Crewai
Day 34 after signup
3 AI agents and the lines they can’t cross
An oil field, a beverage maker and a pharma company. One rule in common.
Why it works
- Open with a brief editor introduction, then quickly establish the issue’s central idea so readers know what connects the examples.
- Give each case study a distinct real-world setting and explain both the agent’s role and its boundaries to make the technical lessons concrete.
- End by turning the examples into a practical question readers can apply to their own work.
How it is built
- Editor introduction
- Three agent case studies
- Shared design principle
Email copy
View in browser Hi there, I’m Johanna. I’m taking The Context Window over from Sumeru, who built it into something worth your inbox. I'm the Head of Marketing at CrewAI with over 15 years in sales & marketing: Kustomer, Contentful, GoodData, and a first act in finance at Merrill Lynch and JPMorgan. What you’ll get from me: carrying the baton on from Sumeru, filtered through someone who spends most of her week talking to the people actually building agents in production. I’m happiest when a builder is the expert in the room and I’m the one asking questions. Enough about me. Let’s get into it. A few editions ago, we climbed the AI ladder with a founder of a fictional sneaker startup named Steph. It was fun, but this week, I want to do the opposite. Let's look at three agents, built by real teams on CrewAI, that might open your mind around what could be done through AI agents. They come from an oil field, a beverage maker and a pharma services company. These are places where a wrong answer costs real money. They share one trait. In each, plain code does most of the work. The agent gets one narrow job, and a line it can’t cross. That’s how you get to an agent you can trust. On CrewAI, it looks like deterministic Flows for the steps that must always go the same way, and agents only where judgment is needed. Let’s explore: Agent One: The Field Hand An independent oil and gas producer, onshore North America. Lease operators work outdoors, in heavy gloves. They can't use a keyboard. But all day they need well data: test results, how full the tanks are, and whether any alarms are going off. So the interface has to be spoken. The company had already built a prototype that listens, looks things up and talks back. About 4,700 lines of custom code. The question wasn't whether an agent could do this. It was whether a governed runtime on CrewAI could match what they already had. An operator asks a question out loud. A small correction map fixes the oil-field terms that speech models mangle, like MCF and BOPD (gas and oil volume units). One agent with three tools then queries a data warehouse. The agent can only ask the database pre-approved questions. It never writes its own. Spoken well names never match the database exactly. So the system resolves each one to the real name before any query runs. If it's ambiguous, the agent asks. One rule worth stealing: "latest" means the last complete day. The agent skips today's partial numbers, and if it has to fall back, it flags that the value may be incomplete. It also does something the old system couldn't: a half-filled form now survives a restart. It now answers in about 5 seconds, on par with the system they built themselves. Agent Two: The Auditor A global beverage manufacturer. Every third-party seller that distributes this company's drinks needs a valid liquor license. If one lapses, the manufacturer is the one on the hook. The checking was manual, across thousands of sellers. Some licenses expired and triggered fines. Others were renewed far too early, which wasted money. Some sellers were simply left out of the review. The agent handles four situations: a new license, a renewal, a deregistration, or a penalty. Plain database joins find the seller and its license, no model involved. A router then sends each case down one of four paths, and the path comes from the record, not from a guess. Next, a legal agent reads the license documents and the local rules and returns a position: compliant, deficient or unclear, citing the clause it relied on. Then comes the gate. It’s a rule. If required fields are missing or the legal agent's confidence is low, the case can't move forward, whatever the agent concluded. Clean, in-policy cases go through without a person. Anything that needs judgment goes to the accountable owner with the evidence attached. Fees and penalties are calculated and submitted by a tool, not the agent. Every decision lands in an audit trail, with a clo