... open five tools, screenshot the numbers, paste them into Google Slides, and spend two hours making it look like you didn't just paste screenshots into Google Slides. We just made that whole process unnecessary. Artifacts by Databox lets you turn any Genie conversation into a polished, shareable document. Ask for a report, a slide deck, or even an interactive calculator, and Genie builds it on the spot, pulling live numbers straight from your connected data. No exporting ... ... same reason it's wrong, it reads well. So the feature I'd push toward, building on Jernej's point: make the artifact carry its own provenance - the date range, why the range ends there (nightly sync vs

... shared it for. A client report, a board deck, something weirder? Haven't tried it yet? Just ask Genie for a report, a deck, or a calculator. It's free, and you can share the link with anyone, no Databox account needed on their ...

... median points needed to break the top 5 and top 10 on each day. Check the full report here: https://app.databox.com/shared/a... The short version: Saturday is the easiest day. Only 266 median points to crack top 5, vs 360 on Wednesday. That's a 35% harder climb on the worst day vs

... choice, and start typing context it doesn't have - what's a good conversion rate for you, which channels actually matter, what "normal" looks like for your traffic. We just made that whole loop unnecessary. Skills Marketplace by Databox is a free library of plug-and-play AI analytics skills and workflows. Pick one - GA4 traffic, LinkedIn performance, Google Ads, SEO visibility, and more - connect your data sources once through Databox

... Skills Marketplace by Databox launched yesterday (June 30th), and the community pushed it to #2 Product of the Day . Thank you. Huge thanks to the Databox

... made them succeed or fail? For those who've sold into small/mid-sized businesses, what's usually the biggest blocker to adoption price, integration effort, or something else? Is there a feature here that seems like a "nice to have" versus something that would actually change behavior? Would appreciate any perspective, whether from experience building similar things or just as someone who's dealt with this as a customer or business owner. Comment from Tommy Kang(@sjtkang): What I'm building ... ... entire roadmap. Comment from Nolan Vu(@nolan_vu): @thenameisarian  Interesting, alternative

... like telegram more than the whatsapp for chatting :) VS Code : i do code . Comment from mono.(@shakutovbekzat): Here s my stack for building mobile apps today: Antigravity + Codex (AI Agent): Switched to this setup recently. Previously, VS

... Yesterday ( June 1st ), we launched Databox MCP, and we finished #3 Product of the Day! This wouldn't have happened without the dedicated and highly engaged team in Databox

... www.producthunt.com/products/dat... Most analytics tools give you a dashboard. You open it, look at it, and go back to your spreadsheet to answer the actual question. We just changed that. Databox MCP connects your business data to the AI tools you already use - Claude, ChatGPT, Cursor, n8n. Instead of building dashboards to get answers, you just ask. What happened to your CAC last week? Which campaign drove the most revenue? Your AI does the math using your real metrics, definitions ... ... answer properly. Congrats on the launch, @zigapotocnik what's the latency like when querying against larger metric histories? Comment from Ziga Potocnik(@zigapotocnik): @tolstov_gleb  great points - role-based metric sets is something we think about a lot. Databox

... open a new app. They embed into surfaces people already touch. Hardware: Dune Keypad (46 upvotes) sits next to your keyboard with Claude integration. Video calls: Mina Meeting Assistant (47 upvotes). Text threads: folk (51 upvotes). Chat windows: Databox MCP (39 upvotes) plugs business data into Claude via Model Context Protocol. Mac autocomplete: Typeahead (22 upvotes). The pattern is clear: shipping AI as a new app is the slow path. The fast path is grafting onto a surface the user ...

