DevRel @RasaHQ · Professor of AI @ITAM_mx teaching @SovereignAgents Architectures · Content Creator @profrodai

Joined September 2015
93 Photos and videos
Rod Rivera retweeted
Why does your AI agent demo beautifully and break later? It's the harness, not the model. Starting Friday at 11 AM EDT, free weekly office hours with @Nebius_Academy and @rasa_hq builders on exactly this. Share your questions. I will answer live on Zoom for 60 minutes. RSVP: lu.ma/7ci6q3zp
3
3
200
Rod Rivera retweeted
I pulled an all-nighter to finish and release the final project for our course at Nebius Academy. One part of the project was open-sourcing the Sovereign Agent. You can check it out here: github.com/sovereignagents/s… This is my first fully open-source contribution to PyPI, and I really hope others will find it useful. Over the past few weeks, I’ve been studying how modern, always-on AI agents are built in 2026. I call these 'sovereign agents.' Think of tools like OpenClaw, Claude Code, Aider, and similar projects. My goal was to make something simple enough to help people learn, but also practical for building real projects. These days, agents seem overly complex and packed with dependencies. For example, OpenClaw has hundreds of thousands of lines of code, but it doesn’t have to be that complicated. For those familiar with it, my inspiration was the fast.ai library. It was designed for learning how Deep Learning works, but many people ended up using it for their own projects. Since this field is moving fast, I already have plans for version 2 and hope to release it in the next few days. I’m also working on documenting all the patterns these agents use. If you don’t want to miss any updates, please star the project and share your comments or feedback!
1
1
89
For selected examples, the results are impressive, but as soon as you try ChatGPT's latest image model with prompts that have less data, it breaks. Anyone living in London will confirm that this map has many inaccuracies. However, it is a pretty hallucination!
Apr 22
Replying to @deedydas
“Map of California with exaggerated labels features” I love this prompt so much. Really cool way to understand the geography of various places. 9/11
1
2
188
Here the Berlin equivalent
1
41
Once you look into major non-Western cities, the examples stop making sense Again, it is very pretty & very impressive, given that just in 2024, we did not even have legible text in genAI images (remember those alien-looking signs). Plus, everything looked cyberpunk or ethereal.
34
Rod Rivera retweeted
You’ve built your Rasa agent. But no matter how much you test, you can’t predict every path a real user will take. Nobody can. That’s exactly why Arklex AI and Rasa are teaming up. Rasa’s CALM architecture gives your agents the flexibility to understand users and the reliability to act predictably. Arksim closes the last mile, automatically running quality tests across thousands of simulated conversations to catch errors before real users ever do. No more holding your breath at launch. Try Arksim on your next Rasa project: github.com/arklexai/arksim/t… #rasa #AIagent #opensource #AIEval
2
3
172
The problem with naming your product after the current thing is that it ends up sounding dated fast! Anything with "GPT" appended feels stuck in 2023. And if you are a "Copilot," it sounds even older. Same will happen to all those products with "Claw" in the name.
28
Have you heard the term "harness engineering" before? And do you have thoughts on the topic? H.E is an emerging discipline in AI development focusing on building infrastructure, tools, and wiring necessary for AI agents to autonomously build, test, and manage software products
32
I've spent years building recsys, and I love "customers also bought" algos. Here we have: "People who buy peanut butter powder also listen to Andrew Huberman?" Is that useful? At what point does correlation stop being a signal?
43
When we use AI to generate our images and Finland gets labeled as Russia and Czechia as Germany
Europe Forgot the Lesson the 1970s Oil Shocks Once Taught The continent answered with reactors, pipeline diplomacy, and offshore drilling, then spent three decades neglecting and dismantling everything it had built. a mega🧵inspired in part by my conversation with Doomberg. The European response to the OPEC embargo was an impressive mobilization that moved decisively and pragmatically taking advantage of the unique conditions available throughout the bloc. France moved decisively launching the The Messmer Plan in direct response to the oil shock. It remains the fastest large-scale nuclear buildout in history. France had little domestic oil, but it had everything else the program required: a large corps of state-trained engineers produced by the Grandes Écoles, heavy industrial capacity rebuilt under the postwar dirigiste economic model, and a nationalized utility in Électricité de France (EDF) already accustomed to executing at the direction of the state rather than waiting on market incentives. Its political class drew the logical conclusion: electrify aggressively around a domestic nuclear base, using a standardized reactor designs that a purpose-built supply chain could replicate at pace. Space heating, water heating, rail and significant portions of industrial process heat were shifted onto the grid as the fleet came online, deliberately substituting domestic electrons for imported hydrocarbons across as much of the economy as the technology of the era allowed. The result over roughly twenty years was 54 operating reactors, an electricity system generating around 75 percent of its output from nuclear, net electricity exports to neighbours who had made different choices, and as an unintentional side effect a per-capita carbon footprint in the power sector that remains among the lowest in the developed world.
1
75
Rod Rivera retweeted
If you want to understand how "always-on" AI agents, such as OpenClaw, or conversational agents, such as @Rasa_HQ , work and build your own, join us in March! It will be in person in Central London in the evenings. Plus, best of all, it's free! Let's learn together how to harness these technologies to automate tasks and deliver better customer experiences! You can apply to the @nebiusacademy at the link below. (and of course, if you're obsessed with #OpenClaw like I am, subscribe to @localainet to stay up to date on what's happening in the OpenClaw ecosystem)
Meet @profrodai 🎓 DevRel at Rasa and Professor of the Practice at ITAM, Rod will be teaching at our free AI Performance Engineering course in London this spring. You’ll learn how to build AI agents for business tasks on top of third-party APIs. Apply: bit.ly/40aMVbE
1
2
6
143
Rod Rivera retweeted
Most of us use Claude Code just for the basics, but when it gets complex, we're back to copy-pasting into ChatGPT. That's why I'm joining Denis Volkhonskiy and Stan Fedotov, PhD, from @nebiusacademy to enter the Claude Code "engine room" tomorrow. What we are breaking down: * Reliability: How to stop "hallucination loops" in agent-based iteration. * Speed: Building high-speed pipelines that don't sacrifice code quality. * Production: Moving past experiments into actual ML and DevOps workflows. We'll also be giving a first look at the AI Performance Engineering course coming to London this March. It’s a 14-week deep dive (completely free) for those ready to move from "using AI" to "engineering AI systems." In the course, I'll show you how to build voice AI agents with @Rasa_HQ and tools like OpenClaw. If you’re an ML engineer, DevOps specialist, or a dev looking to upgrade your stack, you must come and join us! 📅 Tomorrow, Feb 17 🕓 04:00 PM GMT 🔗 Register here: hellorasa.info/4aqzMzN Can't make it? I also curate a calendar of the best AI events happening in London (online in-person). It would be great to see you at one of those instead: hellorasa.info/4aAUQ6O #ClaudeCode #AIagents #Rasa #NebiusAcademy #SoftwareEngineering #MLOps
2
3
338
Rod Rivera retweeted
OpenClaw is great! But local != secure if the LLM has full home directory access. Check out AgenShield for: ✅ Static policies (not vibes) ✅ Kernel-level enforcement (macOS Seatbelt) ✅ JIT secrets 🔗 Shield: bit.ly/4qpSjT6 💻 GitHub: bit.ly/3MsvjVv

