I don't know why these posts are being treated by anything beyond a clever prompting effort. If not explicitly requested, simply adjusting the soul.md file to be (insert persona), it will behave as such, it is not emergent.

But - it is absolutely hilarious.

Because there doesn't seem to be anything indicating the was a 'clever prompting effort'.

Respectfully, the same argument was for Moltbook's controversial posts and it turned out to be humans.

This is fantastic! I created a GMAIL for my Clawdbot and Google deleted the account after an hour.

Happy we could provide a solution!

I built something similar to this before Langraph had their agent builder @braid.ink, because Claude Code kept referencing old documentation. But the problem ended up solving itself when Langraph came out with their agent builder, and Claude Code can better navigate its documentation.

The only thing I would mention is that building a lot of agents and working with a lot of plug-ins and MCPs is everything is super situation- and context-dependent. It's hard to spin up a general agent that's useful in a production workflow because it requires so much configuration from a standard template. And if you're not being very careful in monitoring it, then it won't meet your requirements when it's completed, when it comes to agents, precision and control is key.

This really resonates - the opacity problem is exactly what makes MCP-based agents hard to trust in production. You can't control what you can't see.

We built toran.sh specifically for this: it lets you watch real API requests from your agents as they happen, without adding SDKs or logging code. Replace the base URL, and you see exactly what the agent sent and what came back.

The "precision and control" point is key though - visibility is step one, but you also need guardrails. We're working on that layer too (keypost.ai for policy enforcement on MCP pipelines).

Would love to hear what monitoring approaches you've found work well for production agent workflows.

At first I was reading this like 'oh boy here we go, a marketing ploy by ChatGPT when Gemini 3 does the same thing better', but the integration with data streams and specialized memory is interesting.

One thing I've noticed in healthcare is for the rich it is preventative but for everyone else it is reactive. For the rich everything is an option (homeopathics/alternatives), for everyone else it is straight to generic pharma drugs.

AI has the potential to bring these to the masses and I think for those who care, it will bring a concierge style experience.

I’ve been writing about building Agent-First SaaS and working with teams implementing LangGraph flows. I’ve noticed a recurring pattern where we get stuck trying to perfectly replicate a human's SOP (e.g., "click this button, then read this PDF"). While reproducing human workflows is great for trust and "human-on-the-loop" auditing, I argue it often traps us in a local optimum.

This post explores the difference between "Replica Agents" (biomimicry) and "First-Principles Agents" (optimizing for the objective function). I draw on examples like Amazon's "Chaos Storage" and AlphaGo to suggest that sometimes the most efficient agent workflow looks nothing like the human one.

Curious to hear how others are balancing "legibility" vs. "efficiency" in their agent designs.

I’ve been writing about building Agent-First SaaS and working with teams implementing LangGraph flows.

I’ve noticed a recurring pattern where we get stuck trying to perfectly replicate a human's SOP (e.g., "click this button, then read this PDF"). While reproducing human workflows is great for trust and "human-on-the-loop" auditing, I argue it often traps us in a local optimum.

This post explores the difference between "Replica Agents" (biomimicry) and "First-Principles Agents" (optimizing for the objective function). I draw on examples like Amazon's "Chaos Storage" and AlphaGo to suggest that sometimes the most efficient agent workflow looks nothing like the human one.

Curious to hear how others are balancing "legibility" vs. "efficiency" in their agent designs.

Backtesting is a complete waste in this scenario. The models already know the best outcomes and are biased towards it.

I find it a bit surprising GenAI has made it this far without this benchmark

They will seed in a few dozen influencers and there will be lines out the door

Beatifully said and you are right. I will get mine on Temu.