Prof Rod AI Automation
@profrodai.bsky.social
🤖 Teaching how to use AI to automate work & build agents
💡 AI hot takes, news, explainers
🗯️ Fun educational AI comics
Follow for daily AI tips & updates!
💡 AI hot takes, news, explainers
🗯️ Fun educational AI comics
Follow for daily AI tips & updates!
The clawdbot / moltbot team rebranded again now to OpenClaw :D
It feels as if they are running an AI agent as their brand manager doing greedy exploration.
It feels as if they are running an AI agent as their brand manager doing greedy exploration.
January 31, 2026 at 1:07 AM
The clawdbot / moltbot team rebranded again now to OpenClaw :D
It feels as if they are running an AI agent as their brand manager doing greedy exploration.
It feels as if they are running an AI agent as their brand manager doing greedy exploration.
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
The solution is not “more sophisticated system prompts”
is.gd/SLjWazis
is.gd
January 30, 2026 at 5:15 PM
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
The solution is not “more sophisticated system prompts”
is.gd/SLjWazis
Moltbot just hit 102K stars. Interest in local agents is exploding. But are they safe?
If your AI agent can browse the web AND access your sensitive data, you're already compromised.
The problem is that you can't firewall your way out of prompt injection.
If your AI agent can browse the web AND access your sensitive data, you're already compromised.
The problem is that you can't firewall your way out of prompt injection.
January 29, 2026 at 7:24 PM
Moltbot just hit 102K stars. Interest in local agents is exploding. But are they safe?
If your AI agent can browse the web AND access your sensitive data, you're already compromised.
The problem is that you can't firewall your way out of prompt injection.
If your AI agent can browse the web AND access your sensitive data, you're already compromised.
The problem is that you can't firewall your way out of prompt injection.
Clawdbot/Moltbot is already labeled as a “high-level AI tool” on par with Clay and relevant for GTM profiles. Yet, Clawdbot is still clunky to install, very unsafe to run for the average user, and still very brittle.
However, that won’t stop mass adoption of local AI agents to automate work.
However, that won’t stop mass adoption of local AI agents to automate work.
January 28, 2026 at 5:54 PM
Clawdbot/Moltbot is already labeled as a “high-level AI tool” on par with Clay and relevant for GTM profiles. Yet, Clawdbot is still clunky to install, very unsafe to run for the average user, and still very brittle.
However, that won’t stop mass adoption of local AI agents to automate work.
However, that won’t stop mass adoption of local AI agents to automate work.
How long will it take Moltbot / Clawdbot to become as popular as n8n? n8n currently has 172k stars on GitHub, moltbot already sits at 82k, and is not even 3 months old.
Some say Moltbot is a fad that will go away, but at 82k stars, it has become proof of what's possible and already inspired many.
Some say Moltbot is a fad that will go away, but at 82k stars, it has become proof of what's possible and already inspired many.
January 28, 2026 at 11:27 AM
How long will it take Moltbot / Clawdbot to become as popular as n8n? n8n currently has 172k stars on GitHub, moltbot already sits at 82k, and is not even 3 months old.
Some say Moltbot is a fad that will go away, but at 82k stars, it has become proof of what's possible and already inspired many.
Some say Moltbot is a fad that will go away, but at 82k stars, it has become proof of what's possible and already inspired many.
I bought a Mac Mini to run Moltbot / Clawdbot and Local AI!
My goal isn't just to “use AI,” but to build a system where AI replaces organizational roles, and have locally hosted digital co-workers.
Let's go together through this journey!
www.profrod.ai/p/i-bought-a...
My goal isn't just to “use AI,” but to build a system where AI replaces organizational roles, and have locally hosted digital co-workers.
Let's go together through this journey!
www.profrod.ai/p/i-bought-a...
I Bought a Mac Mini to Run Moltbot and Local AI
My goal: Build a system where AI replaces organizational roles and have digital co-workers
www.profrod.ai
January 28, 2026 at 1:41 AM
I bought a Mac Mini to run Moltbot / Clawdbot and Local AI!
My goal isn't just to “use AI,” but to build a system where AI replaces organizational roles, and have locally hosted digital co-workers.
Let's go together through this journey!
www.profrod.ai/p/i-bought-a...
My goal isn't just to “use AI,” but to build a system where AI replaces organizational roles, and have locally hosted digital co-workers.