1
1
54
Rod Rivera retweeted
Just a week ago, I was wondering how long it would take for OpenClaw to have more stars on GitHub than n8n. It took n8n 81 months to get to 174k stars. OpenClaw achieved it in 3 months. At the beginning of the year, before becoming aware of OpenClaw, I mentioned that 2026 is the year of the digital coworker, where we finally move from software and AI that help us with our workflow to software that autonomously completes outcomes, software that truly works like a digital peer to whom we can delegate tasks. Right now, this vision isn't yet fully materialized. OpenClaw and similar tools are far from perfect and very experimental. But you can imagine a very close future where we aren't paying a yearly subscription for a CRM at $6,000 USD, but instead we start paying $15,000 or $20,000 for a digital SDR. It might sound like a lot to pay for software, but when you consider that a human SDR has a yearly base salary of around $40,000, you realize a company saves more than half the costs while getting more or less the same results. And without someone who goes on holidays, takes days off, or might leave you at some point. This might sound grim, but the other side of the coin is that anyone adopting OpenClaw and similar digital coworkers starts to have a virtual team at their disposal that truly makes them 10x more productive. We just have to look at how products like Lovable already empower marketing teams to do in days what was truly impossible and unthinkable before without involving agencies, high budgets, and months of planning and development. This is the first time since ChatGPT went live in late 2022 where it feels that, again, AI is accelerating and radical changes are starting to happen. How are you using OpenClaw?
2
1
2
337
Rod Rivera retweeted
Today’s OpenClaw Daily is out! And if you are watching your OpenClaw API bills explode, you're not alone. This issue highlights @MattGanzak guide showing how simple config changes can drop costs from $1,500 /month to under $50 localainet.substack.com/p/sl…

1
2
4
129
Rod Rivera retweeted
Today's edition of the OpenClaw Daily covers: - How one builder created a 10-agent "Mission Control" system with persistent memory - Critical security vulnerabilities discovered (and patched) - The Moltbook controversy and database exposure incident localainet.substack.com/p/op…
2
2
44
Rod Rivera retweeted
There is an almost religious belief that system prompts and guardrails are what will protect Moltbot, or any other agent, from exposing data or executing malicious actions. The solution is not “more sophisticated system prompts” is.gd/SLjWazis

1
1
40
In 2023, I began talking about "AI Product Engineer". Mostly, as AI Engineer had already been coined by Swix. Recently, I was thinking, "Nobody uses the term." Wrong! It's amazing to see JDs & job titles on LI. As with everything, the key is to keep talking til someone listens
1
80
Rod Rivera retweeted
It is not an exaggeration to say that Moltbot is the next big AI platform to master and build on. On Google Trends, there has been more search interest in the last two days around Moltbot than around: • Claude Code (blue) • Cursor (yellow) • N8N (green) • Manus (Purple) • LangChain (orange) And we must remember Moltbot is not even 3 months old. It currently stands at 67.2k stars and 8.4k forks. Btw, I am writing an article on how to install and run Moltbot safely. Everyone is asking: "How do I run Moltbot without risking my inbox, files, and credit card?" Stay tuned.
2
1
300
Life update: I joined the wave of Mac Mini buyers to run Moltbot in a restricted environment. I want to test everything under the sun. Share your favorite models / projects / libraries for running local AI! I'll be building in the open and sharing my findings and impressions!
160