PERSONAL PRODUCTIVITY
AI Refresh Brief for Stale Loom Walkthroughs
For each stale, low-view Loom walkthrough, transcribes the recording, uses an LLM to judge whether its content is likely outdated.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled sweep begins
- ActionList stale low-view videos and fetch transcriptsLoom
- ActionLLM rates staleness and extracts outdated claimsOpenAI
- LogicDrop low-risk, keep flagged-outdated videos
- OutputOpen Linear refresh issue with checklistLinear
What it does
It does the judgment work on aging Loom walkthroughs: pulling the transcript, reasoning about whether the content has likely drifted out of date, and opening a scoped refresh task only for the ones that actually need re-recording.
When to use it
Use it when your stale backlog is large and you do not want to manually rewatch every clip to decide what to redo. Best for product, support, or enablement teams whose walkthroughs reference fast-changing UI, pricing, or process that silently goes stale.
How it works
- 1A schedule kicks off the periodic sweep.
- 2It lists Loom videos older than the threshold with low view counts and fetches each one's transcript.
- 3An LLM step reads the transcript and rates likely staleness, returning a verdict plus the specific outdated claims it spotted.
- 4A logic branch drops low-risk videos and keeps the ones flagged as outdated.
- 5For each flagged video it creates a Linear issue containing the suspect claims and a re-record checklist, linking back to the original recording.
Set it up
What you configure once, before turning it on.
- 1Connect LoomVideo transcripts, libraries.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Personal Productivity workflows
Log Outlook promises to Airtable with per-recipient commitment rollups
Captures promises from sent Outlook mail into an Airtable base, linking each commitment to a recipient record so you get a running per-contact view of everything you've promised…
Turn Outlook email promises into assigned Asana tasks with due dates
When you send an email containing a commitment, an LLM extracts the promise and its deadline and creates a corresponding Asana task assigned to you with the due date set.
Auto-decline low-priority invites that collide with deep-work blocks
When a new calendar invite lands on top of a protected deep-work block, an AI scores its priority and auto-declines low-value meetings with a polite note proposing alternative…
Decline focus-block meetings and auto-propose a free slot via Notion log
When a low-priority invite hits a focus block, it declines the meeting, finds your next genuinely free slot, replies with a counter-proposal.
Monthly Meeting Cost Report by Email
On the first of each month, tallies every recurring meeting's total person-hours across the team, converts to an estimated dollar cost.
Auto-create weekly focus blocks around existing meetings and guard them
Every Sunday an agent reads next week's confirmed meetings, carves protected deep-work blocks into the open gaps, sets your Slack status to defend them.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.