This goes against the grain - but I’m starting to reimagine enterprise & manufacturing workflows using AI.

Very good leadership support, small (but great) team, huge mandate and uncertainties - and it’s quite exciting.

We are also hiring - AI+Full Stack https://cenovus.wd3.myworkdayjobs.com/en-US/careers/job/Seni...

I love the article & the protocol. However, MCP reminded me (somewhat) of microservices & SOA. Are we creating failure vectors nightmare? Or, is it, because of agents, we can gracefully increase reliability?

How I understood it is that natural language will form relatively large portions of stacks (endpoint descriptions, instructions, prompts, documentations, etc…). In addition to code generated by agents (which would fall under 1.0)

Windsurf feels more organic. Context size will likely still be a problem.

I'm curious about your approach and the nature of those industrial apps. Is it more of recommender agents accessing available sources (through URIs) - or more like explainers. Would be great to connect https://shorturl.at/xdOee

Back in the day, I remember an application that 'analyzed' websites for their Rails hallmarks. I don't know if Rails apps are as distinct nowadays.

Take that RAG parser

I'm currently listening to "Endurance: Shackleton's Incredible Voyage by Alfred Lansing". I've also heard of some of the arguments against Shackleton (I haven't watched the talk).

I have to think of what Shackleton, as a leader (boss), was going through and with uncertainties abound.

28 people who he hired based not only on capability alone, but also for crew (team) fit.

He apparently cared deeply for them, and they in-turn cared for one another.

They managed to work together in the harshest of environments. They all made it.

That in and of itself, is a remarkable feat.

How is this built? What'd be the approach if I'd like to achieve similar results against proprietary data.

References article speak of RAG and RIG - but I wonder if they factor into fine-tuning the models. AFAIK, RAG doesn't play nicely with structured data.

I haven't read it in great detail, but it looks like there's documentation for self-hosting[1] (on Google Cloud).

[1] https://docs.datacommons.org/custom_dc/

I came to recommend this as well. Still relevant. I hope he's doing well.

I’m doing not too bad these days, thanks for the well-wishes! :o)