One AI toolkit fordata analysts
Khint doesn't touch your warehouse. It takes the other half of the job: questioning the chart on your screen, turning findings into something a stakeholder reads, and answering the ticket that asked for the number.
The query took twenty minutes,
the write-up takes the afternoon
A chat tab can't see the dashboard you're staring at, the ticket that asked for the number, or the four things you already ruled out this morning. So every answer starts with you retyping the context. Khint works on whatever is on screen and keeps the rest of the thread in a work session that stays on your machine, from the request landing to the write-up going out.
Confluence · Team Velocity Gadget
The real Capture and ask window, questioning a chart that sits in a tool with no export button.
Two ways to answer an ad-hoc request
Neither of them runs your query. They differ on what the write-up is allowed to see, and on how many tabs the answer has to be pasted into.
The chart has no export button
None of this is the analysis. It's everything around it: the figure you can't lift off a screen, the definition you half remember, the third paste.
- The number you need is rendered in a BI tool that exports nothing, so it gets retyped by hand or screenshotted into a doc nobody can search.
- How the metric was defined last quarter is in a Confluence page you half remember, and finding it costs more than recomputing it.
- Every prompt restates the request, the caveats and the four things you already ruled out, because the tab kept none of them.
- The finished summary then gets pasted into Slack, into the page, and onto the ticket. Three tabs, one paragraph, three chances to drift.
Khint, on whatever is on screen
Drag a box over whatever is rendered, keep the request in a session, and let one run reach every place the answer is expected.
- Drag a box over the chart. Extract text puts the table on your clipboard; Capture and ask opens a conversation on the screenshot itself.
- Knowledge pulls the definition your team agreed on out of your own indexed Jira, Confluence, Notion and Linear content, on every run.
- An active session already holds the request, the captures and the caveats you flagged, so you're editing a draft rather than starting one.
- One workflow posts to Slack and appends to the Confluence page in the same run, and a step can comment on the issue that asked.
Post to the channel that asked
Append to the analysis page
Comment on the requestThe four pieces
the write-up half runs on
Khint has no connection to a warehouse, a BI tool or a query engine, and it never runs a query. These four are what happens once the numbers land, and each is a shipped feature rather than a roadmap slide.
Capture
Drag a box over the table a BI tool refuses to export. Nothing is sent anywhere until you trigger the run yourself.
Knowledge
How the metric was defined in March, without the tab hunt. Your Jira, Confluence, Notion and Linear indexed on your own machine.
Agents
Rough findings to something a stakeholder actually reads, in your format. Treat a spreadsheet as text, never as a calculation engine.
Workflows
Format the write-up, then post it to Slack and append it to the Confluence page in one run, and comment on the ticket that asked.
What changes on an ad-hoc request
Three things, and none of them needs a warehouse connection approved.
- StopsRetyping the context into every promptThe session carries what was asked, what you captured and the caveats you flagged, so the write-up starts from the thread instead of from your summary of it.
- LandsBoth of the places people actually lookOne run posts the summary to the Slack channel and appends it to the Confluence page, and a separate step drops the answer on the Jira issue that requested it.
- Gets backThe half of the job that's not the queryThe querying stays in your usual tools. What changes is the reading, the questioning and the writing that happen once the numbers are already there.
Common questions from data and BI analysts
Does Khint connect to my database or write SQL?
No, and that's the honest boundary. Khint has no connection to a warehouse, a BI tool or a query engine, and it never runs a query. It works on what you hand it: the text you selected, a region of your screen, a file you point an agent at, or your voice. The querying stays in your usual tools; Khint takes the reading, questioning and writing that happens after the numbers land.
How does it read a dashboard I can't export?
Drag a box over it. Extract text runs OCR on that region and puts the result on your clipboard, which covers the table a BI tool refuses to export. Capture and ask instead opens a chat on the screenshot, so you can ask what the trend does after the third sprint and keep asking on the same image across several turns. Nothing is sent anywhere until you trigger the run.
Can it read an exported spreadsheet?
It can read one as text. An agent whose input is set to Document extracts the text of a .xlsx, .docx, .pptx, PDF or plain export locally, and only the extracted text is used. It's not computing over your cells: treat it as a way to summarize, restructure or write up a sheet, not as a calculation engine. Documents with an edit-in-place agent come back as the same file with its formatting intact.
Do the numbers I work on leave my machine?
Only what you explicitly act on. An action sees the text you selected plus, if you switched it on, the active session's compact summary. Memory sessions and the local Knowledge index live in a SQLite file on your machine and are never synced. Any agent can have Hide personal details switched on, which replaces emails, phone numbers and account identifiers with placeholders before the text reaches the AI. Integration credentials stay in your OS keychain.
Which tools can it write into, and is there a free plan?
Connect Jira and Confluence with an email plus API token, Linear or Notion with a key, Slack with a token, Gmail through sign-in. The palette then gains rows like Comment on Jira issue, Append to Confluence page and Post to Slack, and a workflow can end on any of them. The free tier is 300 credits a month, roughly 10 actions a day, no credit card. Paid plans start at €7 a month, and every plan includes all the work integrations.
Write up tomorrow's analysis with it
Free with 300 credits a month, about 10 AI actions a day. No credit card, no warehouse connection to approve: it reads your screen and your selection, nothing else.