ajoski9

does this engine compile sql or just provide context in a structured way?

Would a semantic layer integration into JetBrains help here?

Let me guess, it's the boring stuff.

The article didn't explain how a well organized civilization couldn't reap the benefits of a new technology faster. Guns were fairly decentralized tech. Civilization didn't collapse.

Sure but wouldn't and organized kingdom have the resources to scale up iron weapons production faster? They certainly had larger armies I would imagine.

so economically speaking it was cheaper to mass produce iron weapons.. I would have assumed a first mover advantage. It would be surprising if iron tech sprung up everywhere at the same time. And sure smaller groups could do it, but some groups would do it better,faster, cheaper (paretto principle). They should have had a material advantage me thinks. Since its cheaper you could arm more people perhaps. Lastly, the current powers could have also adopted iron and armed larger armies.

Why didnt the people who mastered iron just conquer and continue civilization? Like we see with every other case where there is a tech advantage.

Thanks for the heads up. I do have a specific question on your implementation. We were thinking about launching a semantic layer as a service api. You post your model and we give you fast query generation. You can then use this in your own tools. Benefits are a fast expressive semantic layer, model hosted, and your actual data stays behind your firewall. What do you think of this?

Great question. Semantic layer has been around before I was even in the industry. Probably late 90's. Innovation on this layer has gone backwards actually. Simpler and less capable (Looker vs Strategy for example).

It does however improve on agent performance in one important way: rejects plausible queries that are invalid. Agents writing sql are more likely to be inventive in unexpected ways. Business users won't know the difference. It is definitely not useful for developers/data engineers anymore. But quite a good tool as part of analytics harness for business users.

The one issue with Snowflake semantic dialect is the lack of expressiveness. Agents have to route to sql for many common scenarios. What do you think?