Prof Rod

Daily lessons on why AI agents fail & how to fix them. Learn harness engineering & sovereign agents. Free courses, office hours & comic explainers

[Prof Rod @profrodai]

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: https://t.co/9uxBHZHZKc

[Prof Rod @profrodai]

If you're in Munich on Saturday 02/05 and would like to understand Why AI agents fail? And what you can do about it!

Come to our free workshop!

We will discuss failure modes and how to counter them and many of our learnings at @Rasa_HQ.

RSVP: https://t.co/2s0X820G7I

[Prof Rod @profrodai]

@willchen500 In the age of Ai, the value of code is 0.

Anyone can vibecode pretty much any SaaS today.

The differentiators will remain brand and distribution.

Anyone can open-source Harvey and Legora, but how do you have lawyers and legal experts install it, adopt it and manage it?

[Prof Rod @profrodai]

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: https://t.co/Ju8u3YiJne

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 https://t.co/3KimzMfqaJ 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!

[Prof Rod @profrodai]

Are agentic skills simply a new way to store and organize prompts?

I’ve checked out some popular skills on GitHub, and I’m surprised that many are just a single simple prompt, like: "Interview me relentlessly about every aspect of this plan until we reach a shared understanding."

One reason might be that we never really learned how to prompt well. Prompting was often seen as a temporary skill or even as "pseudo-engineering."

Even as the models improve, it makes less sense to start every prompt with "You are a world-class X."

When we structure prompts well, or what we call 'skills', we get more consistent results from these models.

You don’t always have to, but adding a role to your prompt and giving clear instructions can help.

So what if we never really learned how to do all this?

Luckily, that’s where repositories and directories of SKILL.MDs can help.

This example shows how much we can get out of a simple prompt, without using tool calls or writing 100 lines of instructions. Even now, four years into ChatGPT, we’re still just scratching the surface of what’s possible with LLMs.

That’s why I encourage everyone to keep looking for ways to improve their prompting if they want to build better agents, harnesses, or skills.

[Prof Rod @profrodai]

@christianmiele How are robotics and AI gonna stop it? They only accelerate the trend

We don’t need that many workers if 1 can do the job of 10 with AI

Anthropic is a direct MSFT competitor. Headcount is 3k vs 300k

In 🇩🇪 job destruction will be worse. Many roles only exist due paper processes

[Prof Rod @profrodai]

Last week, @Rasa_HQ and @nebiusacademy co-hosted a webinar, and nearly 100 engineers attended to discuss AI agents and Claude Code.

Thanks to Denis Volkhonskiy and Stan Fedotov for the deep dive into Claude Code. I walked away with sharper mental models myself.

Here is what stuck with me:

1. An agent is not just an LLM
Brains (LLM) plus Knowledge (RAG) plus Tools (Bash, file I/O) plus Workflow control. All four layers have to work together before you have something production-ready.

2. Plan Mode changes everything
Stop asking agents to "fix the bug." Enter a collaborative planning state first. The agent proposes a path, you approve it, and then it executes. No surprises.

At Rasa, we call this equivalent Conversation-Driven Development. Listen before you build. The same principle applies to agents.

3. Security is not an afterthought
When you give an agent a Bash tool, you're handing it the keys to your house. Two non-negotiables: never expose .env files, and vet every MCP skill like you'd vet a random script from the internet.

4. Context is your budget. Spend it deliberately.
Use “compact” or “clear” between sub-tasks. Tag specific files with “@” instead of pointing at the whole repo. "Look at everything" equals hallucinations plus a bill you didn't expect.

What's next
We are headed into a future of digital coworkers, conversational and headless. The engineers who figure out how to combine both are going to have an unfair advantage.

We're building a hyper-local community of AI engineers in London. If you're in London, sign up here: https://t.co/dV6Blp2OkF

I also wrote a longer post with my learnings from the webinar here: https://t.co/hv9icUMl6r

Plus, don't forget to apply to the AI Performance Engineering program from Nebius, the deadline is approaching!

[Prof Rod @profrodai]

@Siftedeu Doesn't Lecun, in the picture, live in the US?

And isn't the company where he is involved also a US company?

Who in Europe is doing world models who is actually relevant?

[Prof Rod @profrodai]

Massive disinformation here. OpenClaw was not acquired. OpenClaw is becoming a foundation.

Its license remains MIT; anyone can use it as they see fit, also commercially.

The founder got a job at OpenAI, which was extremely well paid, but nowhere close to the numbers mentioned here.

[Prof Rod @profrodai]

Apply here to the @nebiusacademy AI Performance Engineering program, it's free, in London, and starts in March: https://t.co/9pfFq05Mun

[Prof Rod @profrodai]

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)

[Nebius Academy @Nebius_Academy]

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: https://t.co/BePqR2jH4C

[Prof Rod @profrodai]

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: https://t.co/bN8iLlOhvx

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: https://t.co/dV6Blp2gv7

#ClaudeCode #AIagents #Rasa #NebiusAcademy #SoftwareEngineering #MLOps

[Prof Rod @profrodai]

We built the next electricity.

Our killer app? "Put me in an 80's yearbook."

[Prof Rod @profrodai]

We have now vibecoding, Lovable, and v0, and so many tools to create websites fast.

Yet, most new websites keep looking like they used one of the free templates available on Webflow

[Prof Rod @profrodai]

@OmriBuilds OpenClaw + n8n is a mid-term solution, as n8n still has the stability, connectors, workflows, etc, but long-term, I don't see why we should keep both

[Prof Rod @profrodai]

In today's edition of OpenClaw Daily, we dig into:

* Security Beyond the Prompt
* The 24-Hour Exploit Cycle
* Persistence & Backends

and more!

https://t.co/UonctU0yh6

[Prof Rod @profrodai]

In today's edition of OpenClaw Daily, we dig into:

* Security Beyond the Prompt: We explore why "writing better instructions" isn't a security plan. For production agents, we need kernel-level enforcement and zero-trust architectures.
* The 24-Hour Exploit Cycle: Analyzing how quickly vulnerabilities are being scanned in the wild post-launch.
* Persistence & Backends: How to give agents the databases and APIs they need to function 24/7.

and feature community contributions by

* Sagi Rodin for the deep dive into AgenShield and shifting security from "vibes" to deterministic policies.
* Angel Dimitrov for his fascinating experiment in multimodal feedback loops, giving his agent a face and a mirror to refine its own expressions.
* Chris Rosendale & Eric Pauley for providing critical data on how scanning activity ramps up globally within hours of an exploit's discovery.
* Knut Martin Tornes for showcasing how to integrate https://t.co/DdH7m5hhbF to provide agents with a robust, serverless backend.
* Rob Pisacane for his strategic look at "Agentic SEO" and how businesses must adapt for machine-readable web traffic.
* Steffen Maas at Ocean One Ventures for the "Mr. Crabs" case study, where they maintain data sovereignty while building an autonomous executive assistant.

Read below!

Have an interesting project or opinion?
We would love to feature your work or insights in an upcoming edition.

Want to join the conversation?

We have a WhatsApp community where we discuss all things OpenClaw. Contact me for access.

https://t.co/IjWVc378vj

[Prof Rod @profrodai]

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: https://t.co/ISXeGyk4O0
💻 GitHub: https://t.co/R2F6kTm9xb

[Prof Rod @profrodai]

In issue 07 of OpenClaw Daily, we feature insights from:

- 🦄 Peter Steinberger
- Bence Csernak
- Alex Cheema
- Jason M. Lemkin
- Mesut Gulecen
- Rachel Nguyen

Also in this issue: We take a look at OpenShears

https://t.co/KD3IghPsT4