Kevin Denman

building

[Kevin Denman @kcdenman]

The Rise of Cybereconomic Smart Agents

📖👇

https://t.co/7cegYsxC7B

[Kevin Denman @kcdenman]

HERMES

[Kevin Denman @kcdenman]

@Shaughnessy119 @NousResearch Your cat is based

[Kevin Denman @kcdenman]

@markvalorian @ChatGPTapp @ajambrosino 20

[Kevin Denman @kcdenman]

@E720Economy @pmarca Don’t lie. The mistakes are real

[Kevin Denman @kcdenman]

@gregisenberg Abundance and Jevon’s paradox for the win!

[Kevin Denman @kcdenman]

@gregisenberg Abundance and Jevon’s paradox for the win!

[Kevin Denman @kcdenman]

down to jam on this.

As the builder network has grown on AgentGraph, I’v spent a lot of time thinking about role definitions and how augmenting human work with agents is disruptive to our current mental model

For example, agentic coding has created the “Product Engineer”

A technical product engineer picks up the coding or an intuitive full stack engineer picks up the product research.

WorkOS has a nice article on Product Engineering https://t.co/dGUvzLJLk3

I also like Agent Engineer (credit langchain) https://t.co/iLZujTrIR1

[Kevin Denman @kcdenman]

If you are building service-adjacent software, make sure it comes with services.

The age of “make one copy of software and sell it to everyone” is coming to an end.

You need to deliver the full stack - enabling software and services.

The software aspect used to be the leverage point, now it’s everything else.

[WillC @willchen500]

Harvey is valued at $11B. Legora just raised at $5.5B. I built their entire web application in two weeks and I'm making it open-source and free for everyone to use. Say hi to Mike: https://t.co/NdtTt5MSJ2.

When I got the chance to try Harvey and Legora, I was surprised by how simple they were. A thought came to mind: I could probably build something similar in no time at all with Claude. And so I did.

Assistant, project, tabular review and workflows. You get it all without vendor lock-in.

Mike offers law firms an alternative, where they own the application layer and aren't stuck with a vendor they're renewing forever.

You can try Mike in the demo on the website, or go to the GitHub link on the site to download the code and run a local version yourself.

[Kevin Denman @kcdenman]

Thoughtful design and implementation of agentic systems is much harder to find than you’d think.

The AGI-pilled think the work just magically happens.

The real builders understand that agentic systems need to be thoughtfully designed with business process, existing systems integration, and workforce change management as major factors.

The foundations of the agentic enterprise are not the agents as much as they are the enterprises ability to empower agents to add value.

As they say, ask not what Claude can do for you, ask what you can do for Claude.

[Ayman Al-Abdullah 🧱 @aymanalabdul]

Getting requests from clients for real AI implementation partners.

All I'm finding are Vibe Code Bros or Zapier shops.

I want firms that:
• Diagnose the actual business problem
• Bring PMs + Product + AI talent
• Build + integrate into real workflows
• Care about security and stability
• Ship and iterate

Who’s best in the world at this?

[Kevin Denman @kcdenman]

@mattpocockuk @mattpocockuk this is great. I've been playing around with ephemeral sandboxes inside of Daytona using the Mastra framework

It feels like the missing piece is putting the coding into a robust harness

In your framework, should I think about "agent: codex()" as the harness?

[Kevin Denman @kcdenman]

Thanks @grinich

I’ve been looking for more writings like this.

Agentic coding (and many other AI agent use cases) have fundamentally shifted working patterns in tech.

Product engineering is a really succinct way to take two roles that used to be decoupled and show how AI Agents can now enable one person to address the full spectrum of product and engineering in a single role.

[Kevin Denman @kcdenman]

@shl Agentic coding makes this possible. @AgentGraphAI thesis is that elite agentic engineers with proper context can outcompete large implementation teams. Let’s go!

[Kevin Denman @kcdenman]

Cursor may be the most import RL environment there is right now.

[Michael Truell @mntruell]

We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution.

Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days.

This suggests that our technique for scaling agent coordination might generalize beyond coding.

[Kevin Denman @kcdenman]

@frankdegods If it’s not open source it’s not comparable to OpenClaw

[Kevin Denman @kcdenman]

I could not emphasize this enough to builders.

I’m about 3000 hours in to agentic coding.

If your product (API / CLI / MCP / Docs / Templates) can’t talk to my agents it won’t get into the stack.

Edge cases: writing C++ directly on Ethernet cables to optimize AI throughput

[Aakash Gupta @aakashgupta]

Karpathy is telling you something most product teams haven’t internalized yet.

The new distribution channel for software is agents. Agents don’t browse your marketing site, watch your demo video, or click through your onboarding flow. They call your CLI. They hit your MCP server. They read your docs programmatically. If none of those surface areas exist, your product is invisible to them.

Look at how fast this moved. MCP went from zero to 97 million monthly SDK downloads in twelve months. 10,000+ active servers. OpenAI, Google DeepMind, Microsoft, and Cloudflare all adopted it. By December 2025, Anthropic donated MCP to the Linux Foundation because the standard had already won. Running an MCP server is now compared to running a web server.

That’s the new baseline for product discovery.

85% of enterprises are expected to have AI agents deployed. Those agents need structured, programmatic access to your product. They need CLIs, MCP endpoints, and machine-readable documentation. A beautiful React dashboard is worthless to an agent trying to pull data into a workflow at 3am.

This tells you everything about why Karpathy’s framing of CLIs as “legacy” technology is so precise. Legacy means battle-tested, standardized, universally parseable. stdin/stdout, flags, JSON output. The entire Unix philosophy was accidentally designed for AI agents decades before they existed.

Your competitor ships an MCP server and suddenly every Claude Code user, every Cursor session, every autonomous workflow can discover and use their product. No human ever visits the website. No sales call. No onboarding email. The agent just finds the tool and starts using it.

The companies that win the next 24 months are the ones building agent-accessible surface area right now. The ones that lose are still optimizing their landing page above the fold.

[Kevin Denman @kcdenman]

@MbBrainz congrats on the launch @MbBrainz ! looking forward to trying it out

[Kevin Denman @kcdenman]

Did agentic coding break @github ?

[Kevin Denman @kcdenman]

@DataChaz @ollama What machine do you recommend for this?

[Kevin Denman @kcdenman]

@tom_doerr Can this be added on to an existing memory system for the learning capability or are you required to implement it as the core memory architecture

[Kevin Denman @kcdenman]

👍 agree with you here

The idea that advanced technology is going to create generation of less capable people is short sighted.

This has never happened- ever.

Advanced technology, like LLMs and Coding agents, will be the tools that are used to build incredible things and the “mental models” will be very human indeed

[Kevin Denman @kcdenman]

@boardyai @rauchg Don’t be such a sensationalist