DEVOPS
Weekly Replicate Cold-Start Trend Report to BigQuery
Each week it pulls Replicate prediction history, computes cold-start frequency and latency percentiles, writes the rollup to BigQuery.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule
- ActionPage through week of Replicate predictionsReplicate
- LogicCompute cold-start rate + latency percentiles vs last week
- ActionAppend weekly rollup to BigQuery tableBigQuery
- OutputPost trend digest to SlackSlack
What it does
This workflow gives you the data to decide whether a warm pool or dedicated instance is worth it. Weekly, it aggregates Replicate cold-start behavior — how often workers booted cold, p50/p95 cold-start latency, and how that compares to last week — then persists the rollup to BigQuery and shares a human-readable digest.
When to use it
Use it for capacity and cost planning on Replicate endpoints. When you need evidence to justify (or retire) always-on capacity, this builds the longitudinal record warm-pool tuning decisions should rest on.
How it works
A weekly scheduled trigger starts the run. An action pages through the past week of Replicate predictions, collecting boot and predict timings. A logic step computes cold-start counts and latency percentiles and compares them to the prior week's stored values. An action appends the weekly rollup row to a BigQuery table for long-term trend analysis. Finally the flow posts a Slack digest with the headline numbers, the week-over-week delta, and a recommendation flag when cold starts trend worse.
Set it up
What you configure once, before turning it on.
- 1Connect ReplicateImage, video, and model inference.
- 2Connect BigQueryDatasets, queries, schemas.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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 DevOps workflows
Block costly Hugging Face Space hardware upgrades in PR review
When a pull request changes a Space's hardware config, it estimates the new monthly cost and posts a GitHub PR comment that flags upgrades crossing a budget ceiling.
Auto-spin a Zoom war-room when PagerDuty hits SEV-1
When a PagerDuty incident escalates to a critical severity, this workflow creates a dedicated Zoom meeting and posts the bridge link to the incident's Slack channel so responders…
Page on-call when a Hugging Face Space build is stuck or errored
Polls Hugging Face Space runtime status on a schedule and opens a PagerDuty incident when a Space sits in a build or error state past a deadline, with a Slack heads-up.
Slack-approved pause for idle Hugging Face Spaces
On a daily scan it finds idle paid Spaces and posts an interactive Slack approval; on approve it pauses the Space and logs the decision to a GitHub issue audit trail.
Hugging Face Spaces idle-runtime sweep with auto-pause
On a schedule, scans all Hugging Face Spaces for ones running idle past a threshold, pauses them to stop billing, and posts a Slack summary with the estimated monthly savings.
Open a Zoom war-room from a Datadog multi-alert storm
When a Datadog monitor crosses a critical threshold, this workflow dedupes against active incidents, and only for a genuinely new outage it creates a Zoom bridge.
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.