Refactor importer into batched jobs
IssueTodo
Dana
Dana- Estimate
- 5 points
- Team
- Platform·Team
Acceptance criteria
- Importer runs in batches of 500
- Failed batches retry without blocking the rest
Your sprint planning just shipped 12 tickets
Run sprint planning, standups, and reviews in Tana, and the meeting ships the work itself: tickets filed, PRs drafted, decisions logged, before you leave the call. Nothing to re-enter in Linear afterward.
Try now
30-day free trialCredit card not requiredCancel anytime
Planning meetings produce sticky notes, not tickets.
An hour of alignment, then someone has to translate it into work: open Linear, write the tickets, add acceptance criteria, attach the screenshot, and re-explain the context the room already had.
20–30 min
of manual ticket entry after every planning meeting.
Often skipped
so decisions slip and the next standup re-litigates them.
Talking = doing
You talk through the sprint. The agent turns each thing you agree on into tracked work, live.
Dana12:17Let's split the importer into smaller batched jobs.
Send to Linear
Mia12:19And we need CSV validation before the next release.
Send to Linear
Theo12:24Open a spike PR so we can try the streaming approach.
Send to GitHubWorks for every meeting you already run
Pick a meeting type and see what comes out of it.
Discuss the sprint, and every item you align on becomes a tracked issue with acceptance criteria and an estimate.
Send to Linear
Reads from and writes to the tools you already ship with. Screen-share aware, so it captures what is on the screen, not just what is said.
Questions and answers
Can it really create tickets during the call?
Yes. Say “file that as a ticket” or let the wrap-up do it. The agent writes the title, description, and acceptance criteria, attaches the relevant screen-share screenshot, and creates the issue in Linear or Jira, linked back to the meeting.
Does it work with Linear and Jira?
Both. Agents read from and write to Linear, GitHub, Jira, and Slack, so the work lands in whichever tracker your team already uses.
Can it open pull requests?
Yes. Agree on the change on the call and an agent opens a draft pull request on GitHub from what you described, ready for you to refine.
Does it capture what is on the shared screen?
Yes. Tana is screen-share aware: the agent sees the Figma, the failing test, the stack trace, or the PR diff you are walking through, and uses it as context for the work it files.
How is this different from an AI notetaker?
A notetaker hands engineers a transcript. Tana files the tickets, opens the draft PRs, and updates the board, with the screen-share screenshot attached. It is a full video meeting platform too, and can also capture on Zoom, Google Meet, and Microsoft Teams.
Do we have to change our tools or process?
No. Work is created in Linear, Jira, GitHub, and Slack. Tana is not a new system of record, and there is nothing to wire up before your next standup.
Is our code and data private?
Privacy is built in, with granular control over what is shared with which people and agents. Your data is never used to train AI models, unless you consent to it. Tana is SOC2 compliant*. See the privacy page for how your data is handled.* In progress. ETA Q3 2026.
Run your next standup in Tana.
Try now
30-day free trialCredit card not requiredCancel anytime