... saying "let me get back to you on that." The data exists. The dashboards exist. But the path from question to answer still has too much friction in it. That's the problem we set out to solve with Databox MCP - launching on Product Hunt May 28. Instead of navigating dashboards, you ask the question directly in whatever AI tool you already use - Claude, ChatGPT, n8n, Cursor - and get an answer pulled from your live data. We'd love ... ... owns the dashboard? Or something else entirely? Comment from Ziga Potocnik(@zigapotocnik): @olivier_jury  they are currently view-only, but the AI client can either provide you with exportable data or vice versa, the data is exportable from Databox

... just launched Custom Integrations - and it's live on the leaderboard today. https://www.producthunt.com/prod... The problem it solves: your data is out there, but it's not in Databox. You submit an integration request, it goes into the backlog, and you wait. Sometimes for months. Sometimes it never comes. Custom Integrations flips that. Connect any JSON API yourself - OAuth2, pagination, dynamic date handling all covered. Turn the response into a structured dataset and start analyzing it with Genie ... ... connect my product analytics API first. If I can skip engineering tickets and just plug it in myself, that s a huge shift in how I work. Comment from Ziga Potocnik(@zigapotocnik): @gjinprelvukaj  Stripe actually has a native Databox

... heard this from a lot of Databox users over the years. There's a tool you rely on, a data source that matters to your reporting, and it's just not in our integration library. You submit a request, we add it to the backlog, and then... you wait. Sometimes for months. Sometimes it never comes. That's been one of the most consistent frustrations we've heard - and honestly, one we've felt ourselves. Our native library covers ... ... matter how fast we build, we can't keep up with every API out there. So we built a different answer entirely. Custom Integrations - launching on Product Hunt May 6 - lets you connect any API returning JSON to Databox

... launching Custom Integrations for Databox next Tuesday and would love some support from the PH community! Here's what it does: connect any JSON-based API to Databox

... community, Two days ago ( March 18th ), we launched Genie - Databox's AI analyst, and we finished #3 Product of the Day ! On a day when Anthropic, OpenAI, xAI, and Perplexity were also on the board. We're honestly still processing that. This wouldn't have happened without this community. The upvotes, the comments, the shares - and especially everyone who followed along in this forum over the past weeks. You shaped how we talked about the product and what we prioritized ... ... tried Genie - what's working? What's missing? Would love to hear it. And if you haven't tried it yet, you can try it for free at https://databox.com/ai-analyst . Ask it anything about your business data. - Databox

... spent the last few months building Genie, an AI analyst inside Databox. Tomorrow it goes live on Product Hunt. The short version: you ask a question about your data in plain language, Genie finds the right metrics, runs the analysis, and returns an answer with a chart in seconds. No SQL, no waiting on someone else. If you've been following along in this forum, thank you the conversations here genuinely shaped how we think about the product ... ... does Genie handle multi-source data blends for queries like "What's driving churn this quarter?" and spot correlations automatically? Comment from Ziga Potocnik(@zigapotocnik): @swati_paliwal  Great question, Swati! Genie works within your connected data sources in Databox

... just launched Genie - Databox's AI analyst, and it's live on the leaderboard today. One thing we kept seeing in user research: teams have dashboards, but still can't get fast answers. "Why are leads down this week?" still takes hours of manual digging. Genie fixes that - you ask in plain language, it finds the right metrics, runs the analysis, and returns an answer with a chart. No SQL, no waiting. A few things I'm curious to hear ...

... been building Genie - an AI analyst inside Databox, and one thing kept coming up in user research: people don't lack data. They lack fast answers. Dashboards exist. Reports get built. But when someone asks "why are signups down this week?" or "are we on pace to hit our revenue target?" - getting a clear answer still takes hours. We're launching Genie on Product Hunt on March 18th, and we'd love to hear from you before we do: What ...

... auth its just device id stored in keychain no accounts needed which keeps onboarding super minimal biggest challenge has been text extraction different sites block scrapers differently. revenucat for subscriptions has been great tbh, saves a ton of time vs rolling your own Comment from nim(@sup_nim): been building a few ios apps under studio.gold three live rn: speakeasy (turns any article url into audio), astrologica (ai personalized daily horoscope podcasts based on ur birth chart), and wordplay (daily ... ... LinkedIn posts in your voice. It's web-based, and I used Next.js, I used Better-Auth for authentication, and I added 3 strategies: email/password, Google OAuth and LinkedIn OAuth. I used PostgreSQL as the database and Polar (Stripe alternative