AI AGENTS
AI Inbox Triage with Auto-Drafted Replies
Watches your Gmail inbox, classifies each new message by intent and urgency, and writes a ready-to-send draft reply for the routine ones while flagging anything that needs your…
How it runs
The automated pipeline, trigger to output.
- TriggerNew email arrives in GmailGmail
- ActionClassify intent and urgencyOpenAI
- LogicBranch: routine vs. needs-human
- ActionDraft reply in sender's threadGmail
- OutputEscalate ambiguous mail to SlackSlack
What it does
Every new email is read, classified, and either drafted or escalated. Routine messages (scheduling, FAQs, status pings) get a reply drafted directly in Gmail so you only review and hit send. Anything ambiguous or high-stakes is left untouched and surfaced to you with a one-line reason.
When to use it
For founders, account managers, or support leads who lose an hour a day to inbox cleanup but don't want an agent sending mail unsupervised. You keep final approval; the agent does the typing.
How it works
- 1A new email arriving in Gmail triggers the run.
- 2OpenAI classifies the message into an intent (scheduling, question, sales, no-reply) and an urgency score.
- 3A branch routes: routine + low-risk goes to drafting, everything else to escalation.
- 4For routine mail, OpenAI composes a reply in your voice using thread context.
- 5The draft is saved to the Gmail thread as an unsent draft for your review.
- 6Escalated messages post a short summary and reason to your Slack triage channel.
Set it up
What you configure once, before turning it on.
- 1Connect GmailRead, draft, send, label.
- 2Connect OpenAIModels, embeddings, files.
- 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 AI Agents workflows
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
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.