Hacker News: ajoski9

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 08 Oct 2026 16:52:00 +0000

hey everyone, we just launched a live demo site: https://demo.strata.do

So you don't have to setup docker if you just want to try the product directly. Thanks!

New comment by ajoski9 in "Archaeologists Are Reconstructing the 'Invisible' Technologies of the Stone Age"

ajoski9 — Thu, 08 Oct 2026 16:50:27 +0000

Let me guess, it's the boring stuff.

New comment by ajoski9 in "Show HN: 0Sql – Semantic Layer as a Service"

ajoski9 — Wed, 07 Oct 2026 15:14:30 +0000

You can now try it live with zero setup: https://www.0sql.io/try/

Show HN: 0Sql – Semantic Layer as a Service

ajoski9 — Tue, 06 Oct 2026 19:36:55 +0000

We pulled out the semantic layer from our other app (Strata.do) and made it a standalone service. Now anyone can build data apps with an integrated deterministic, secure, and fast query layer.

How it works: 1. Use the zsql cli to build your model locally 2. zsql deploy (self hosted versions soon) 3. Post a query spec to your projects end point 4. Get back SQL

We never connect to your data warehouse or see any actual data. We only see your model and generate valid sql's.

This is an alternative to using Cube, MetricFlow, Semantic Views, and various other solutions. See our comparison table for the key differences: https://www.0sql.io/#compare

Thanks for checking it out! What do you think??

Comments URL: https://news.ycombinator.com/item?id=49982997

Points: 7

# Comments: 5

New comment by ajoski9 in "Why the Bronze Age Collapsed"

ajoski9 — Fri, 02 Oct 2026 12:41:58 +0000

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.

New comment by ajoski9 in "Why the Bronze Age Collapsed"

ajoski9 — Fri, 02 Oct 2026 12:39:05 +0000

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.

New comment by ajoski9 in "Why the Bronze Age Collapsed"

ajoski9 — Thu, 01 Oct 2026 15:28:53 +0000

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.

New comment by ajoski9 in "Why the Bronze Age Collapsed"

ajoski9 — Thu, 01 Oct 2026 14:13:04 +0000

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.

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 14:07:53 +0000

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?

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 13:55:38 +0000

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?

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 13:49:31 +0000

ah man, that's not cool

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 13:48:59 +0000

Good point. Should've linked to the main page. Thanks

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 13:48:28 +0000

Thanks a mill for that! I meant to keep try in the body only.

New comment by ajoski9 in "Show HN: Strata – an expressive semantic layer that can say no to your LLM"

ajoski9 — Thu, 01 Oct 2026 12:53:19 +0000

Thanks for the comment. We are highly focused on certain use cases and want to be upfront about that.

Show HN: Strata – an expressive semantic layer that can say no to your LLM

ajoski9 — Wed, 30 Sep 2026 14:59:57 +0000

Hello HN, I'm Ajo and I built Strata.

I spent 4 years at Netflix solving self service for non-technical business users. I think I cracked it with my unique approach to semantic layer design. The key challenge is balancing expressiveness with ease of use for our non technical colleagues. It just so happens that focus made it work pretty well with LLMs too.

Strata is a full stack solution. It includes a semantic layer, dashboards, subscriptions, and google sheets exports. All of it can be done view agent conversation or via MCP.

Some key concepts and features: - Names are strict. Only one thing called Revenue can exist in a project. If revenue is mapped to multiple tables, the query grain plus speed will decide table. - Strict naming conventions lends itself to enabling Automatic data blending acrros fact domains. - Partition and Aggregate aware semantic routing. This allows you to load a portion of your data into a faster compute engine like Druid or ClickHose, while keeping full history in trino or something cheaper. The query engine will choose the faster tier if the query can be resolved there. - Complex measures: out of the box support for snapshot, LOD (include/exclude), Compound, and Auto leveling compound measures. - On top of the semantic layer users can create custom calculations that span fact domains. - Another interesting feature is the ability to create cohorts and apply as filter to an entire query or single measure within a query.

We are deliberately not building a semantic layer that your BI tools connect to. I think that is a dead end. We have apis, and mcp for anything custom you want to build on top.

Try it free on docker: https://strata.do/try/

Docs here to get you going: https://strata.do/docs/

This is an early beta version. It is NOT open source. However, the free tier includes up to 25 users. You should be able to run it entirely on your machine with docker.

I would love to hear your feedback. Especially, those working with Looker and Cube.

Thanks for reading!

Comments URL: https://news.ycombinator.com/item?id=49909913

Points: 25

# Comments: 17