Supernova

All your data in Claude and Codex

Analytics

Artificial Intelligence

Data

Visit WebsiteSee on Product HuntTwitter ⧉Github ⧉

Supernova’s permission controls and background syncing look promising, especially for large datasets. I’m curious how teams monitor sync failures or schema changes across integrations, and where the process still needs manual intervention.
How do you give Claude or Codex access to live company data without creating a new governance and maintenance burden?

Sounds like a really exciting update, Luke and Kate! Love how Supernova makes it simple to connect company data without extra setup, and the open‑source angle is a huge plus. Curious to see how teams will use those dashboards in practice — what’s been the most surprising use case you’ve seen so far? Congratulations!

We ship a remote MCP server too, and the thing that surprised me most was how misleading the tool-call metrics are. Ours read close to a 100 percent failure rate for a while. When I broke it down, 36 of 80 recorded tool calls were unauthenticated probes getting a 401, and 27 more named tools we do not publish at all. Seven were real calls from real clients, and all seven were the same bug.

So the number that looked like a broken product was mostly the open internet knocking on the door.

With 30 plus connectors exposed, do you separate authenticated traffic from probes before computing anything? And do you pass upstream errors to the model verbatim or normalise them? We were turning a 402 into a 5xx and it made the real failure unreadable for months.

Good to see you back for a second launch. Table permissions went from private preview to shipped for everyone while the thread was still running. Congrats on that turnaround.

Well designed;

How does this compare to leveraging OpenAI/Claude provided dashboard that can connect to all of your data sources already and present them as desired?

I'm not understanding why a tool needs to sit in the middle; feels like more of a vitamin than a pain killer tool.

Is this expensive? At a previous company we paid a lot for a fortune for data warehousing and syncing

Love that Supernova meets teams inside Claude and Codex instead of forcing everyone into yet another BI dashboard, that alone removes so much friction from getting answers.

Connecting live company data straight into Claude and Codex without traditional ETL setup is brilliant. Huge congrats on the launch!

the thing i would want to know most: when someone asks what revenue looked like last month and the model has the right rows in front of it, how often does the number come back right?

we pointed eight models at a live pricing api recently and two of them misread a quantity ladder they had been handed correctly. not hallucination, the data was in context, they just read the wrong row. one was out by 4x, the other by about 6 percent, and the 6 percent one is the dangerous one because nobody double checks a number that looks plausible.

for a support reply that is an annoyed customer. for revenue analysis it is a number that ends up in a board deck. do you verify the arithmetic anywhere before it renders, or is that left to the model?

The best analytics tool is sometimes the one that lets you skip building the dashboard.

For an early stage startup avoiding a full BI stack can be a pretty big deal. you dont necessarily need 40 dashboards you need answers when decisions are being made.

The concept is compelling but I’d want to know how you prevent confident nonsense when the underlying data is incomplete or inconsistent across systems.

I would be more interested in the permission model than the number of integrations. once an AI can query revenue and customer data being able to control exactly what it can see becomes critical.

Can you control which tables or field Claude is allowed to access? That would be important for sensitive customer data.

I like that this doesn't force teams to build another dashboard just to answer simple data questions.

I like the idea, but I’m wondering how teams handle cases where their data is incomplete or spread across many different tools.