Building the future of agent frameworks at Embabel. Creator of Spring. Developer, Entrepreneur, Investor, Author. https://xitter.cf/t.co/IBqJ1rMmFe
Sydney / Bay Area
Joined April 2009
- Tweets5.5K
- Following806
- Followers34.1K
- Likes2.5K
Pinned Tweet
New blog on why a Context Layer is critical AI infrastructure, and announcing Embabel Worlds: an evolving knowledge graph that understands your business.
medium.com/@springrod/a-new-…
The present industry fascination with FDEs is strange.
The consultant->FDE rebranding was brilliant from a marketing perspective. Less so for customers or the wider industry.
Are we really back in the 1990s?
New blog:
medium.com/@springrod/fdes-c…
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-…
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-…
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.
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
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
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.
Anybody else seeing occasional Chinese characters mixed into Claude model output? This was from Fable:
View YAML syntax and app serving路径
Watching an interview with Anders Hjelsberg. Very impressive. Sharp, clear, pragmatic, to the point. Nothing load bearing; no seams; no performative honesty or unlocks.
A reminder that smart humans can achieve a clarity of communication we're increasingly missing. @ahejlsberg
Your regular reminder that Embabel's structure-aware, agentic RAG goes well beyond naive vector search, and is easily extensible to handle custom sources.
See how easy it is to add quality RAG to your JVM apps!
medium.com/@springrod/rethin…
@java #embabel
Nice to see the uptick in star count since Embabel went GA
Remember to star Embabel and the other open source projects you use! One of the easiest of the many ways you can contribute.
Open source community is an amazing thing
@java @springboot
github.com/embabel/embabel-a…
Embabel 1.5.0 has just gone GA, supporting Spring Boot 4.x/Spring AI 2.x
Embabel 1.0 supports Boot 3.x
Whatever your Spring version, you can use our sophisticated workflows, agentic RAG and beautiful fluent API!
github.com/embabel/embabel-a…
@java @springboot @SpringAICentral
Vibe coding UIs can be amazing.
Vibe coding infrastructure software is a recipe for unmaintainable, duplicative, buggy disaster. Agents can accelerate enormously, but must be closely managed.
Good software layering is more important than ever.
Strong paper, and good validation of Embabel's core design of dynamically composing atomic actions into a task-specific execution plan, available since May 2025.
github.com/embabel/embabel-a…
medium.com/@springrod/ai-for…
ICML researchers just published the agent architecture everyone will copy next year.
One shared graph.
A custom workflow for every task.
Here’s the system:
Step 1 → Break workflows into reusable operations
Step 2 → Store them inside one shared graph
Step 3 → Generate the right workflow at runtime
Step 4 → Reuse state instead of rebuilding context
The result:
Better performance across five benchmarks
Around 4× lower memory usage
Most teams are still hard-coding static agent workflows.
This paper shows what replaces them.
Static workflows are the old architecture.
Runtime graphs are the new one.
Bookmark this before every agent team starts building it.
Then read the full graph engineering playbook below ↓
Opus 5 makes more mistakes than 4.8. Period.
Are we in a period of diminishing returns from the frontier model vendors, despite their greater than ever fanfare?