Skip to main content
Raindrop Triage is your all-in-one agent for everything happening inside your AI app. Ask it anything about your agents and it deep-dives the events, explains why they’re happening, helps you track the behavior going forward, and tells you what to fix, every answer grounded in the real conversations that prove it.

​
How it works

You reach Triage in three places, and it brings the same investigation toolkit to each:
  • Slack: @Raindrop from any channel and continue in-thread.
  • Web: chat with Triage from inside the Raindrop app.
  • MCP: your coding agent (Claude Code, Cursor, Codex, etc.) can call it too. See the MCP overview.

​
Roles and permissions

  • The Triage Agent requires a paid plan. Issue Detection and Stumbles additionally require the Pro plan; without it, Triage still investigates using signals, events, and conversations.
  • Changing the org-wide conversation scope (Settings → Triage Agent → Use all projects) is limited to Owner and Admin. See Project scope.

​
Using the Triage Agent

​
Ask a question

@mention Raindrop with a question. Triage runs the investigation, replies in thread with examples and a hypothesis, and keeps context across follow-ups (“is this still happening?”, “didn’t we fix it last week?”) so you can keep poking until you understand the issue. For broad questions such as “what issues happened today?”, Triage checks both Issue Detection reports for broader distribution changes and Stumbles for individual interactions where something bad happened.
@mention Raindrop in Slack
A few things to try:
  • @raindrop how's the rollout on flag checkout-v2?
  • @raindrop is this still happening? (with a screenshot of a customer complaint)
  • @raindrop what are the top issues affecting enterprise customers this week?
Every answer grounds in real conversations you can click into.

​
Schedule investigations with Agent Briefs

Agent Briefs are scheduled investigations Triage runs on a cadence and posts back to Slack. Describe what you want investigated and when, and Triage saves the prompt, the schedule, and the destination, then runs the investigation against fresh data on every tick.
Agent brief delivered to Slack
Two ways to create one:
@mention Raindrop with a scheduling request. Triage will confirm and save it.
Prefixing with Remind me: also works:
What’s configurable:
  • Prompt: the investigation Triage runs each tick (e.g. “summarize tool error rates each morning”)
  • Schedule: a standard 5-field cron expression, running at most once every 3 hours. Common cadences like daily, weekly, or weekday-only are inferred from natural language
  • Timezone: defaults to your org’s default timezone
  • Channel: Slack channel to post to (or your DM)
  • Status: active or paused, plus a Run now action
Common briefs teams set up:
  • Summarize tool error rates each morning
  • Weekly, show me which users churned last week and what issues they hit
  • Every Monday, highlight any new use cases from last week
  • Every day until Friday, report on the checkout-v2 rollout

​
Get a Daily Digest

There’s a built-in Daily Digest that ships out of the box: a morning summary of patterns and changes from the day before. Toggle it on at Settings → Notifications. Compact mode posts one-liners with details in-thread.

​
Set custom monitors

Set thresholds on any signal (error rate, frustration rate, a custom classifier) and Raindrop pings the channel when the threshold is crossed. Configure them at Settings → Notifications under Signal Alerts, or ask Triage in Slack to set one up. See Alerts for the full configuration options.
Custom monitors

​
Create signals from chat

When an investigation surfaces a pattern worth tracking going forward, ask Triage to track it and it’ll draft a signal for you, no leaving the conversation.
Triage scopes the behavior, generates a code signal (a small sandboxed function that labels matching events), and seeds it with examples it just found. You confirm or tweak a few matches in the app, and Raindrop saves it to run over every future event and backfills recent history so you get counts right away. You can refine in chat too: “only count negative mentions”, “tighten this to LinkedIn URLs only”, and Triage regenerates the signal and re-samples. See Signals for the full set of signal types and how they work end-to-end.

​
Fix issues in your coding agent

Triage is also available as an MCP server, so Claude Code, Cursor, Codex, and any other MCP-compatible coding agent can call it directly. Your agent pulls a live issue from production, reads the failing examples, edits the relevant file, runs tests, and opens a PR, all without leaving your editor.
See the MCP overview for setup instructions for each editor.

​
Reference

​
Project scope

Triage operates within your projects. A conversation reads and writes one project’s data at a time, or runs across all projects at once, depending on the surface and your settings: When a conversation runs across all projects, creating something project-scoped (a signal, an Agent Brief, an alert) first asks which project it should live in.

​
Troubleshooting

Triage says Issue Detection or Stumbles isn’t available. Both require the Pro plan. Triage keeps investigating with signals, events, and conversations in the meantime. See Roles and permissions. Triage can’t see data you expected. Check the conversation’s project scope. A project-scoped chat only reads that one project, so switch projects or widen the scope. See Project scope. @Raindrop doesn’t respond in Slack. Confirm Raindrop is installed and has been invited to the channel. See Get started.

​
Get started

1

Install

Add Raindrop to Slack with one-click OAuth. No infra to run.
2

Pick channels

Choose where Triage posts proactive alerts, monitors, and Agent Briefs at Settings → Notifications.
3

Ask

@mention Raindrop with a question, or schedule an Agent Brief.
For coding-agent setup, see the MCP overview. Raindrop uses AI to generate issue analyses, digests, and conversational responses. AI-generated content may be inaccurate, incomplete, or misleading. Always verify critical information independently before making decisions based on Raindrop’s outputs. Triage is a tool to assist your team, not a replacement for human judgment.