The AI Daily Brief: Artificial Intelligence News and Analysis

The Coolest Agents I've Built So Far

March 14, 2026

AI Summary

5 min read

The host of The AI Daily Brief walks through a personal bracket of 16 AI agents and projects he has built so far this year, ranking them by technical complexity, daily usefulness, broader value, and personal affinity. The exercise reveals a clear pattern: the most compelling agents are not one-off tools but persistent, conversational systems that continuously learn and adapt. The winner, Mycroft, is a digital chief AI officer that builds and updates a company’s entire AI strategy over time.

The Shift from Static Tools to Persistent Agents

The host notes a massive shift over the last three to four months: "everyone is building way more agents than we were last year." The projects in his bracket reflect this. On the low end of complexity are static builds like the AI Daily Brief website (a Lovable site with a terminal theme) or the AIDB New Year self-directed program (a 10-week curriculum that attracted over 7,000 participants). These are useful but not agentic. The more interesting projects are persistent, conversational agents that live in Slack or on the web, continuously gathering information and updating their outputs. The key distinction is between a tool you use once and an agent that keeps working.

The Holmes Ecosystem: Individual and Company AI Advisors

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of The AI Daily Brief: Artificial Intelligence News and Analysis

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **Introduction: Agent Madness Tournament** - NLW introduces a bracket-style competition to determine the coolest AI agent he has built this year, seeded by Claude and ChatGPT.
2 (02:29) **Bracket A: Holmes Agent vs. AIDB Website** - The AIDB website is a simple Lovable-built hub, while Holmes is a personal AI advisor that interviews users and builds case files.
3 (05:49) **Bracket A: OpenClaw Coder vs. Perplexity Research Library** - The OpenClaw coder (Witty Builder) allows vibe coding via Telegram, while the Perplexity build automates AI research aggregation.
4 (07:23) **Bracket A: Chucky (Good Will Hunting Agent) vs. AIDB New Years** - Chucky is an agent that acts as a builder's representative, interactively showcasing a portfolio of built agents.
5 (10:35) **Bracket A: 221B Knowledge Hub vs. Model MOG** - 221B is an agentic knowledge base that ingests transcripts and web searches to power other agents like Holmes and Mycroft.
6 (12:14) **Bracket B: Claw Camp vs. Mycroft** - Claw Camp is a self-directed program for learning OpenClaw, while Mycroft is a digital Chief AI Officer that builds company-wide AI strategy.
7 (13:50) **Bracket B: OpenClaw Chief of Staff vs. Mission Control Center** - The Chief of Staff manages multiple project manager agents, while Mission Control is a central interface for monitoring all agents.

+ Full timestamped outline available in the app

Show Notes

In this Operators Bonus Episode, I pit 16 different things I've built this year against each other in a March Madness-style bracket — from OpenClaw bots and vibe-coded side projects to the Sherlock Holmes-inspired agent ecosystem I'm developing for enterprise AI strategy. It's a behind-the-scenes tour of what's worked, what hasn't, and what I think has the most potential going forward.

Submit to Agent Madness! https://www.agentmadness.ai/

If you want to check out the AI Strategy Agents Mycroft/Holmes I mentioned: https://aidailybrief.ai/ai-strategy-agents