Meeting notes in,filed Jira ticket out
Refinement ends with a list of decisions and no tickets. Khint drafts the ticket with AI (summary, description, acceptance criteria) and files it in Jira from one keyboard shortcut, on the notes you already typed.
The decisions are made,
the tickets still aren't written
A good refinement produces a dozen clear decisions, and a backlog of transcription work for afterwards. Each one has to become a summary, a description, and acceptance criteria, then get typed into Jira field by field. That hour after the meeting is where momentum dies and where vague tickets get filed because you ran out of patience. Khint closes that gap: its Agents turn your raw notes into a structured ticket, the Jira integration files it, and Memorykeeps the meeting's context attached to every draft.
One refinement, start to filed tickets
A sprint-refinement meeting, step by step.
Start a session for the meeting
Before refinement starts, open Memory and start a session: “Sprint 14 refinement”. Every Action you run from now on is logged and Khint keeps a compact running summary, so each ticket you draft already shares the meeting's context. How Memory works →
Connect Jira once
On Khint's Integrations page, paste your Atlassian email, an API token, and your cloud domain into the Atlassian card. From then on the palette shows a JIRA section, and any workflow can carry a Create Jira issue step. How integrations work →
Jot the decision in plain language
Mid-meeting you type the gist into your notes: “Export to CSV is timing out on big boards. New ticket: add server-side pagination. AC: under 2s for 5k rows, keep column order, no UI change.” No formatting, no Jira fields, just what was decided.
Run the drafting workflow
Select those lines and launch your workflow from the palette (Cmd+Shift+K). The first Agent rewrites the notes into a structured ticket (a one-line summary, a clear description, a bullet list of acceptance criteria) and the final step is Create Jira issue. The first line becomes the summary; the rest becomes the description.
Get the issue key, keep the trail
The created issue key is the workflow's output. Paste it straight into the meeting thread so everyone sees the ticket exists. The filing is also logged into your active session, so by the end of the hour your Memory session reads like a refinement log: what was decided, what you filed, where it landed.
The workflow is yours to shape
Up to five steps in series: AI Actions, then an integration write at the end.
Swap the drafting Actions for your own: your team's story template, a definition-of-done check, a translation step for a bilingual team. Or skip the hand-assembly: describe the flow in plain language and Khint's workflow generator builds the chain, reusing Actions you already have and slotting in the Jira step when the integration is connected. The same machinery also writes to Confluence and Linear, so a sibling workflow can publish the meeting summary as a page right after it files the tickets.
No workflow? The palette files it too
For a one-off ticket you don't need a chain at all. With Jira connected, the palette's JIRA section carries a Create issuerow that runs a formatting Action on your selected notes and files the result in one move, alongside rows to pull an issue, see the active sprint, search, add a comment, or change status, so the backlog stays in reach without leaving the app you're in. And when you want a longer working session, Khint ships an MCP server so Claude Desktop or Codex can read your meeting session directly (the notes, the drafts, the filed tickets) without copy-paste.
Common questions
Can Khint create a Jira ticket from my meeting notes?
Yes, as a step you trigger, never in the background. Connect Jira with your email, an API token, and your cloud domain on Khint's Integrations page. Then either use the Create issue row in the palette, or add a Create Jira issue step to a workflow and pin the project and issue type in the editor. When you run it on selected notes, the first line becomes the ticket summary and the rest becomes the description, and the new issue key comes back as the result.
How does the ticket get a proper structure instead of a raw dump?
An AI Action does the drafting first. You write an Action ("rewrite these notes as a Jira ticket: a one-line summary, a description, and a bullet list of acceptance criteria") and it runs on the selected text before the Jira step files the result. The Action editor can Generate that prompt from a plain-language description and Improve it later, so you are not writing prompt boilerplate by hand.
Does it remember what the meeting was about?
If a Memory session is active, yes. Start a session for the meeting and everything you run is logged and compacted into a short summary that rides along with each AI Action, so the ticket draft already knows which feature you were refining without you re-explaining it. Sessions are stored locally in SQLite on your machine and are never synced to the cloud.
What does Khint send to the AI?
Only the text you selected, plus (if a Memory session is active) the compacted session summary. Nothing else leaves your device silently. Your Jira email, API token, and cloud domain are kept in your OS keychain, and every issue Khint files is logged into your local session history so you can trace what was created and when.
Try it on your next refinement
Free with 10 AI actions and 5 captures per day. No credit card. Type the decision, draft the ticket, get the issue key back.