Run the grooming meeting:leave with tickets, not homework
Grooming aligns the team, then the decisions evaporate into a scratch doc and you rewrite them afterward. Khint is the assistant beside you in the ceremony: it holds the whole session in Memory, turns each decision into a clean ticket the moment it's made, and pushes it back to Jira from the same keyboard shortcut, before the team moves to the next story.
The meeting ends,
and the work begins again
A good grooming session produces clear decisions, but if only you were writing them down, they land as bullet points in a doc nobody reads. Then you spend the afternoon reconstructing what the team meant, retyping it into each ticket, and filing status changes one by one. Khint collapses that second shift into the first: its three pillars (Agents, Capture, and Memory) sit behind one palette, so the ticket is refined and filed while the team is still in the room. This is the live companion to the quiet backlog refinement prep you do beforehand.
One ceremony, every ticket ready by the end
Facilitating a live “Sprint 24” grooming, story by story.
Open one session for the whole ceremony
Before the call starts, start a Memory session: call it “Sprint 24 grooming”. Everything you run for the next hour is logged to it, and Khint keeps a compact running summary. That summary rides along on each AI Action, so decisions the team makes on story three are still in context when you reach story twelve: no re-explaining the product area every time. How Memory works →
Pull the story up as the team reaches it
With Atlassian connected, the palette's Jira Active sprint and Search rows put the item on screen the moment the group turns to it. Pull issue drops its current text into Khint so you are editing the real ticket, not a copy that has to be reconciled later. How integrations work →
Turn the decision into a ticket, live
As the team settles what the story actually means, select the note you just jotted, hit Cmd+Shift+K, and run a reusable Action: “Refine to ready”. No prompt yet? Type a one-line description and press Generate; Khint drafts it, and Improve sharpens it later. Or clone the Backlog Refiner starter pack. The clean problem statement and acceptance criteria appear in place, in front of the whole room, so anyone can sanity-check them before you move on.
Fill the gaps the discussion exposed
When the team spots a missing edge case or an unclear rule, run a second Action: an acceptance-criteria drafter that returns Given/When/Then. If someone screen-shares a mockup or an error, Khint's Capture pulls the text straight off it so it lands in the ticket too. Chain your refine and criteria Actions into one Workflow and a raw story becomes a ready one in a single keystroke. Acceptance criteria, in one action →
Close the item before the next one
Use the Jira Add comment row to post the agreed criteria onto the issue, then Change status to move it from raw to ready: one issue per run, so the room sees each change land. Want a single artifact for the whole session? Confluence Create page publishes the groomed batch as one page the team can open in sprint planning.
Why not just take notes and do it after?
Because “after” is where accuracy goes to die: a day later you are guessing at what the team meant, and the tickets you file don't match the conversation. Filing in the meeting keeps the record honest and lets the room correct it on the spot. Khint makes that fast: the refinement Action is saved once and reused on every story, Memory carries the session context into every prompt automatically, and the Atlassian and Linear integrations push changes where the team already works. Because Actions only see the text you select (plus the session summary you opted into), your unreleased backlog never sits in a chatbot history.
Common questions
How is a grooming assistant different from backlog refinement prep?
Refinement prep is the solo pass you do before the meeting, quietly upgrading stale tickets to your Definition of Ready. A grooming assistant is what you reach for during the ceremony itself, while the team is talking. The problem it solves is the after-meeting tax: the team aligns on a story, then the decision lives in someone's head or a scratch doc, and you re-do the writing later. Khint sits behind one shortcut (Cmd+Shift+K) so you capture each decision the moment the team lands it: the ticket leaves the room updated. If you want the before-the-meeting workflow instead, see how Khint handles backlog refinement.
Does Khint listen to or transcribe the meeting?
No. Khint never records audio and has no microphone access. You facilitate the discussion; when the team settles a story, you select the note you jotted, hit the shortcut, and a reusable AI Action turns it into a clean problem statement and acceptance criteria. It works on the text you highlight: nothing is captured silently in the background.
Can it update the ticket in Jira without leaving the meeting?
Once you connect Atlassian with your email, API token, and cloud domain, the palette adds Jira rows. Active sprint and Search surface the item the team is discussing, Pull issue brings its text into Khint, Add comment posts the refined criteria the group just agreed, and Change status moves it from raw to ready. Each is one issue per run, so every change on the shared screen is deliberate and visible to the room.
How does it keep context across a full grooming session?
Start a Memory session named for the ceremony, say "Sprint 24 grooming". Every Action you run is logged to it and Khint keeps a compact running summary that rides along on each later prompt. So when you reach the tenth story, the model already knows the product area, the constraints, and the decisions the team made earlier in the same meeting. Sessions live in a local SQLite database on your Mac and are never synced to Khint's servers.
Facilitate your next grooming with it
Free with 10 AI actions and 5 captures per day. No credit card. Save the Action once, run it on every story you groom.