Let's go together through this journey!
www.profrod.ai/p/i-bought-a...
Clawdbot is poised to be the next big thing in agentic AI. On par with LangChain in 2022. In 2 months, it went from 0 stars to 50k stars.
There seems to be a real need to run a personal local agent with your tools and data.
Have you played with ClawdBot?
There seems to be a real need to run a personal local agent with your tools and data.
Have you played with ClawdBot?
January 27, 2026 at 11:36 AM
Clawdbot is poised to be the next big thing in agentic AI. On par with LangChain in 2022. In 2 months, it went from 0 stars to 50k stars.
There seems to be a real need to run a personal local agent with your tools and data.
Have you played with ClawdBot?
There seems to be a real need to run a personal local agent with your tools and data.
Have you played with ClawdBot?
A damning analysis by GPTZero revealed that 53 papers accepted to NeurIPS 2025, the world’s most prestigious AI conference, contained over 100 hallucinated citations.
January 23, 2026 at 5:15 PM
A damning analysis by GPTZero revealed that 53 papers accepted to NeurIPS 2025, the world’s most prestigious AI conference, contained over 100 hallucinated citations.
Light vs. heavy agents miss the real axis: durability vs. disposability. I was thinking about this while reading the latest post of Hamza from ZenML.
He makes a compelling distinction between Light Agents (chat wrappers) and Heavy Agents (orchestrated workflows).
He makes a compelling distinction between Light Agents (chat wrappers) and Heavy Agents (orchestrated workflows).
January 16, 2026 at 1:23 AM
Light vs. heavy agents miss the real axis: durability vs. disposability. I was thinking about this while reading the latest post of Hamza from ZenML.
He makes a compelling distinction between Light Agents (chat wrappers) and Heavy Agents (orchestrated workflows).
He makes a compelling distinction between Light Agents (chat wrappers) and Heavy Agents (orchestrated workflows).
1/
🚨 Hot take: We’re not early on AI anymore.
10% of humanity already uses ChatGPT regularly.
2026 is year 4 of the AI revolution.
And that changes everything. 👇
🚨 Hot take: We’re not early on AI anymore.
10% of humanity already uses ChatGPT regularly.
2026 is year 4 of the AI revolution.
And that changes everything. 👇
January 2, 2026 at 9:15 AM
1/
🚨 Hot take: We’re not early on AI anymore.
10% of humanity already uses ChatGPT regularly.
2026 is year 4 of the AI revolution.
And that changes everything. 👇
🚨 Hot take: We’re not early on AI anymore.
10% of humanity already uses ChatGPT regularly.
2026 is year 4 of the AI revolution.
And that changes everything. 👇
AI feels like the 19th century railroad boom.
We're overbuilding infrastructure (datacenters, energy, etc) ahead of real demand. Many projects will fail.
But just like those "redundant" rail lines later became London's metro, today's excess may quietly power tomorrow's society
We're overbuilding infrastructure (datacenters, energy, etc) ahead of real demand. Many projects will fail.
But just like those "redundant" rail lines later became London's metro, today's excess may quietly power tomorrow's society
December 31, 2025 at 5:26 PM
AI feels like the 19th century railroad boom.
We're overbuilding infrastructure (datacenters, energy, etc) ahead of real demand. Many projects will fail.
But just like those "redundant" rail lines later became London's metro, today's excess may quietly power tomorrow's society
We're overbuilding infrastructure (datacenters, energy, etc) ahead of real demand. Many projects will fail.
But just like those "redundant" rail lines later became London's metro, today's excess may quietly power tomorrow's society
More than 200k banking jobs in Europe are at risk by 2030.
Morgan Stanley estimates a 10% workforce reduction due to AI.
The cuts will affect central services, including back-office, middle-office, risk, and compliance.
What's your plan to stay relevant professionally in 2026?
Morgan Stanley estimates a 10% workforce reduction due to AI.
The cuts will affect central services, including back-office, middle-office, risk, and compliance.
What's your plan to stay relevant professionally in 2026?
December 31, 2025 at 2:09 PM
More than 200k banking jobs in Europe are at risk by 2030.
Morgan Stanley estimates a 10% workforce reduction due to AI.
The cuts will affect central services, including back-office, middle-office, risk, and compliance.
