agent

“Oftentimes changing the requirements slightly when the agent is, is hitting a problem might kind of net out a better experience.”

“In beta, we have this product called Agent that does all of that for you. So you don't even have to click, and so you just put your idea there. I will emphasize that it is in early access, so it is still quite buggy.”

“The way agents are built today are kind of a hack. Like it is not really trained to be agentic.”

“It's really like, it's like object-oriented programming for agents.”

“These agents are finally getting to a point where you know, you're, you know, they're, the outcome is, is good. It's quite good.”

“In the future, you would think that a lot of these like agents, so to speak, would come like stock with cursor.”

“So this is the other big unlock with working with agents is that they have a context limit, right? So you know, with Opus, you're looking at about 168,000 tokens. You have to be picking chunks of work that can be fully completed within that context window.”

“People are afraid of like, what if the agent runs by itself? Is it going to go off and do crazy things? And the answer is no, because you gave it a clear user story with clear acceptance criteria, right? It's going to be actually a pretty small thread.”

“This is one of the big unlocks with Ralph or any kind of flow like this is that the agent needs to have a feedback mechanism so that it knows if what it's doing is correct.”

“So you start off with writing a PRD and a PRD thankfully is something that agents are really good at.”

“I think that's one of the very good things for like, Investors in Anthropic, right, is with agents and agents now being, I think probably the new killer feature in Opus. You're going to take whatever token usage and multiply it by the number of agents.”

“Like over, you're going to see over the next two to three months, like some really big winners. And you're going to start to see it work.”

“Now, you don't, you're not going to create software and invite them to the software. You're going to create agents, and you're going to invite them to the agents, and then the agents are going to do work that creates value for these companies. So that's the mi…”

“I really, really, really like working with LLMs as a thinking partner. It's my favorite way of using LLMs. I know people like to use agents and LLMs to build things, but I really like using them to think alongside me.”

“If an agent has that context, you can, it can more effectively give you information about what you should do or not do, or, and it can more effectively make decisions on what should be in your calendar or not in your calendar.”

“Is that writing right now is a big way of how you delegate things to agents. That's like a whole new, that's a whole new aspect of it. So if you can develop a writing habit, You have a lot more context that you can pass over to an agent, which then dramaticall…”

“We should treat models and these agents like very new employees versus like these black magic boxes that like know everything. Right? They know everything because they've been trained on a lot of data, but they don't know your workflow, your steps, right?”

“I think agents are the new SaaS because software is moving from help me do the work to do the work with me.”

“You will be using a software factory. Like, and what I mean is, the agents are going to be writing a hundred percent of your code, reviewing a hundred percent of your code, shipping a hundred percent of your code. Like, that's where we're going.”

“The bigger idea is that agents are going to use the internet in a way software uses infrastructure. So they'll request things, they'll call tools, they'll compare products, they'll retrieve data.”

“There's going to be a new class of citizens on the internet. These are going to be these AI visitors and these AI visitors, these agents are going to book jobs, right?”

“The agents are going to be a commodity at some point. Your judgment about what to Point them to is the moat”