no context. And it's free — the research swarm runs on its own while I sleep.

What This Made Me Realize

The hard part of building this wasn't technical — it was knowing what I wanted. Once I could describe the workflow ("overnight research → synthesis → picks delivered before market open"), the implementation was straightforward. The bottleneck was articulating the goal clearly enough for an agent to execute it.

That turned out to be a theme across everything I built in the weeks that followed.