agentstack.dev

Exploring the future of AI 🤖 • Sharing experiences in building, top news and trends in AI 🚀 • Early DeFi plays 📆 • Airdrop strategies 🪂

[agentstack.dev @agentstack_dev]

@antigravity Looking forward to test.

[agentstack.dev @agentstack_dev]

@msdev Looking forward to it.

[agentstack.dev @agentstack_dev]

@LoopandPixels AI. Let’s connect 🤝

[agentstack.dev @agentstack_dev]

@TechWithAmar AI. Let’s connect 🤝

[agentstack.dev @agentstack_dev]

@MicrosoftLearn AB-100 is already on the list 📝

[agentstack.dev @agentstack_dev]

@RoundtableSpace Yes, for two prompts. —> limit reached 🙈

[agentstack.dev @agentstack_dev]

@msdev @code 7.5x is Crazy

[agentstack.dev @agentstack_dev]

@_catwu Great! Good decision 🤝

[Boris Cherny @bcherny]

Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7 🧵

[agentstack.dev @agentstack_dev]

@ClaudeDevs @bcherny @dpunkt

[Boris Cherny @bcherny]

Opus 4.7 is in Claude Code today. It's more agentic, more precise, and a lot better at long-running work. It carries context across sessions and handles ambiguity much better.

[agentstack.dev @agentstack_dev]

Deliberate access is what makes enterprise AI useful, safe, trusted, and reliable.

[agentstack.dev @agentstack_dev]

today learning snack is about Security and Permissions: Agents are only as good as their access model.

They should only use the data and systems they’re explicitly allowed to access.

That’s what makes them useful, safe, and reliable.

#AIGovernance #AISecurity #Copilot #EnterpriseAI

[agentstack.dev @agentstack_dev]

Before deployment, companies should define the agent’s role, map minimum required access, apply governance controls, and monitor behavior.

[agentstack.dev @agentstack_dev]

@shubhanalytics RAG. Let’s connect 🤝

[agentstack.dev @agentstack_dev]

Quick question:

What agent platform is your company actually using today?

Copilot Studio, n8n, LangGraph, custom internal tooling, or something else?

Curious what is showing up in real enterprise environments.

#AgentPlatform #buildinpublic #enterpriseai

[agentstack.dev @agentstack_dev]

Mistakes 5+6: No owner, wrong expectations + what strong design requires

[agentstack.dev @agentstack_dev]

Todays learning snack topic: Common mistakes when building Agents

Most weak @Copilot Agents do not fail because the idea is bad.

They fail because the design is weak.

Common mistakes:
• vague scope
• unclear purpose
• poor knowledge sources
• weak workflow fit
• unclear ownership
• trying to make the agent do too much

A good agent is not broad by default.

It is clear, focused, and designed around a real job to be done.
#M365Copilot #AIAgents #GenAI #EnterpriseAI

Detailed slides below 👇

Overview here:

[agentstack.dev @agentstack_dev]

Mistake 4: Trying to do too much at once