Raphael De Lio

youtube.comRuntime Data for AI Agents with Redis Context RetrieverYouTube video by Coding with Raphael De Lio

4 Sept

New forward deployed engineer video: In this one, I explain how Spark prepares Snowflake data in Redis and how Redis Context Retriever exposes it to agents through generated MCP tools with access control. www.youtube.com/watch?v=TtII...

youtu.beOpenClaw Is Going Enterprise (RFC 27) + Redis Agent File SystemYouTube video by Coding with Raphael De Lio

28 Aug

OpenClaw is defining an enterprise architecture through RFC 27. In this video, I explain the proposed model and where Redis Agent File System fits as persistent workspace storage for disposable Kubernetes compute. youtu.be/LfdsN1qcekY

28 Aug

OpenClaw Enterprise RFC: github.com/openclaw/rfc... Redis Agent File System: github.com/redis/agent-...

31 May

Experimentations with Spring AI. Multi agent architecture with streaming of what the agent is actually doing while running. #javabubble

31 May

The live agent activity stream is possible thanks to NDJSON (Newline Delimited JSON) where each event is sent as an individual JSON object separated by a newline. Allowing the UI to display agent thoughts, tool calls, and intermediate results as they happen without waiting for the workflow to finish

26 May

AI engineering means designing the context, runtime, and harness around agents so they run reliably, observably, and at scale. In my Redis webinar on May 28, I’ll focus on harness engineering: caching, session management, and rate limiting. RSVP: redis.io/resources/vi...

redis.ioSession management, caching, & rate limitingSolves common real-time application workloads; personalization, search, fraud detection, session management, and AI context.

21 May

Harness engineering is the buzzword of 2026. But the ideas behind it are decades old. Turns out that building scalable agents still requires the same systems engineering skills software engineers have relied on for years to build scalable and sustainable systems. redis.io/resources/vi...

20 May

OpenAI dropped a tool to verify if an image has been AI generated. And LinkedIn is already using it to tag images that were AI made. The technology is grounded in two mechanisms. One that relies on metadata. Another that relies on imperceptible pixels. Read more: openai.com/index/advanc...

Raphael De Lio reposted

Codetaur

@vibe-coded.com

18 May

real software is still so much work wtf

Raphael De Lio reposted

Martijn Smit

@lostdomain.org

13 May

yes. just, yes. 🧑‍🍳

Andras Bacsai@heyandras.dev

We made a fake repo with fake bounties, and the bots are applying fake PRs, so we know who is fake, and we can ban them from the Coolify repo. IQ over 1000

13 May

Happy to announce that I'm returning as the host of the Dutch Kotlin User Group in Amsterdam after a year and a half hiatus!

12 May

I love when users find bugs in my products. It means the product is actually being used.

6 May

Only country in western Europe where internet works reliably: the Netherlands

2 May

Bought more shares of Duolingo yesterday. I had previously bought it when learning Dutch a couple years ago and decided to do so again that I’m learning Japanese. Practicing something like one hour a day during a week and I can already read Hiragana. Love this app.

I’m addicted to seeing how much energy I’m consuming/producing in realtime. I spend more time on this app than any social media 😂 @zonneplan.bsky.social

1/9 If a service commits something to a database and then publishes a message to Kafka, what happens if the database commit succeeds but the Kafka publish fails? This problem has nothing to do with AI. But the mindset behind solving it matters a lot for AI agents.

8/9 This does not mean machine learning does not matter. It absolutely does. Machine learning engineers understand model behavior, evaluation, uncertainty, drift, and failure modes. That expertise is critical.

9/9 But software engineers should not feel like outsiders in AI. If you know how to make unreliable systems behave reliably in production, you already understand one of the hardest parts of building AI agents. Agentic applications need both systems expertise and model expertise

6/9 This is what people are starting to call harness engineering. Harness engineering is the deterministic system you build around the model. The workflows. The validations. The retries. The logs. The tests. The fallbacks. The guardrails.

7/9 In other words, a lot of agentic AI is still about the same engineering guarantees that have always made distributed systems work. Consistency. Reliability. Security. Observability. Failure handling. Production discipline.

4/9 Learning ML fundamentals is valuable. But most software engineers do not need to become machine learning researchers to build agentic applications. Models are available through APIs now. The harder problem is integrating them into real systems.

