"With experience and support from" is a nice landing trick!
How do you extract and relate to each other the facts from the documents that require comprehension and not simple similarity matching using common embeddings models?
This is the kind of content we all deserved in 2026, and this is still why I ask during interviews to explain how cookies are represented in HTTP protocol.
Recently started some agentic features for paid version, and this lead to a side project https://eatmydata.ai - a question-to-sql-to-dashboard builder, where data doesn't get exposed to AI (with bundled in-browser SQLite vector search, NER and many other features).
Why would an LLM want to look into the contents, what for?
We have low-cardinality data and yes this is safe to share and required to build an actual query.
Then we have high-cardinality and possibly PII - there’s absolutely no reason to share that data, there’s nothing for LLM to analyse there. Also semantic index (vector search) will find relevant records much faster and more accurately that any chain-of-thoughts just with an LLM-authored search fn call.
Further there are continuous numerical values and there’s not much LLM needs to see in there either. We can say, for example, if you look at data distributions when building your analysis, it can drive your analysis logic, but another point of view here is taht it creates unnecessary bias instead.
Totally. One thing that all major AI vendors are not doing currently is merging server AI with edge devices.
For example, there is no way neither in Claude nor in ChatGPT to run your own WASM or JS or whatever AI produces directly in user's browser context as a tool/skill - there is no call site for that. The only option is remote server-side.
My whole idea was that AI can perfectly write SQL and dashboard code knowing only the shape of your data and not it's contents. With direct upload to vendor now we're forced to share the contents.
Fast response. I can upload Excel/csv and iterate under 10 seconds from question to result. Doing same thing in Claude with 10x less data takes 5 minutes.
Nice, I recently did a similar but much simpler thing and open-sourced it under MIT, maybe some bits and pieced will be useful https://github.com/eatmydata-org/eatmydata
For example, MIT-licensed sqlite vector search extension.
Overall, I have a orchestrator - sql coder - js coder - dashboards, all without backend, running locally in the browser. It's mostly tested on small analysis and question answering with Gemini Flash Lite, and the overall target was speed from question to answer, including data sharing and waiting.
I built a question-to-sql-to dashboard tool for quick data analysis, just to avoid sharing random personal or customer xlsx documents with external AI. Released it as MIT recently:
For the "show me how many people are from Dallas" in AdventureWorks, it really depends on the model.
With `gemini-3.1-flash-lite` for all agents it produces this sql from the first try for $0.0033:
```
SELECT COUNT(DISTINCT ca.CustomerID) as customer_count
FROM CustomerAddress ca
JOIN (
SELECT a.AddressID
FROM vector_search('Address', 'City', 'Dallas', 20) vs
JOIN Address a ON a.rowid = vs.rowid
WHERE a.City = 'Dallas'
) addr ON ca.AddressID = addr.AddressID
```
and then formats output in Markdown.
I'll bake some default model in later, and more examples. And I guess it needs some default token quota.
I'm working on Routing24 https://routing24.com - we are building free route optimization tool for businesses to plan multi-vehicle multi-stop routes.
Multi-threaded WebAssembly in action for route optimization, all bundled with geocoding, OSM maps and routing, and provided world-wide.
We're adding driver's PWA, saving and sharing of route optimization projects, editing of optimized routes, sharing it with others either for execution or for approval, integrations and AI-assisted data imports, auth flows, support prompts, sales automation and all that boring stuff.
I keep working on Routing24 https://routing24.com, a free route optimization tool for businesses.
It's been approx. an year since we are up and running, and we helped 100+ businesses in the US and world-wide to understand the value and savings of automated route planning, and prepared tens thousands of optimized routes for companies operating from 1 to 50 vehicles. All this keeping our operational expenses low and flat, thanks to our local-first route optimization engine working in the browser, and reliance on OpenStreetMap.
I'd say it's pretty usable to run a EU-sized country or several US states on any commodity PC. For embedded devices, it really depends what is the device. On Raspberry PI it should be fine for batch geocoding, realtime (typeahead) will definitely be lagging.
Why bring server software to edge devices? Because its fucking awesome!