What's your plan to stay relevant professionally in 2026?
Morgan Stanley estimates a 10% workforce reduction due to AI.
The cuts will affect central services, including back-office, middle-office, risk, and compliance.
What's your plan to stay relevant professionally in 2026?
Last night, we hosted a Rasa x Rime event in San Francisco at Continue and focused on one question:
Why does Voice AI still feel frustrating in 2025, despite all the progress and all the investment?
Here is what I learned at the event:
medium.com/@profrodai/v...
Why does Voice AI still feel frustrating in 2025, despite all the progress and all the investment?
Here is what I learned at the event:
medium.com/@profrodai/v...
Voice AI in 2025: What I Learned at the Rasa + Rime Event in San Francisco
Last night, we hosted a Rasa × Rime event in San Francisco at Continue, “🎁 Unwrap the Future: Voice & Agent Orchestration with Rime +…
medium.com
December 19, 2025 at 7:45 AM
Last night, we hosted a Rasa x Rime event in San Francisco at Continue and focused on one question:
Why does Voice AI still feel frustrating in 2025, despite all the progress and all the investment?
Here is what I learned at the event:
medium.com/@profrodai/v...
Why does Voice AI still feel frustrating in 2025, despite all the progress and all the investment?
Here is what I learned at the event:
medium.com/@profrodai/v...
Last week in Paris we debated voice stacks.
Conclusion: “Open vs Commercial” is the wrong question.
The real constraints are engineering ones.
What’s changing 👇
1️⃣ Latency ≠ tokens/sec
It’s jitter, interruption & VAD.
Graceful barge-in is the hardest problem in Voice AI.
Conclusion: “Open vs Commercial” is the wrong question.
The real constraints are engineering ones.
What’s changing 👇
1️⃣ Latency ≠ tokens/sec
It’s jitter, interruption & VAD.
Graceful barge-in is the hardest problem in Voice AI.
December 16, 2025 at 11:47 PM
Last week in Paris we debated voice stacks.
Conclusion: “Open vs Commercial” is the wrong question.
The real constraints are engineering ones.
What’s changing 👇
1️⃣ Latency ≠ tokens/sec
It’s jitter, interruption & VAD.
Graceful barge-in is the hardest problem in Voice AI.
Conclusion: “Open vs Commercial” is the wrong question.
The real constraints are engineering ones.
What’s changing 👇
1️⃣ Latency ≠ tokens/sec
It’s jitter, interruption & VAD.
Graceful barge-in is the hardest problem in Voice AI.
1/
Most voice AI apps fail.
And they don’t just fail on hard tasks. They fail on normal human speech.
Try saying a credit card number naturally:
"My card ends in four five three two."
Watch how fast things fall apart.
---
#VoiceAI #Rasa #RimeAI #Deepgram #AgentEngineering
Most voice AI apps fail.
And they don’t just fail on hard tasks. They fail on normal human speech.
Try saying a credit card number naturally:
"My card ends in four five three two."
Watch how fast things fall apart.
---
#VoiceAI #Rasa #RimeAI #Deepgram #AgentEngineering
December 3, 2025 at 9:54 AM
1/
Most voice AI apps fail.
And they don’t just fail on hard tasks. They fail on normal human speech.
Try saying a credit card number naturally:
"My card ends in four five three two."
Watch how fast things fall apart.
---
#VoiceAI #Rasa #RimeAI #Deepgram #AgentEngineering
Most voice AI apps fail.
And they don’t just fail on hard tasks. They fail on normal human speech.
Try saying a credit card number naturally:
"My card ends in four five three two."
Watch how fast things fall apart.
---
#VoiceAI #Rasa #RimeAI #Deepgram #AgentEngineering
Automate -> Dominate -> Deactivate -> Meditate
History doesn’t repeat, it just reboots.
💡 Follow Prof.Rod for the most relatable (and educational) AI content on the internet.
Inspired from MonkeyUser
History doesn’t repeat, it just reboots.
💡 Follow Prof.Rod for the most relatable (and educational) AI content on the internet.
Inspired from MonkeyUser
October 13, 2025 at 8:38 AM
Automate -> Dominate -> Deactivate -> Meditate
History doesn’t repeat, it just reboots.
💡 Follow Prof.Rod for the most relatable (and educational) AI content on the internet.