5/9 Building AI agents means understanding: How to handle unreliable outputs How to design safe tool calls How to manage state How to recover from partial failures How to protect data and permissions How to observe behavior in production

2/9 In distributed systems, we usually solve this with the Transactional Outbox Pattern. You write the business change and the pending event in the same database transaction. Then another process reliably publishes the event to Kafka.

3/9 When I started moving from software engineering into AI engineering, I thought I needed to deeply understand model training, evaluation, feature engineering, research papers, and ML deployment pipelines before I could build useful agents. I was wrong.

27 Apr

An agent deleted his prod db with one API call Backups were tied to same volume Least privilege. Environment isolation. Secret management. Backup isolation. Audit logs. Recovery testing. None of this is new The agent didnt invent a new failure mode. It compressed an old one into nine seconds

x.comJER on X: "An AI Agent Just Destroyed Our Production Data. It Confessed in Writing." / XAn AI Agent Just Destroyed Our Production Data. It Confessed in Writing.

27 Apr

Read his full story on Twitter: x.com/lifeof_jer/s...

25 Apr

Harness engineering is just ML folks hitting production for the first time, seeing their systems fail because they never had to think about security, scalability, reliability, maintainability, or system design as a whole, and then reinventing software engineering with a new name.

18 Apr

“It’s not the upfront capital that kills you, it’s the operations and maintenance on the backend.” Just read this in the book The Phoenix Project by @realgenekim.bsky.social , Kevin Behr, and George Spafford. Funny how actual it sounds.

18 Apr

They were referring to a database reporting tool that was implemented by a summer marketing intern. Given age only had a couple of months to work on it, it was actually pretty brilliant. It started being used in daily operations and consequently it was handed off to the IT department to support it

18 Apr

When auditors found out they couldn’t secure Access with all the data, they spent weeks cobbling together something that satisfied them. It’s like a free puppy… they say. Because it’s not the upfront capital that kills you, it’s the operations and maintenance on the backend.

meetup.comMeetup Utrecht JUG April 20th: Agentic Systems in Action, ma 20 apr 2026, 17:30 | MeetupWe are excited to announce our next Utrecht JUG meetup on **April 20, 2026,** hosted at the **Kamer van Koophandel.** Join us for an evening focused on the future of softwa

17 Apr

Next Monday @iamsoham.bsky.social and I will be delivering two insightful talks at the Utrecht Java User Group. Join us to learn how AI agents can power autonomous DevSecOps pipelines and how memory works in both humans and AI Agents. www.meetup.com/nl-nl/utrech...

17 Apr

Always a pleasure to be back at @springio.net . Especially when talking about building agentic systems with Spring AI! #java @spring-ai.bsky.social

I’m seeing a lot of posts claiming n8n is dead. I’ve never used it and I wonder if it’s a tool that has value when building enterprise scalable agents? Or did it serve a small niche that was agglutinated by something else?

1/ A former DevOps colleague recently woke up to a $70k GCP bill. And honestly, 𝗶𝘁 𝗺𝗮𝘆 𝗯𝗲 𝘁𝗵𝗲 𝗯𝗲𝘀𝘁 𝘁𝗵𝗶𝗻𝗴 𝘁𝗵𝗮𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝗲𝗱 𝘁𝗼 𝘁𝗵𝗲𝗺. After investigating, they found out that an 𝗔𝗣𝗜 𝗸𝗲𝘆 created in 𝟮𝟬𝟮𝟬 with no restrictions had been leaked and was now being 𝗮𝗯𝘂𝘀𝗲𝗱 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗚𝗲𝗺𝗶𝗻𝗶 𝗔𝗣𝗜.

10/ Now, a an unrestricted key is a node is a much larger graph of trust relationships. 𝗜𝗳 𝗮 𝗺𝗮𝗹𝗶𝗰𝗶𝗼𝘂𝘀 𝘂𝘀𝗲𝗿 𝗰𝗮𝗻 𝘁𝗿𝗮𝘃𝗲𝗿𝘀𝗲 𝘆𝗼𝘂𝗿 𝗴𝗿𝗮𝗽𝗵, 𝗶𝘁 𝗯𝗲𝗰𝗼𝗺𝗲𝘀 𝗮 𝗽𝗮𝘁𝗵𝘄𝗮𝘆 𝘁𝗼 𝗺𝘂𝗰𝗵 𝗺𝗼𝗿𝗲 𝗰𝗮𝘁𝗮𝘀𝘁𝗿𝗼𝗽𝗵𝗶𝗰 𝗼𝘂𝘁𝗰𝗼𝗺𝗲𝘀.

trufflesecurity.comThe Rise of API Worms ◆ Truffle Security Co.API worms are already active and spreading via exposed API keys, with Shai-Hulud showing twice that they can discover keys (even using tools like TruffleHog), move laterally, and self-propagate. Unlik...

