Agent Teams, Not Just Bots - A Human-First Approach to Agentic AI

Unexpectedly, I've been getting a lot of DMs and pings about a blog I pushed recently. So here it is for everyone - the full story behind my agent teams, the security architecture that keeps them safe, and the human-first framework that guides every decision. 🧠

It's Not About One Clever Bot - It's Agent Teams

I don't run a single AI assistant. I run agent teams.

I have a Home Team that handles groceries and schedules. A Work Team that lets me manage AWS infrastructure through natural language. A Self-Upgrade Team that once found our home router was publicly exposed (yes, really 😅). Each team has its own security boundaries, its own context, its own job.

This is the shift I'm seeing everywhere: from monolithic assistants to specialized, orchestrated teams. It's closer to how humans actually work - we don't ask one person to do everything.

Human-First > Automation-First

For individuals, the question isn't "does this make me productive?" - it's "does this give me space to be more human?"

For enterprises, the question isn't "does this trim hours off a workflow?" - it's "does this elevate the entire organisation?"

Same principle, different scale. AI should amplify judgment, creativity, and connection - not just automate tasks. That lens shapes every agent I build.

Security and Governance Is the Real Thing

Melanie (Peiyao) Li's deep dive in the full blog covers a real incident: one user's agent accessed another's conversations. Not theoretical. Real.

The fix? Per-user Firecracker microVM isolation on AWS AgentCore, plus 62 red-team attack scenarios tested on every deploy. Security by design, not as an afterthought.

If you're building multi-agent systems - especially in enterprise settings - this is where the hard work lives. Governance, isolation, auditability. It's not glamorous, but it's what makes agentic AI safe and trustworthy.

What's in the Full Blog

The complete write-up goes deep:

• 🔹 My complete agent team setup - walkthroughs of each team and how they work together
• 🔹 Cost breakdown - spoiler: there's a ~150x price range across models
• 🔹 The full AgentCore architecture for safe multi-tenant deployment
• 🔹 What went wrong in our security testing (and how we fixed it)
• 🔹 A human-first framework for building AI that serves your life, not just your inbox

📖 Read the full write-up here: https://lnkd.in/gJ57QW-U

What Would Your Agent Team Look Like?

If this resonates, I'd love to hear: what would your agent team look like? What parts of your life or work would you delegate to specialized agents? What boundaries would you set?

We're still early in the agentic AI era. The patterns we build now - human-first, secure by design, orchestrated with care - will shape what comes next.

More soon. 🙏

#AlwaysDay1 #AgenticAI #HumanFirstAI #AIAgents #AWS #BedrockAgentCore #MultiAgentSystems #AIGovernance #SecurityByDesign #OpenSource

Resources

• Document