I am looking for PMF and I need some feedback.
I already have a server-side text-to-sql and text-to-visualization that explores your database and generates visualization for a single prompt. It works cool and you can improve accuracy with gold queries and db annotations. So it's cool, but based on my research, if it comes to a dashboard, almost everyone suggests to buy an embeddable solution including dashboard management. And at this point, i built this prototype for a low-code solution for customer facing AI analytics, and i'd like to get some honest feedback on it.
How will it work?
- You can embed the UI with one line of code like <QuerypanelEmbedded dashboardId='' />.
- JWT for auth should be generated on your backend and saved into localstorage
- The ui provides limited text block editor, where you can add titles, paragraph and charts.
- Charts can be generated with AI, using a chat based modal and handling history and versions etc.
- The dashboard has a feature that sums up the data changes based on a given timeline.
- Admins can generate charts on Querypanel, and deploy them with one click to customers
- Customers (tenants) can customize their own dashboard as they wish (probably based on some RBAC)
What do you think? is it somethign that's worth further development ?
I’m working on https://querypanel.io, a server-side SDK that lets your customers chat with their own data, designed with a zero‑trust architecture you can embed directly into your web app. It automatically scans your database schema, gives you a UI to further “train” and refine behaviors, and only stores schema metadata and no credentials or row‑level data. We’ve already reached strong query accuracy on a real client’s ClickHouse setup and are now onboarding more customers.
I am building an SDK for embeddable analytics for text to sql / vizualization. (https://querypanel.io).
It uses zero trust architecture, and provides an interface for training the AI for more accurate results. I already have a client in the loop, hopefully we can close the deal soon.
Scale from tech perspective: I plan to move forward to full dashboard management + agent kit.
Scale from financial perspective: My plan is to reach ~120k - 200k ARR at the end of the year.
I am building https://querypanel.io. it's a server side ai sdk with zero trust architecture, that abstracts away the complexity of LLM/ AI and provides a simple way to implement text to visualization.
I've seen couple of companies that failed on this project in the previous years, but i can also see a couple that reaches 1-5M ARR nowadays and that'd totally fine for me too. Not VC Scale, but for me, with 4-5 ppl 1M would be more than enough.
I am looking for PMF right now, like how to improve the product, and what's the hardest, how to reach out to customers, and how to create the sales pipeline.
It's a server side AI SDK, embeddable analytics tool with zero trust architecture. It abstracts away the AI/LLM complexity and helps you add text to visualisation to your dashboards. It's a side hustle right now, i've already spent couple of month on it, and if i can get 4-5 customers in early 2026, i will be able to move in FTE.
i am about to incorporate my first business, https://querypanel.io. I vibe coded it, but i reviewed every line of code. I created the architecture on my own so i would say it was spec driven.
I have 15+ years of experience in engineering and i think AI is a good thing if you consider your self as an engineer. It speeds things up. Specially opus 4.5 or gemini 3 pro.
Happy to answer questions here. Some extra details:
1. How accuracy is handled
QueryPanel uses a hybrid approach:
schema embeddings for semantic column/table matching
LLM reasoning for query construction
optional “golden queries” to anchor common patterns
If the model is unsure, it returns multiple SQL candidates with confidence scores.
2. Supported databases
PostgreSQL and ClickHouse are stable.
3. Deployment model
Everything is server-side.
You keep your data + credentials.
QueryPanel only keeps: table names, columns, and metadata you enrich in the admin UI.
4. Why not build a full dashboard product?
Some comments usually ask this.
The idea is that most products already have UI — they just don’t want to build the LLM-to-SQL layer. Keeping it as an SDK makes it flexible for SaaS tools, internal dashboards, BI, etc.
5. What I’m looking for
People who want to test NL → SQL for their existing analytics
Feedbacks
Suggestions for benchmark datasets to validate accuracy
Thanks to anyone who takes a look, honest feedback is very welcome.