... Slack, or support desk, then ask Genie why your latest number moved. Comment from Shivam Kushwaha(@shivam_kushwaha16): Huge congrats on #1 Product of the Day well deserved and great launch by the team at Databox Comment from Ziga Potocnik(@zigapotocnik): @jared_coleman  Good question, Jared. It doesn't depend on which tool you connect first. The boundary is set per tool, not per connector order. For every action Genie, our AI Analyst, can take, you choose whether ...

... thank you to everyone who commented on last week's thread. A lot of the tools you mentioned are the ones we connected first. Which tool would you connect first? Let us know in the comments. Comment from Ziga Potocnik(@zigapotocnik): @aruna_polosofttech  Great question, Aruna. We expect most teams will start with troubleshooting. A number drops, someone asks why, and the answer comes back with the deal, ticket, or conversation behind it. That's the quickest ... ... schedule and flags changes, good or bad, with the context attached. Because it can also act on what it finds, a spotted opportunity can turn into a created task or an updated deal right away. Comment from Ziga

... actual deal or thread behind it, not just the number. Before we launch, genuinely curious: when a metric needs explaining, where do you go to find the answer? CRM, Slack, a spreadsheet, or just someone's memory? Comment from Ziga Potocnik(@zigapotocnik): @fatima_sarki  Thanks Fatima! That's the exact problem we built this for, seeing the change is the easy part, finding the why is where all the time goes. Comment from Aleksandr Kubarskii(@al_kub): Before looking ... ... business reason I would check whether tracking or the metric definition changed Then split the drop by account or channel A Slack message can explain one lost deal without explaining the whole drop Comment from Ziga

... break top 5. Thursday needs 235. That's a 70-point gap just from picking a different day. Weekends aren't just easier, they're way less crowded Tuesday averages 30.4 launches a day. Saturday averages 10.7. Fewer competitors, lower bar, most of the effect comes from volume, not some algorithm quirk. If you can't launch on a weekend, Friday is your best bet 205 median points for top 5, the lowest of any weekday and noticeably easier than ... ... Thursday. Tuesday's hidden trap Tuesday has more total launches than Monday (1,064 vs

... when a model changes underneath us and nobody notices for a week. That's the check I'd want shouting at me, because it's exactly the kind I'd never remember to open a dashboard for. Comment from Ziga Potocnik(@zigapotocnik): @asadmalik901  That's a great example, and it's exactly the kind of check that gets skipped because nobody remembers to open a dashboard for it. Routines won't catch a silent model swap ... ... weekly instruction to Genie would work well here. It reads the numbers, tells you what moved and why, so a drift shows up in the notification instead of sitting quiet in a chart for a week. Comment from Ziga

... 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. "I asked for through the 20th," which as he says are opposite meanings on identical dates), which governed metric definition it used, and as-of timestamp. Not because readers will read it every time, but because it turns "trust me" into "verify ... ... holding. Which is it today, snapshot at share time or live? Comment from Anthony Wright(@anthonywrinqsb): most of the effort goes into rebuilding the same slides with fresh numbers.the analysis is the valuable part not the formatting. Comment from Ziga

... 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

... didn't. And if you haven't tried it yet, it's free to get started at https://databox.com/skills-marke... - pick a skill, connect your data once, and your first report is ready in a few minutes. Comment from Ziga Potocnik(@zigapotocnik): @rahulbhavsar  Agreed, and that's a good push to keep emphasizing. That's actually the part we care most about getting right: each skill runs through Databox's metric definitions and live data, not the AI guessing ... ... numbers. It's what makes the report something you can share, not something you have to double check first. Trust in the output matters more long term than the initial download number. Comment from Ziga

... build by hand most often, the one you'd love to just ask for instead? We're in the comments all day - questions, feedback, and pushback all welcome. Comment from Hossein Yazdi(@hosseinyazdi): @zigapotocnik  Upvoted you Ziga! congrats on hitting the #2 spot!! Comment from Ziga

... what's working? What's missing? Would love to hear it. And if you haven't tried it yet, you can get started for free at https://databox.com/mcp . Ask it anything about your business data. Comment from Ziga Potocnik(@zigapotocnik): @aisling_conlon2  Thank you!! Comment from Aisling Conlon(@aisling_conlon2): Congrats @zigapotocnik - a great product like this deserves the PH kudos Comment from Isaac Grau(@isigr57): Congrats on the launch. The MCP integration is the piece that actually ... ... question happens removes that step entirely. The hard part is going to be keeping metric definitions consistent across sources when the model is doing the interpretation. Would love to see how you handle that at scale. Comment from Ziga

... daily / weekly / monthly summaries. It's valuable to ask AI agent and get an immediate reply without SQL / excel spreadsheet. But I suppose to get repeated actions would be essential to retain the users. Best, Gleb Comment from Ziga Potocnik(@zigapotocnik): @riya_pariyar  that acquisition + 30-day retention question is a perfect example - exactly the kind of thing that takes forever manually but is one prompt away with MCP. On latency: for typical metric queries ... ... retention, not just conversion? That's the one that always requires 3 tools and a spreadsheet to answer properly. Congrats on the launch, @zigapotocnik what's the latency like when querying against larger metric histories? Comment from Ziga

... testing this for a product analytics workflow. Is the exported data CSV/JSON, and does it respect the filters I apply before asking the AI? If yes, that fixes my main blocker for using this in reports. Comment from Ziga Potocnik(@zigapotocnik): @olivier_jury  Olivier, this is exactly the scenario we built for - thanks for laying it out so clearly. On your three points: 1. Charts + numbers in 10s - yes, that's the goal. Inline chart rendering (Widgets) is shipping ... ... databox.com/mcp . We're doing a proper PH launch on May 28, but you can connect today and test it before then. Would love your take on whether #1 and #2 land the way you described. Comment from Ziga

... curious to hear from this community: What's the first API you'd connect if you could do it in under 10 minutes? We're in the comments all day - questions, feedback, and pushback all welcome. Comment from Ziga Potocnik(@zigapotocnik): @gjinprelvukaj  Stripe actually has a native Databox integration, so you might not need Custom Integrations for that one - worth checking if it covers what you need first. The internal buggy CRM endpoint though, that's exactly ... ... Stripe. Or honestly, our internal buggy CRM endpoint that'll never see an official integration. Quick one: have you seen anyone hook up an API with OAuth2 + refresh tokens yet? That's usually where these things break. Comment from Ziga

... www.producthunt.com/products/dat... Comment from Swati Paliwal(@swati_paliwal): This is exciting, just a quick question: how 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 - so if you have multiple integrations set up, it can pull metrics across them in a single query. For something like "What's driving ...