• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Reaction

Kylon launches a ‘company harness’ for people and AI agents

A Kylon angel investor says databases behind agent-created Apps are powered by Databricks Neon.

François CholletFC
Jonathan FrankleJF
Yuchen JinYJ
5 Sources, 1h ago, first seen 1h ago

TLDR

A Kylon angel investor describes the launch as a ‘company harness’ designed to help people and AI agents work as one team, arguing that agents need more context about a business. The investor says databases behind agent-created Apps are powered by Databricks Neon. Another angel investor says managing agents with multiple people is harder than managing them solo.

Combined views

—

5 Sources, first seen 1h ago

— likes— comments— saves— reposts

Combined views

—

5 Sources, first seen 1h ago

— likes— comments— saves— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

5 Sources

Yuchen Jin@Yuchenj_UWExcited to see Kylon launch! Co-founded by 2 friends from my college, Kylon is building a “company harness” that lets humans and AI agents work as one team. AI doesn't have an intelligence problem. It has a context problem. Imagine if AI agents knew everything about your company and business. They will become incredibly powerful teammates. One feature I particularly love is Apps. All the databases behind Apps created by agents are powered by Databricks Neon! (Disclosure: I'm a small angel investor in Kylon. I don't do many angel investments, but I really like this product, and it's been incredible watching this small team move so fast over the past 6 months, they're running their entire company on Kylon. Huge congrats on the launch!)1h
Jonathan Frankle@jefrankleThere are plenty of single-player ways of managing agents. Multi-player is much harder. Thankfully, there's Kylon. So excited for @quinn_leng and the entire Kylon team! Quinn was an amazing @databricks researcher, and I'm proud to still be his teammate as an angel.1h
Chubby♨️@kimmonismusI've met the founds in SF and we had dinner together. They explained Kylon to me in detail and it sounded awesome: Kylon brings your team and agents such as Claude Code and Codex into the same workspace! Shared conversations and files give people and agents context as they take over different steps. The team says its memory system summarizes older conversations while keeping the original messages available to retrieve. I've been testing @kylon_ai with sample editorial workflows. When a newer source corrected a newsletter claim, its agent created v2 and kept the original source and v1 intact. That made the change easy to review without losing the earlier work. Super interesting claims and from my testing they hold up. Congrats on that launch!1h
François Chollet@fcholletIf an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments because they lack the context of what the team already discussed and decided. The Kylon app fixes this by running Claude Code and Codex in a shared, multiplayer environment. Agents gain real-time visibility into team consensus and architecture decisions.1h
elvis@omarsar0Pay close attention to harnesses, part 2. Last week I shared a paper where a model more than doubled its score after training inside the harness it runs in. The same idea applies at a higher level. Claude Code and Codex are harnesses for a model. Once a team runs several agents, the company also needs a harness for its people and agents. Kylon is building that layer. You bring the agents your team already uses, like Codex and Claude, into shared rooms where they work alongside everyone.55m
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    5 Sources

    Yuchen Jin@Yuchenj_UWExcited to see Kylon launch! Co-founded by 2 friends from my college, Kylon is building a “company harness” that lets humans and AI agents work as one team. AI doesn't have an intelligence problem. It has a context problem. Imagine if AI agents knew everything about your company and business. They will become incredibly powerful teammates. One feature I particularly love is Apps. All the databases behind Apps created by agents are powered by Databricks Neon! (Disclosure: I'm a small angel investor in Kylon. I don't do many angel investments, but I really like this product, and it's been incredible watching this small team move so fast over the past 6 months, they're running their entire company on Kylon. Huge congrats on the launch!)1h
    Jonathan Frankle@jefrankleThere are plenty of single-player ways of managing agents. Multi-player is much harder. Thankfully, there's Kylon. So excited for @quinn_leng and the entire Kylon team! Quinn was an amazing @databricks researcher, and I'm proud to still be his teammate as an angel.1h
    Chubby♨️@kimmonismusI've met the founds in SF and we had dinner together. They explained Kylon to me in detail and it sounded awesome: Kylon brings your team and agents such as Claude Code and Codex into the same workspace! Shared conversations and files give people and agents context as they take over different steps. The team says its memory system summarizes older conversations while keeping the original messages available to retrieve. I've been testing @kylon_ai with sample editorial workflows. When a newer source corrected a newsletter claim, its agent created v2 and kept the original source and v1 intact. That made the change easy to review without losing the earlier work. Super interesting claims and from my testing they hold up. Congrats on that launch!1h
    François Chollet@fcholletIf an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments because they lack the context of what the team already discussed and decided. The Kylon app fixes this by running Claude Code and Codex in a shared, multiplayer environment. Agents gain real-time visibility into team consensus and architecture decisions.1h
    elvis@omarsar0Pay close attention to harnesses, part 2. Last week I shared a paper where a model more than doubled its score after training inside the harness it runs in. The same idea applies at a higher level. Claude Code and Codex are harnesses for a model. Once a team runs several agents, the company also needs a harness for its people and agents. Kylon is building that layer. You bring the agents your team already uses, like Codex and Claude, into shared rooms where they work alongside everyone.55m
    Today's Rank

    #5

    Today's Rank

    #5