Загрузка видео...

Не удалось загрузить видео

На главную

Made a UI to visualize multiple AI agents playing as different civilizations, each navigating its own decision tree Most agent workflow UIs are pretty static, so I wanted to build something that feels more dynamic and fun to explore

124,083 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 47

Фото профиля XIN Chen
XIN Chen3 месяцев назад

For Drug Design

Фото профиля Mikhail Kashkin
Mikhail Kashkin3 месяцев назад

UI is sleek and beautiful, love it!

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Mikhail

Фото профиля Nick Venturi
Nick Venturi3 месяцев назад

basically a digital ant farm 🤤

Фото профиля mars
mars3 месяцев назад

this is so cool!

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks

Фото профиля Matthieu Talbot
Matthieu Talbot3 месяцев назад

Il me faut ça, pour ma vie; je parle à mon agent le soir, et à la fin de la semaine il me fait un récap en mode Civilisation Tech Tree.

Фото профиля gil
gil3 месяцев назад

Like others have said, this is very well thought out and makes me realize I’ve been lazy in my UX approach to drawing graphs. I don’t have to just take vue flow ootb. Well done.

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks!, That's why I choose topics like these for my demos. When working with real data, it gets boring pretty quickly, so there are definitely times when I also just use whatever's available ootb and call it a day

Фото профиля Sofiia Matsiutsia
Sofiia Matsiutsia3 месяцев назад

this is genius 🤌

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Sofiia!

Фото профиля niccomi 🧙‍♂️
niccomi 🧙‍♂️3 месяцев назад

civ gamers will rejoice

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

it is heavily inspired by the civ tech tree🙂

Фото профиля KS
KS3 месяцев назад

What was your approach for this? I'm doing something similar for my custom dashboard/mission control but I've found throughput tanks as soon as I ask for custom graphical assets, textures etc.

Фото профиля Dillon
Dillon3 месяцев назад

Age of Agents

Фото профиля ChronoAI
ChronoAI3 месяцев назад

This is the same idea we built consensus-loop around — different agents playing different roles, sealed from each other, meta-judge converges. Got it running 24/7 on real repo issues now: solvers + reviewers actually ship PRs and releases on their own.

Фото профиля SecWay
SecWay3 месяцев назад

有意思,值得欣赏

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

谢谢

Фото профиля hlitoroy (opinion arc)
hlitoroy (opinion arc)3 месяцев назад

another ai slop

Фото профиля Saaga
Saaga3 месяцев назад

Really cool UI

Фото профиля 🤖 🇺🇸 ²
🤖 🇺🇸 ²3 месяцев назад

Love this! Any chance you’d release it for others to try?

Фото профиля Crazyox🌶️(微微辣版)
Crazyox🌶️(微微辣版)3 месяцев назад

这个好玩,如果你能让硅基文明和碳基文明交汇并且自然发展出多种结局,我真的会想看。

Фото профиля Quinn Favo
Quinn Favo3 месяцев назад

Pretty cool!

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks

Фото профиля Brandon Bartlett
Brandon Bartlett3 месяцев назад

This is pretty cool. I had a similar idea. Making it like what happens if this or that choice is made then what the downstream effects are

Фото профиля Trog
Trog3 месяцев назад

Thats pretty cool. Want to teach a man to fish?

Фото профиля Matt Nicosia
Matt Nicosia3 месяцев назад

This is awesome

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Matt

Фото профиля 0XNEET
0XNEET3 месяцев назад

Really love your content. It's so inspiring

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks

Фото профиля Leo Ge
Leo Ge3 месяцев назад

Cool!!!

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Leo

Фото профиля leolee
leolee3 месяцев назад

This is the kind of UI that makes agent systems feel less like dashboards and more like a world you can actually read. The civilization framing is smart too — it gives each agent a clear identity instead of a pile of nodes doing random stuff. Static workflow UIs get old fast. This feels easier to explore, and probably easier to debug when things go sideways. Nice balance of useful and fun 🔥

Фото профиля Tyler Mayberry
Tyler Mayberry3 месяцев назад

This is really cool making me come up with a lot of new ideas.

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Tyler!

Фото профиля Yann André
Yann André3 месяцев назад

I love that. 👍🏻

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks Yann

Фото профиля Thành
Thành2 месяцев назад

This is the coolest agent

Фото профиля AI Mastery Guide
AI Mastery Guide3 месяцев назад

Visualizing agent decision trees as a live civilization map makes multi-agent workflows actually fun to watch unfold 🗺️

Фото профиля Pan's
Pan's3 месяцев назад

really cool

Фото профиля Bruno Serrate → postyourmind.com
Bruno Serrate → postyourmind.com3 месяцев назад

Pretty cool UI. This could be easy a UI game or something lol

Фото профиля Dilum Sanjaya
Dilum Sanjaya3 месяцев назад

thanks, it is inspired by Civilization games

Фото профиля Samian
Samian3 месяцев назад

visualizing the decision tree branching in real time would be the win. like actually seeing each agent weigh its options before committing, not just the final move

Фото профиля Dr. Xi Zeng
Dr. Xi Zeng3 месяцев назад

The agent map is the right instinct. Most workflow screens make agents look like boxes waiting in line. A game-like view can show the part users need: which agent saw what, chose what, and got stuck where.

Фото профиля paleocybernetic
paleocybernetic3 месяцев назад

oh my gosh please open source so I can update my AI advisor council with this

Фото профиля Gene
Gene3 месяцев назад

Mmm interesting

Фото профиля Harley Lewis Foote
Harley Lewis Foote3 месяцев назад

Looks fun. Most agent UIs still feel like a spreadsheet with extra steps.

Похожие видео

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,758 просмотров • 1 год назад