Inspired from MonkeyUser
History doesn’t repeat, it just reboots.
💡 Follow Prof.Rod for the most relatable (and educational) AI content on the internet.
Inspired from MonkeyUser
1/ The next AI Agents London Meetup is happening on October 15th! 🚀
After what we saw at the last one, you definitely don't want to miss it.
RSVP: www.meetup.com/london-agent...
After what we saw at the last one, you definitely don't want to miss it.
RSVP: www.meetup.com/london-agent...
October 1, 2025 at 8:54 AM
1/ The next AI Agents London Meetup is happening on October 15th! 🚀
After what we saw at the last one, you definitely don't want to miss it.
RSVP: www.meetup.com/london-agent...
After what we saw at the last one, you definitely don't want to miss it.
RSVP: www.meetup.com/london-agent...
Is Standard Agent all we need for agentic AI? I'm hosting a live AMA with Rishikesh Ajit (Founding Engineer @ Jentic, maintainer of Standard Agent).
We’ll walk the repo, run code, and show how you can onboard + contribute.
📅 Oct 2 · 4pm IST
🔗 RSVP: luma.com/hplglc1u
We’ll walk the repo, run code, and show how you can onboard + contribute.
📅 Oct 2 · 4pm IST
🔗 RSVP: luma.com/hplglc1u
September 29, 2025 at 8:38 AM
Is Standard Agent all we need for agentic AI? I'm hosting a live AMA with Rishikesh Ajit (Founding Engineer @ Jentic, maintainer of Standard Agent).
We’ll walk the repo, run code, and show how you can onboard + contribute.
📅 Oct 2 · 4pm IST
🔗 RSVP: luma.com/hplglc1u
We’ll walk the repo, run code, and show how you can onboard + contribute.
📅 Oct 2 · 4pm IST
🔗 RSVP: luma.com/hplglc1u
Agentic Happy Hours after MCP Dev Summit 🍻
@Apify + @jenticai hosting a casual pub meetup. Limited space.
📅 Thursday, Oct 2
🕡 6:30pm-10:00pm
📍 Ye Olde London, London EC4M
RSVP: luma.com/MCP-Dev-Summ...
@Apify + @jenticai hosting a casual pub meetup. Limited space.
📅 Thursday, Oct 2
🕡 6:30pm-10:00pm
📍 Ye Olde London, London EC4M
RSVP: luma.com/MCP-Dev-Summ...
September 26, 2025 at 8:15 AM
Agentic Happy Hours after MCP Dev Summit 🍻
@Apify + @jenticai hosting a casual pub meetup. Limited space.
📅 Thursday, Oct 2
🕡 6:30pm-10:00pm
📍 Ye Olde London, London EC4M
RSVP: luma.com/MCP-Dev-Summ...
@Apify + @jenticai hosting a casual pub meetup. Limited space.
📅 Thursday, Oct 2
🕡 6:30pm-10:00pm
📍 Ye Olde London, London EC4M
RSVP: luma.com/MCP-Dev-Summ...
1/ Do agents really need evals?
That was the question I asked Hamza Tahir, CTO of ZenML, in our first live webinar. The internet treated it as binary. The reality is more nuanced. 🧵
That was the question I asked Hamza Tahir, CTO of ZenML, in our first live webinar. The internet treated it as binary. The reality is more nuanced. 🧵
September 19, 2025 at 8:15 AM
1/ Do agents really need evals?
That was the question I asked Hamza Tahir, CTO of ZenML, in our first live webinar. The internet treated it as binary. The reality is more nuanced. 🧵
That was the question I asked Hamza Tahir, CTO of ZenML, in our first live webinar. The internet treated it as binary. The reality is more nuanced. 🧵
🚀 London, we’re live!
On Sept 17, join us + Xcede for the 1st London Agentic AI Meet-Up.
Speakers from Microsoft + Tomoro AI.
📍 111 Buckingham Palace Rd
🕕 6pm doors, 6:30 talks
AI agents, best practices, networking. Seats are limited!
RSVP: www.meetup.com/london-agent...
On Sept 17, join us + Xcede for the 1st London Agentic AI Meet-Up.
Speakers from Microsoft + Tomoro AI.
📍 111 Buckingham Palace Rd
🕕 6pm doors, 6:30 talks
AI agents, best practices, networking. Seats are limited!
