How Many AI Agents Are Running in Your Company?
How many AI agents are running in your company right now?
Most teams can't give a number. Coding agents, chat assistants and MCP servers spread faster than anyone tracks them.
And you can't manage what you can't monitor. An agent nobody is watching can read data it shouldn't, call tools it shouldn't, or run up a bill. Most of the time the cause is carelessness, not an attacker. This workshop is about what closes that gap.
Brad Cypert is an engineering team lead at Speakeasy, where he works on the AI control plane: the layer that shows how AI is used across a company, defines what each agent can access, and enforces security policy across agents, MCP servers and Skills. He builds this every day, and he'll show how it works under the hood.
The session goes top-down. Brad starts with why agent observability matters and what to measure in a single agent session: cost, duration and risk. Then he goes technical: how one on-device agent can cover whichever AI tools your team uses, and how an AI agent gets its own identity the same way a person in your org does.
You'll walk away with:
The questions to ask about AI agents in your own org, starting with how many you have
What to monitor in an agent session, and which signals point to risk
A clear picture of what can go wrong, including MCP security gaps
A way to decide whether to build agent monitoring yourself or buy it
Come if you are:
An engineer, data scientist or MLOps lead building or running AI agents
A CTO, VP of Engineering or security lead who needs to know what agents are doing
A PM or founder rolling out AI tools across a team
Anyone weighing build vs. buy for agent governance
Want the backstory? Watch Speakeasy COO Hector Hernandez on the TwoSetAI podcast.
Format: 60 minutes, live on YouTube. ~40 min technical deep-dive, ~15 min live Q&A.
About the series
Part of the TwoSetAI Workshop series.
More sessions:
July 17: Why multi-agent systems fail
July 31: Inside AgensFlow
August 14: Token Budgets for Coding Agents
August 28: Self-Improving Agent Loops
September 18: Building A Personal Agent That Actually Works and Sounds Like You
September 25: Behind Navigator n2: The Recursive Training Loop That Made a 27B Model Beat GPT-5.6 and Claude
October 2: How Enterprises Are Actually Adopting AI: From the Boardroom to Bare Metal
October 16: One Person, Many Voices: How to Build Agents That Sound Like a Real Person
October 30: First-Time Founders - Are You Raising? Set a Valuation Cap You Can Actually Defend.
November 13: How Many AI Agents Are Running in Your Company?
December 4: Anyone Can Build. Not Everyone Gets Heard.
December 11: Your AI Agent Is Probabilistic. Its Decisions Don't Have to Be.
See all upcoming sessions: https://twosetai.com/lab/workshops/
About the instructor
Brad Cypert is an engineering team lead at Speakeasy working on the AI control plane, with 16 years of experience building software. He also runs the YouTube channel Code With Cypert.
About the host
Angelina Yang runs TwoSetAI and hosts TwoSetAI and Decoding AI Builders, long-form interview platforms where she's interviewed 100+ AI founders shaping this era. fast.ai fellow. 2024 Anthropic Build Tournament winner. Curates the workshop series and connects the speakers with builders who care.
About Speakeasy
Speakeasy is the AI control plane for enterprises: one governed path between a company's AI tools and everything those tools can reach, with identity, policy, observability and audit built in. The company has raised $22M+, including a $15M Series A led by FPV Ventures with GV (Google Ventures) and Quiet Capital. It shipped one of the first tools to auto-generate MCP servers in early 2025. MoonPay went from no visibility into its AI usage to 200+ governed MCP servers in a 30-day proof of concept, and Speakeasy now governs 60,000+ agent sessions a week there.
Hosted by TwoSetAI.
Past events replay
July 17: Stop Your Agents From Spinning, with Nicole Königstein
July 31: Inside AgensFlow: Design Your Reliability Layer for Your AI Agents, with Nicole Königstein
August 14: Token Budgets for Coding Agents, with Nicole Königstein
August 28: Self-Improving Agent Loops Without Breaking Your Budget, with Nicole Königstein
September 18: Building A Personal Agent That Actually Works and Sounds Like You, with Ahmet İlten of The Sentience Company
September 25: Behind Navigator n2: How did Yutori make AI agents 10x cheaper? With Skanda Vaidyanath of Yutori