---
title: "Coinbase's CEO Runs 3 Tiers of Agents"
url: https://nativefirst.ai/blog/coinbase-ceo-three-tiers-of-agents/
description: "Brian Armstrong runs a chief of staff agent over lead agents over sub-agents. He named the tiers and no counts. Hiten Shah agreed a day later."
author: John Tan
category: "AI Workflows"
published: 2026-11-08
updated: 2026-11-08
publisher: nativefirst.ai
format: Markdown copy of the web page at the url above, same text.
---

# Coinbase's CEO Runs 3 Tiers of Agents. A chief of staff sits on top.

He gave the shape and skipped every number.

John Tan · November 7, 2026 · 3 min read

Almost every description of an agent workflow comes from somebody selling agent workflows. This one came from the chief executive of a public company, describing his own week, with nothing attached to buy.

> "I've changed how I work over the last few weeks. I now have **one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them.** Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members."
>
> **Brian Armstrong** · CEO of Coinbase · [November 7, 2026](https://x.com/brian_armstrong/status/2119112609223827547)

Read the structure rather than the enthusiasm. There are three tiers, and each one has a different job.

## It is an org chart

At the top, a chief of staff agent whose work is oversight rather than output. Below it, one lead agent per area of focus, and the load-bearing phrase there is **running all the time**. Not opened, prompted and closed. Standing. Below those, sub-agents doing the work that has a definition of done: writing code, testing it, chasing reviews, coordinating with the humans.

That has a span of control, a delegation boundary and an escalation path. It was not designed by an engineering team and handed upward. It was designed by the person at the top, which is the part worth noticing, because the usual failure of AI inside a company is that the people who pick the tools have no authority over how the work is organised.

**Figure 1. Brian Armstrong's structure · Three tiers, and only the bottom one does the work.**

HOW MANY Chief of staff agent 1 Lead Lead Lead one area of focus each, always on not stated write code · test it · chase reviews · coordinate not stated HOW MANY Chief of staff agent 1 Lead Lead Lead not stated one area each, always on write code · test it chase reviews · coordinate not stated

Every label is Armstrong's own word, from his post of 7 November 2026. He gave a count for the top tier only.

## The operating rules he left out

Armstrong gave the shape. The next day Hiten Shah quoted him and supplied the part a reader can actually copy: the rules his own team has run this way since February.

> "Your coding agents should have a manager. **That manager should be a coding agent.**"
>
> **Hiten Shah** · Founder, 20 years in SaaS · [X · November 8, 2026](https://x.com/hnshah/status/2119464781459710450)

Shah's version, in five rules:

1. **One lead agent per project.** It holds the plan, remembers the decisions, delegates, and knows what is stuck.
2. **Task agents work in parallel under it.** They take questions back to the lead, not to you, and report results there.
3. **Agents show the work.** Screenshots, live pages, the alternatives they considered, and what changed since the last round.
4. **One review queue for the human.** Everything that needs judgment lands in a single place, where you approve, request changes or give feedback, and the answer routes back to the agent that asked.
5. **Feedback stays open until it is handled.** Changes are tested before they land, merges get a second opinion, and risky changes need approval.

Two days later Anthropic published a run that shows what that layer is for: [1,000 agents went flat at 86% and only finished because somebody restarted them](https://nativefirst.ai/blog/fable-52-fermat-1000-agents/).

Rule four is the one that makes the hierarchy pay. Without it, every agent interrupts you directly and the org chart is decoration. With it, the human stops supervising agents and starts reviewing finished work.

It converges on a hierarchy for the same reason companies did. A single agent handed everything runs out of context and out of attention, and the work it drops is invisible because nothing is watching it. Splitting by area and putting something above it to arbitrate is the cheapest available fix. Organisations of humans found that answer too, and for the same reason.

## Copy the design, not the claim

Treat this as a shape to borrow rather than a result to cite. The pattern it names has appeared in this Playbook twice already, from operators rather than executives, and it keeps resolving the same way: [something has to sit above the agents](https://nativefirst.ai/blog/grok-bot-chief-of-staff/), and the thing that sits above them works best when it is also an agent.

What changed on 7 November is who said it. Not a founder of a tools company, not a researcher, not an anonymous thread. The chief executive of a listed company, describing the way he personally works now, in four sentences with an org chart inside them.

So the useful question is not how many agents you are running. It is whether anything sits above them, whether there is one queue where their work reaches you, and whether you could sketch the result on one page.

**Draw the org chart.**

[John Tan ↗](https://www.linkedin.com/in/johntans/)

Founder of nativefirst.ai. Runs everything on agents and writes down what works.

Sources

1 Brian Armstrong, X, 7 November 2026, quoted verbatim: one lead agent per area of focus running all the time, a chief of staff agent overseeing them, and sub-agents under each lead that write code, test it, chase reviews and coordinate with team members. No counts, costs or outcomes were stated.

2 Hiten Shah, X, 8 November 2026, quoted verbatim. Posted as a quote of Armstrong's, so it is a response to it rather than independent corroboration.

3 Perplexity figures as covered in this Playbook's edition of 5 November 2026.