RSVP: www.meetup.com/london-agent...
September 18, 2025 at 9:08 PM
🚀 London, we’re live!
On Sept 17, join us + Xcede for the 1st London Agentic AI Meet-Up.
Speakers from Microsoft + Tomoro AI.
📍 111 Buckingham Palace Rd
🕕 6pm doors, 6:30 talks
AI agents, best practices, networking. Seats are limited!
RSVP: www.meetup.com/london-agent...
On Sept 17, join us + Xcede for the 1st London Agentic AI Meet-Up.
Speakers from Microsoft + Tomoro AI.
📍 111 Buckingham Palace Rd
🕕 6pm doors, 6:30 talks
AI agents, best practices, networking. Seats are limited!
RSVP: www.meetup.com/london-agent...
Reposted by Prof Rod AI Automation
🔥 Want to know what it takes to build AI agents and raise millions for your startup?
This Thu, Aug 28 (16:00 UTC+1) join our Ask Me Anything with
@seanblanchfield.bsky.social, CEO of Jentic (€4M pre-seed) moderated by @rodriveraai.bsky.social
Sign Up Link Below! ⬇️
#AI #AIAgents #Startups #AMA
This Thu, Aug 28 (16:00 UTC+1) join our Ask Me Anything with
@seanblanchfield.bsky.social, CEO of Jentic (€4M pre-seed) moderated by @rodriveraai.bsky.social
Sign Up Link Below! ⬇️
#AI #AIAgents #Startups #AMA
August 27, 2025 at 12:49 PM
🔥 Want to know what it takes to build AI agents and raise millions for your startup?
This Thu, Aug 28 (16:00 UTC+1) join our Ask Me Anything with
@seanblanchfield.bsky.social, CEO of Jentic (€4M pre-seed) moderated by @rodriveraai.bsky.social
Sign Up Link Below! ⬇️
#AI #AIAgents #Startups #AMA
This Thu, Aug 28 (16:00 UTC+1) join our Ask Me Anything with
@seanblanchfield.bsky.social, CEO of Jentic (€4M pre-seed) moderated by @rodriveraai.bsky.social
Sign Up Link Below! ⬇️
#AI #AIAgents #Startups #AMA
1/
I just published my first article on Dev.to 🎉
"Stop Building Brittle Agent Workflows" why AI agents break when chaining API calls, and how the Arazzo Engine makes workflows deterministic and reliable.
🧵
I just published my first article on Dev.to 🎉
"Stop Building Brittle Agent Workflows" why AI agents break when chaining API calls, and how the Arazzo Engine makes workflows deterministic and reliable.
🧵
September 17, 2025 at 8:54 AM
1/
I just published my first article on Dev.to 🎉
"Stop Building Brittle Agent Workflows" why AI agents break when chaining API calls, and how the Arazzo Engine makes workflows deterministic and reliable.
🧵
I just published my first article on Dev.to 🎉
"Stop Building Brittle Agent Workflows" why AI agents break when chaining API calls, and how the Arazzo Engine makes workflows deterministic and reliable.
🧵
1/ Evals discourse is loud right now:
"Evals or you're shipping vibes."
"Ship, monitor, A/B – evals slow you down."
Both are right in context. What matters is systematic measurement of quality, sized to your stage.
"Evals or you're shipping vibes."
"Ship, monitor, A/B – evals slow you down."
Both are right in context. What matters is systematic measurement of quality, sized to your stage.
September 8, 2025 at 3:36 PM
1/ Evals discourse is loud right now:
"Evals or you're shipping vibes."
"Ship, monitor, A/B – evals slow you down."
Both are right in context. What matters is systematic measurement of quality, sized to your stage.
"Evals or you're shipping vibes."
"Ship, monitor, A/B – evals slow you down."
Both are right in context. What matters is systematic measurement of quality, sized to your stage.
Starting soon - 16:00 UTC+1! AMA with Michael Cordner on building agents that are simple, open, and actually useful!
Jump in + get the ping: luma.com/et0is0mj
Jump in + get the ping: luma.com/et0is0mj
September 4, 2025 at 1:43 PM
Starting soon - 16:00 UTC+1! AMA with Michael Cordner on building agents that are simple, open, and actually useful!
Jump in + get the ping: luma.com/et0is0mj
Jump in + get the ping: luma.com/et0is0mj