Skip to main content
The AI Breakdown

The Coolest Agents I've Built So Far

20 min episode · 2 min read

Episode

20 min

Read time

2 min

Topics

Career Growth, Remote Work, Investing

AI-Generated Summary

Key Takeaways

  • Agentic shift timeline: The transition from standard AI tools to agent-based workflows accelerated dramatically in the three to four months preceding March 2025, driven by OpenClaw, Claude Code, Codex, and Perplexity Computer. Builders should audit current workflows now and identify which repetitive research, project management, or discovery tasks can be handed to a persistent autonomous agent.
  • Persistent AI strategy over one-time consulting: Rather than deploying AI assessments as periodic engagements, the Mycroft model runs continuously in Slack, updating company-wide AI roadmaps across six vectors: use cases, systems, data integration, outcomes, people, and governance. Organizations can replicate this by assigning a dedicated agent to maintain a living strategy document rather than a static quarterly report.
  • Agent portfolio representation via Chucky: When demonstrating AI-building skills to clients or employers, static resumes and portfolios fall short. The Chucky model deploys an interactive agent that fields questions, surfaces screenshots, links to live tools, and visualizes the full ecosystem of builds. Builders should consider creating a conversational representative rather than a PDF portfolio for client outreach.
  • 24/7 autonomous research as highest-utility OpenClaw use case: The Widi Radars researcher agent runs continuously, scanning studies, surveys, and reports to populate a tiered use-case database categorized as Primetime, Emerging, or Frontier. Teams tracking fast-moving domains like AI adoption should deploy a persistent research agent feeding a structured database rather than relying on manual literature reviews.
  • Power users average 3.5 models simultaneously: Monthly pulse survey data from the AIDB community shows the most active AI users employ an average of 3.5 different models, each selected for specific use cases. Practitioners should map their recurring task types, then deliberately assign the most capable model per task category rather than defaulting to a single general-purpose model for everything.

What It Covers

Host NLW runs 16 of his 2025 AI builds through a March Madness-style bracket tournament, covering agents built with OpenClaw, Claude Code, and Perplexity. Mycroft, a Slack-based digital Chief AI Officer that builds continuous company-wide AI strategy roadmaps, wins the tournament over Chucky, an interactive agent portfolio representative.

Key Questions Answered

  • Agentic shift timeline: The transition from standard AI tools to agent-based workflows accelerated dramatically in the three to four months preceding March 2025, driven by OpenClaw, Claude Code, Codex, and Perplexity Computer. Builders should audit current workflows now and identify which repetitive research, project management, or discovery tasks can be handed to a persistent autonomous agent.
  • Persistent AI strategy over one-time consulting: Rather than deploying AI assessments as periodic engagements, the Mycroft model runs continuously in Slack, updating company-wide AI roadmaps across six vectors: use cases, systems, data integration, outcomes, people, and governance. Organizations can replicate this by assigning a dedicated agent to maintain a living strategy document rather than a static quarterly report.
  • Agent portfolio representation via Chucky: When demonstrating AI-building skills to clients or employers, static resumes and portfolios fall short. The Chucky model deploys an interactive agent that fields questions, surfaces screenshots, links to live tools, and visualizes the full ecosystem of builds. Builders should consider creating a conversational representative rather than a PDF portfolio for client outreach.
  • 24/7 autonomous research as highest-utility OpenClaw use case: The Widi Radars researcher agent runs continuously, scanning studies, surveys, and reports to populate a tiered use-case database categorized as Primetime, Emerging, or Frontier. Teams tracking fast-moving domains like AI adoption should deploy a persistent research agent feeding a structured database rather than relying on manual literature reviews.
  • Power users average 3.5 models simultaneously: Monthly pulse survey data from the AIDB community shows the most active AI users employ an average of 3.5 different models, each selected for specific use cases. Practitioners should map their recurring task types, then deliberately assign the most capable model per task category rather than defaulting to a single general-purpose model for everything.

Notable Moment

The Holmes agent autonomously generates personalized AI tool recommendations for individuals, then updates those recommendations weekly by pulling fresh intelligence from the 221B knowledge hub — creating a self-improving advisory loop without any manual input from the user after initial setup.

Know someone who'd find this useful?

Episode Transcript

16 agents enter the arena. One leaves. Today, we are doing a head by head competition to see what is the coolest thing that I have built with AI so far this year. The AI Daily Brief is a daily podcast and video about the most important news and discussions in AI. Welcome back to the AI Daily Brief. We have got a fun little operator's bonus episode for you guys today. You might have heard me mention over the last couple of days agent madness. The TLDR on this thing is that, one, everyone is building way more agents than we were last year. There has been a massive shift over the last three to four months. It is an agentic shift, and between OpenClaw and Claude code and codex and perplexity computer and all these things, everyone is getting agentified. Two, a lot of the people who are going through that are in this community. Many of you have participated in the AIDB New Year's projects or claw camp or enterprise claw. Many of you are building and sharing things in the AI operators community that goes alongside AIDB. And three, since it is March, the season of March Madness, the big NCAA tournament, one of the coolest sporting events of the year, I thought we would hold our very own bracket to figure out what is the coolest agent that people in this community have built so far this year. Now as I was planning this, I started thinking about just how many different things I had built this year. Not all of them have been fully formed, not all of them have been all that useful, but they've all been, if nothing else, helpful in learning how to use some new tool or learning what isn't quite useful for me right now. So what we've done today is put 16 different things that I've built this year, all vibe coded or AI assisted builds, many agentic, up against each other in our own mini tournament as part of agent madness. I gave both Claude and Chad GPT a list of the projects to seed, and they actually came up with almost exactly the same seeding. The brackets are not divided by theme. Instead, we have a diversity of different types of projects, so we can have some really strong head to heads. When it comes to who or what wins each of these matchups, I'm gonna be ranking it based on a highly subjective concoction that includes technical complexity, usefulness in my daily life, things that I think have value beyond just me, and whatever x factor of I just particularly like the thing. We will keep track as we go through, and ultimately crown a coolest thing that I have built this year so far. You guys are getting a lot of behind the scenes on this one, so buckle up. Starting with bracket a, we have the one versus the eight seed, the Holmes …

Get the full transcript (4,310 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all The AI Breakdown transcripts →

You just read a 3-minute summary of a 17-minute episode.

Get The AI Breakdown summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • Host NLW runs 16 of his 2025 AI builds through a March Madness-style bracket tournament, covering agents built with OpenClaw, Claude Code, and Perplexity.
  • The transition from standard AI tools to agent-based workflows accelerated dramatically in the three to four months preceding March 2025, driven by OpenClaw, Claude Code, Codex, and Perplexity Computer.
  • Host NLW runs 16 of his 2025 AI builds through a March Madness-style bracket tournament, covering agents built with OpenClaw, Claude Code, and Perplexity.
  • by Anthropic

    Host NLW runs 16 of his 2025 AI builds through a March Madness-style bracket tournament, covering agents built with OpenClaw, Claude Code, and Perplexity.
  • The transition from standard AI tools to agent-based workflows accelerated dramatically in the three to four months preceding March 2025, driven by OpenClaw, Claude Code, Codex, and Perplexity Computer.
  • Mycroft, a Slack-based digital Chief AI Officer that builds continuous company-wide AI strategy roadmaps, wins the tournament over Chucky, an interactive agent portfolio representative.
  • Monthly pulse survey data from the AIDB community shows the most active AI users employ an average of 3.5 different models, each selected for specific use cases.

More from The AI Breakdown

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into The AI Breakdown.

Every Monday, we deliver AI summaries of the latest episodes from The AI Breakdown and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime