Auto-triage

A persistent Opulent that monitors a Slack channel, inbox, or ticket queue and automatically triages incoming issues

Auto-triage is a special type of automation where a persistent Opulent monitors an incoming stream — a Slack channel, a shared inbox, or a ticket queue — and automatically classifies and routes work as it arrives. Instead of manually assigning someone to look at every report, an Autonomous Knowledge Worker watches the source around the clock, decides what needs attention, and spawns focused child sessions to diagnose or resolve each item.

Auto-triage has long-term memory — it accumulates context over time and learns from you via its scratchpad. It intelligently deduplicates repeated reports and automatically routes each issue to the right owner.

How it works

A long-running parent session monitors your channel and listens to every new message. It filters out noise, detects duplicates, and spawns focused parallel child sessions to investigate actionable issues. Each child reads the relevant code or source material, traces the root cause, posts a diagnosis in the thread, and tags the right owner.

Setting up auto-triage

1. Invite Opulent to the Slack channel you want monitored (e.g. #bugs, #incidents)
2. Go to Automations and create a new automation using the Triage bug reports on Slack template
3. Select the channel and save

That's it — Opulent will start watching the channel and triaging incoming messages.

Customizing behavior

Setup prompt

The setup prompt lets you customize how the triage session behaves. This is injected into the agent's instructions and influences how it handles incoming messages. Examples:

• "Focus on regressions in the payments service. For frontend bugs, tag the UI team."
• "Only investigate issues that include error logs or stack traces. Ask for more details if the report is vague."
• "When you find a root cause, always include a link to the relevant source file."

Connectors

Connect approved connectors to give the triage session access to external tools. For example:

• Datadog — Pull metrics, logs, and traces to correlate issues with runtime behavior
• Sentry — Look up error details, stack traces, and affected users
• Linear — Check for related tickets or create new ones

Enable connectors in Settings > Connections before setting up the automation.

The scratchpad

The parent monitor and all child sessions share a persistent scratchpad. This is used to:

• Track recently triaged items (channel ID, message timestamp, reporter)
• Maintain a routing table mapping areas to owners
• Record duplicate items so future reports can be linked to existing threads
• Store context that persists across restarts

The scratchpad is the automation's long-term memory. The parent is primarily responsible for maintaining it, but children can read it for context and update it when they discover new information (e.g. someone says "that's not my area").

Security

Since incoming messages can contain untrusted user input (e.g. from support tickets), consider enabling a network policy to restrict outbound access for your auto-triage automation.

Limits

Like all automations, auto-triage supports usage limits and invocation limits to control resource usage. Each child session spawned by the parent counts as a session against your usage budget.

Tips for effective auto-triage

• Start with a focused source. Pick a channel dedicated to bug reports rather than a general engineering channel. Less noise means better signal.
• Set clear expectations in the setup prompt. Tell Opulent what kinds of issues to prioritize and what to ignore.
• Connect relevant connectors. Datadog, Sentry, and other observability tools dramatically improve triage quality by giving Opulent access to runtime data.
• Correct routing mistakes. When Opulent tags the wrong person, reply in the thread with a correction. The parent updates its routing table and gets it right next time.