11/ Read @trufflesec.bsky.social full article at about 𝗔𝗣𝗜 𝗪𝗼𝗿𝗺𝘀 at: trufflesecurity.com/blog/the-ris...

8/ - Your Jira might contain customer secrets - Your artifact store might contain embedded credentials - Your support system might expose third-party access

9/ 𝗧𝗵𝗶𝘀 𝗶𝘀 𝗲𝘅𝗮𝗰𝘁𝗹𝘆 𝗵𝗼𝘄 𝗹𝗮𝘁𝗲𝗿𝗮𝗹 𝗺𝗼𝘃𝗲𝗺𝗲𝗻𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝘀 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝘁𝗼𝘂𝗰𝗵𝗶𝗻𝗴 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝘀𝗲𝗿𝘃𝗲𝗿. A $70k bill is painful. But it’s contained and obvious. The multinational he works for can live with it.

6/ 4.Those credentials unlock other platforms (Jira, artifact stores, ticketing systems) 5.The process repeats across systems, accounts, and even companies The important detail is that not all keys are equal, but 𝗮𝗹𝗹 𝗸𝗲𝘆𝘀 𝗮𝗿𝗲 𝘂𝘀𝗲𝗳𝘂𝗹.

7/ • Data plane keys (S3, logs, tickets) → expose internal data and often more credentials • Control plane / compute keys (CI/CD, artifact repos) → allow publishing, modification, and supply chain impact Once an attacker gets in, every integration becomes a pivot point.

4/ See, there’s a growing class of threats called 𝗔𝗣𝗜 𝘄𝗼𝗿𝗺𝘀. @trufflesec.bsky.social has been writing about them, and we now have real-world examples like 𝗦𝗵𝗮𝗶-𝗛𝘂𝗹𝘂𝗱. These rely on chaining trust across services. 𝗡𝗼𝘁 on compromising hosts.

5/ 𝗔 𝘁𝘆𝗽𝗶𝗰𝗮𝗹 𝗽𝗮𝘁𝗵 𝗹𝗼𝗼𝗸𝘀 𝗹𝗶𝗸𝗲 𝘁𝗵𝗶𝘀: 1.A leaked API key is discovered (GitHub, S3, logs, etc.) 2.That key grants access to a service (storage, analytics, CI/CD) 3.Inside that service, more credentials are discovered

2/ They disabled the key immediately, only to discover it was tied to their Firebase SSO implementation. The key was meant to exist and to be public. It wasn’t meant to be unrestricted.

3/ The developer who created it likely intended it for development only. He stayed at the company for just six months in 2020 and somehow, the key made it into production after he left. 𝗦𝗶𝘅 𝘆𝗲𝗮𝗿𝘀 𝗹𝗮𝘁𝗲𝗿, 𝗶𝘁 𝘄𝗮𝘀 𝗲𝘅𝗽𝗹𝗼𝗶𝘁𝗲𝗱. 𝗔𝗻𝗱 𝗵𝗼𝗻𝗲𝘀𝘁𝗹𝘆, 𝘁𝗵𝗶𝘀 𝗺𝗶𝗴𝗵𝘁'𝘃𝗲 𝗯𝗲𝗲𝗻 𝘁𝗵𝗲 𝗯𝗲𝘀𝘁 𝗼𝘂𝘁𝗰𝗼𝗺𝗲. 𝗔𝘁 𝗹𝗲𝗮𝘀𝘁 𝗶𝘁 𝘄𝗮𝘀 𝘃𝗶𝘀𝗶𝗯𝗹𝗲.

youtu.beApple Just Showed Us Rare Prototypes—Even Tim Cook Hasn’t Seen Them | WSJYouTube video by The Wall Street Journal

"Products are only overnight successes in reverse. The iPod was not, the iPhone was not, the Watch was not." - Tim Cook (youtu.be/74qPQt_5DdM)

10 Apr

Building agentic system is not about machine learning, just like building enterprise systems is not about low-level programming. @albertheijn.bsky.social has understood that. They're hiring seasoned backend engineers to implement agentic systems: www.linkedin.com/jobs/view/44...