←
Rod Johnson5,466 posts
Rod Johnson avatar

Rod Johnson

@springrod

Building the future of agent frameworks at Embabel. Creator of Spring. Developer, Entrepreneur, Investor, Author. linkedin.com/in/johnsonroda/

◷ Joined April 2009▧ 106 Photos and videos
Rod Johnson avatar
Rod Johnson@springrod·Nov 8

Gartner cites AI context platforms among the top strategic technology trends. "Gartner predicts that by 2027, organizations that prioritize semantics in AI-ready data will increase agentic AI accuracy by up to 80% and reduce costs by up to 60%." We agree worlds.embabel.com

Rod Johnson avatar
Rod Johnson@springrod·Nov 7

Great piece @iRomin. Google Knowledge Catalog is a nice option for the meaning layer, and we're adding an integration to Embabel Worlds. Interested in an Embabel version of Chai & Co, with the same Google services underneath?

How can you make it easier for builders to do the right thing? Earlier this week, @springrod published a post on governed context layers (medium.com/@springrod/vibe-c…). Read it. @iRomin took that idea and built a safe context layer in @googlecloud. Read it. medium.com/google-cloud/safe…

Rod Johnson avatar
Rod Johnson@springrod·Nov 7

"Code mode" is the future. LLMs should write programs vs call many individual tools. Saves context, builds on their training on huge amounts of code, and is a better way to expose business understanding Next question: what language should LLMs code in? medium.com/@springrod/the-gr…

Rod Johnson avatar
Rod Johnson@springrod·Nov 6

Cypher is great. It's awesome for grounding LLM responses. What if it was much bigger than a single database, and you could query anything with it? With Embabel Worlds, you can. Today. New blog about the technical choices in our context layer. medium.com/@springrod/the-gr…

Rod Johnson avatar
Rod Johnson@springrod·Oct 16

Vibe coding can help users build great things without code. But it only works over infrastructure that ensures that apps are deployable, secure, validated, safe and efficient. Embabel Worlds lets users build safely over their knowledge graphs: medium.com/@springrod/a-new-…

Post attachment
Rod Johnson avatar
Rod Johnson@springrod·Oct 16

Code mode is the future of tool calling, allowing LLMs to write programs vs call individual tools. The challenge is to make it safe, through curation, approvals and sandboxing. One role of a context layer is to provide a surface LLMs can code against. medium.com/@springrod/a-new-…

Rod Johnson avatar
Rod Johnson@springrod·Oct 15

Anthropic would have us believe that AI might soon be able to end humanity. Meanwhile, we wait for Claude Code to provide a sane way to copy to the clipboard.

Rod Johnson avatar
Rod Johnson@springrod·Sep 22

Jev is yet more proof that no organization should outsource its AI strategy to a frontier LLM vendor or company that wants to sell tokens LLMs are great, BUT - Open weights models are capable of more & more tasks - AI > Gen AI. You don't always need an LLM @JamesWard @jtdavies

Rod Johnson avatar
Rod Johnson@springrod·Sep 22

We live in a time when products can talk to you to help you learn how to use them. The fact that nearly every enterprise AI product is "call sales for a demo" is a massive product red flag, and helps explain why most enterprise AI fails. This is not the 1990s

Rod Johnson avatar
Rod Johnson@springrod·Aug 21

So not only is Opus 5 a clear regression compared to Opus 4.8, which was itself far more annoying than its predecessors, but in recent days, context compaction has started totally losing the thread.

Rod Johnson avatar
Rod Johnson@springrod·Aug 21

Anybody else seeing occasional Chinese characters mixed into Claude model output? This was from Fable: View YAML syntax and app serving路径