Svdc

We just had that same bug when we used a conventional ML engine to OCR a document. Thats very common on quantities. The new LLMs allow for prompt engineering, so we were able to solve it.

This is exactly one of the main issues if not the biggest issue of B2B products.

>> Will the traders at Cargill, Vitol, Exxon, Trafigura, Glencore buy it? Do they want to take the time to "learn" another tool?

I worked for this company that was built on a consortium of the biggest players, and adoption requires a lot of effort. Not only on the relationships you have to build, either by the account management team or by a product person, and trust also plays a big role - a lot of babysitting and support is required.

But trust me when i say that if they find that "yet another tool" provides the time-savings and the cost savings they are after, then they will use it. It will take take, which for most companies is not an option, but patience is key.

My experience also tells me that what one company is after does not mean it is translated easily to another. A Trader in one company might be very open to new tools and new business processes, others not so much. I would also say that if a specific role has so many nuances from company to company, that will also be true from commodity to commodity.

On another note, we had in the past product specialist to help on the product development side, and they had come from very robust backgrounds from logistics operations. But what they knew was very specific to how the companies they worked before operated and that didn't resonate sometimes for other clients.

Its a difficult industry to penetrate, smaller to medium sized companies are more likely to adopt disrupt technologies, while bigger ones tend to take longer.

for what i have seen in the demo it looks very very good. And I agree with a teak here and there this sw can be adopted by a range of trading houses of any kind of commodity, including the big ones with refineries. The difficulty in building systems like these, even if AI driven, is the myriad of business rules and the different specifics of each commodity trading.

I was doing AI implementations for a company in Oil and Refined products. And I can tell you that AI can massively improve the processes and and streamline their operations. In fact, it can easily transform any data entry to structure data without the needless sw development of API integrations and gateways.

My first point as a contribution is, traders are lazy and operators are control freaks. In a way traders only care about doing deals so any trade entry in a system us prone to errors and misalignment, such as the ETRM system's reference data. And Operators are control freaks in a way that if they find our that your AI missed a single entry they will mistrust it forever. They rather spend more time copy pasting that to trust your AI. But any automation is welcome they still want to have control (which some in contrast will argue that that control is a nuisance and a waste of time).

Oh well, though customers is what they are.

I am really happy to know that there are others trying to solve the same problems in a world of ineffectiveness.