Artifacts by Databox - Ask your AI Analyst and get back a ready-to-share report
by•
Turn any conversation with your AI Analyst into a polished report, slide deck, or interactive document built from your live data. Generate it from a single prompt, then share it via public link or download as a PDF.
Replies
How customizable are the reports? Can teams define their own metrics and reporting structure?
Databox
@reda_roqai_chaoui Pretty customizable on the structure and styling side, you can ask Genie for a specific layout, sections, and restyle colors, fonts, and charts to match your needs. On metrics, Genie pulls from whatever data sources you've connected to Databox (130+ integrations), so it's working from your existing metrics rather than a fixed template. If you mean defining brand-new custom calculations from scratch, that's more a Databox metric-building question than an Artifacts one, happy to point you to the right resource if that's what you're after.
The Databox MCP release fast-forwarded years of experience for the junior folks on the marketing agency teams I work with. Artifacts just took that to the next level.
I sit at the intersection of ops, strategy, delivery, and client services, and month-end analysis has always been the hardest thing to scale. Even once a junior analyst could get a real answer out of the data, someone senior still had to turn it into something you could put in front of a client. That type of redundancy eats away at account margin week after week after week.
This morning I asked Genie to build a marketing report on a client account. Sessions were up 45%, which is the number a junior AM might lead the client call with and stop there. The artifact tied that jump to four pages we shipped during the month, then flagged that search visibility had actually declined over the same window, so the growth was coming from social and direct rather than search. Real traffic, but it doesn't compound the way search does. The first of six recommendations was to get the remaining pages live so it starts to.
That's a senior strategist's output, and anyone on the account team can produce it on their own now.
Really excited to see where this goes with the rest of the roadmap!
Databox
@garyjmag This is one of the best examples in the whole thread, thanks for the detail. The sessions-up-45%-but-search-visibility-declining catch is exactly the gap we wanted to close, a junior AM reading the headline number would've walked into that client call with the wrong story. Turning that into "a senior strategist's output anyone on the team can produce" is a better summary of the goal than we've written ourselves. Really appreciate you taking the time to actually test it against a real account instead of just reading the launch copy.
Hey all! Weighing in here. From a technical standpoint, what makes this reliable is where the data comes from. The artifact isn't summarizing a pasted export, it's pulling from your live connected sources across 130+ integrations. That's the difference between a document that reads well and one I can actually stand behind in a meeting 💪🏻
Databox
@emil_korpar Nailed the technical distinction here. Summarizing a pasted export is the easy version, standing behind the number when someone asks "where did this come from" in a meeting is the bar we actually held ourselves to. Thanks for breaking that down for the thread.
Databox
IMO, the most exciting launch recently. 🚀 It’s become the only way I’ve been doing analysis and reporting over the last couple of weeks.
Huge congrats to the team! This is just the beginning… can’t wait to see what’s coming next. 👀
Databox
@rtadej There is a teaser in one of the last images in the post; a sidebar is revealing what is coming next
Congrats on launch #8, Pete and team. The part I like is that it doesn't stop at the chart - it packages the analysis into something you can actually hand to someone. That last mile of turning an answer into a shareable artifact is where most BI tools quietly leave you. Nice work.
Databox
@ben_kahan Appreciate that, Ben. That last mile is exactly what we kept pointing at internally, an answer that stays in a dashboard doesn't travel, an artifact does. Thanks for the kind words.
This one clicked for me right away. You tell Genie what you actually did, so the report explains the result instead of just restating it. Dashboards were never the bottleneck. Nice work.
Databox
@lucasjpols Thanks Lucas. That's a good way to put it, dashboards were never the bottleneck, getting the "so what" out of them and into someone's hands was. Glad it clicked right away.
ZapDigits
Nice one!
Databox
@malithmcrdev Thanks! Here is the live example of one Artifact in action - no login needed, just open it: https://app.databox.com/shared/artifacts/8cc805b913e00e1c4641a177acf11867
no rush, honestly the fact that you'd rather confirm than guess on a data-loss question is the right instinct. that's exactly the kind of answer that's worse wrong than late. I'll keep an eye out for the follow up
Databox
@galdayan Appreciate that, and appreciate the patience. Will circle back here as soon as I've got a confirmed answer rather than leave you hanging too long.
The frozen-snapshot answer makes sense. The version I keep hitting is source data that restates after the fact: I generate a June report, share it, then re-trigger the same report in August and June's numbers have moved because an integration backfilled or a metric definition changed. The client sees two different Junes. Does Genie surface that the underlying data shifted between generations, or do you find out when someone asks?
Databox
@alexander_bl Good question, and a real scenario, not a hypothetical one. Straight answer: no, Genie doesn't flag that the underlying data shifted between generations. If a metric definition changes, the original June report is effectively obsolete, it captured the old definition at that point in time. Genie always pulls the latest definition when it generates a report, so a re-triggered report in August reflects current logic, not what June looked like under the old rules. So the two Junes aren't a bug, they're two different snapshots taken under two different definitions. Worth being upfront with clients about that if metric definitions are actively changing underneath a recurring report.
@zigapotocnik That's a clear answer, thanks. The thing that would make it safe for recurring client reports is stamping the artifact with the definition version or an as-of date, so a reader can tell which rules produced the numbers instead of having to remember. We ended up doing that for point-in-time data because "why did last quarter change" was otherwise unanswerable.