Who builds an organization's agents: every team, or a central group?

“What the working model that we've used for all of our internal agent development is basically a tripod. It's a GTM engineer, a data scientist, and then the best person, the best subject matter expert in that function. And they sit down shoulder to shoulder and document the best practice for that particular function and then encode that in workflows that ultimately form an agent. We then keep a human in the loop so that human will basically QA the agent. The agent won't be allowed to autonomously execute its action. And then over time as the subject matter expert has less feedback for the agent, we finally pull that person.”

Jeanne DeWitt GrosserChief Operating Officer, Vercel · Executive, Vercel

“We have on-call assistant that begins investigating the moment an incident is declared. We have Testo, a QA-focused agent. Our data team built Ramp research, creating an entirely custom tool set for the agent that's built on top of Inspect's access to our data warehouses. Our product operations team built Voice of the Customer, which synthesizes feedback from all the sources we have access to and compiles reports for teams. These, along with 200 other custom agents, all run on the Inspect's platform.”

Zach BruggemanPrincipal engineer, Ramp · Practitioner, Ramp

“Anyone could build and deploy workflow-specific agents that could use tools. Over 4,000 agents were built using this system.”

Sharadh KrishnamurthyEngineering manager, Agent Foundation team · Leader, Stripe

“Our most successful example of this has been review buddy, our code review agent. It started with engineers on another team hooking up a GitHub webhook to Inspect's API with a review-oriented prompt. They could just focus on making the code review part great while we provided them all the infrastructure to actually run this agent. Now, review buddy runs on every pull request at Ramp, and we've replaced all of our third-party code review tools.”

Zach BruggemanPrincipal engineer, Ramp · Practitioner, Ramp

“I used coding agents to build agents that automated part of my job.”

GitHubPublished by the organization itself (post), no named author

“And so we got a lot of feedback. And then we had a public channel. And so we started getting like all of the engineering managers started using it and asking us if we could like come help them talk about how to do knowledge work for engineering. Our data scientists have one that is like essentially a fork of this. And so we were getting a lot of feedback about what it was good at and what it wasn't good at.”

Ezra MechaberGrowth product manager, Figma · Practitioner, Figma

“We built Agentic MLE, short for machine learning engineer, to take on more of that work. It’s a set of tools and instructions that lets AI agents operate in Stripe's existing ML infrastructure, carrying an experiment from an idea to a result: explore the data, implement a feature, compute its historical values, train a model, and evaluate it against a baseline.”

StripePublished by the organization itself (post), no named author