Skip to main content
Auto-investigations let Edgedive monitor your connected sources and automatically investigate new alerts, issues, or tasks—without anyone needing to @mention or assign Edgedive.
SourceTriggerScope
SlackNew messages in monitored channelsInvestigation channels
LinearNew issues createdDefault team
AsanaNew tasks createdActive projects
Auto-investigations work best when combined with keyword filtering to focus on the alerts that matter most. See Keyword Filtering below.

Slack

Slack auto-investigation monitors messages in your configured investigation channels and uses AI classification to determine which messages warrant an investigation.
1

Go to Connections

Navigate to Connections and find your Slack integration
2

Open Manage

Click Manage on the Slack connection card
3

Configure investigation channels

Select the channels Edgedive should monitor for alerts (e.g., #prod-alerts, #sentry-errors)
4

(Optional) Add keyword filters

Configure include/exclude keywords to control which messages trigger investigations. See Keyword Filtering.

How It Works

  1. A new message arrives in a monitored investigation channel
  2. If keyword filters are configured, Edgedive checks the message against your rules
  3. If no keyword filters are set, Edgedive uses AI classification to determine if the message is an actionable alert
  4. Qualifying messages trigger an automatic investigation
Edgedive ignores bot messages from itself and messages in threads to avoid duplicate investigations.

Linear

Linear auto-investigation monitors new issues created in your configured default team.
1

Go to Connections

Navigate to Connections and find your Linear integration
2

Open Manage

Click Manage on the Linear connection card
3

Select a default team

Choose the team whose issues Edgedive should monitor
4

Enable auto-investigation

Toggle Auto-investigate new issues on
5

(Optional) Add keyword filters

Configure include/exclude keywords to focus on specific issue types. See Keyword Filtering.

How It Works

  1. A new issue is created in your configured default team
  2. Edgedive checks the issue title and description against your keyword filters (if configured)
  3. If keywords match (or no keywords are set), Edgedive creates an investigation
  4. Results are posted as a comment on the Linear issue
Auto-investigation only monitors the default team configured in your Linear settings. Issues in other teams are not monitored.

Asana

Asana auto-investigation monitors new tasks created in your active projects.
1

Go to Connections

Navigate to Connections and find your Asana integration
2

Open Manage

Click Manage on the Asana connection card
3

Select active projects

Choose which projects Edgedive should monitor
4

Enable auto-investigation

Toggle Auto-investigate new tasks on
5

(Optional) Add keyword filters

Configure include/exclude keywords to focus on specific task types. See Keyword Filtering.

How It Works

  1. A new task is created in one of your active Asana projects
  2. Edgedive checks the task name and description against your keyword filters (if configured)
  3. If keywords match (or no keywords are set), Edgedive creates an investigation
  4. Results are posted as a comment on the Asana task

Keyword Filtering

Keyword filtering gives you precise control over which messages, issues, or tasks trigger auto-investigations. When keywords are configured, they bypass AI classification entirely—matching is deterministic and instant.

Include Keywords

Messages containing any include keyword will trigger an investigation.
error
OOMKilled
pod*crash
deployment failed

Exclude Keywords

Messages matching any exclude keyword are skipped, even if they match an include keyword. Use these to filter out noise.
staging
test-alert
resolved
bot-message

Matching Rules

RuleExample KeywordMatches
Case-insensitiveerror”Error”, “ERROR”, “Runtime error”
Substring matchingcrash”pod crash detected”, “crashloop”
Wildcard (*)pod*crash”pod crash”, “pod-crash”, “pods crashing”
Multiple wildcards*OOM*”OOMKilled”, “Go OOM error”

How Keywords Interact

Include KeywordsExclude KeywordsBehavior
ConfiguredConfiguredMust match an include keyword and not match any exclude keyword
ConfiguredNot configuredMust match at least one include keyword
Not configuredConfiguredInvestigated unless an exclude keyword matches
Not configuredNot configuredAI classification (Slack) or all items investigated (Linear, Asana)
When no keywords are configured but auto-investigation is enabled, Edgedive falls back to AI classification (Slack) or investigates all new items (Linear, Asana).

Configuration

Keywords are configured per-source in each integration’s Manage modal:
  1. Open Connections → click Manage on the integration
  2. Scroll to Keyword Filtering
  3. Enter one keyword per line in the Include Keywords or Exclude Keywords fields
  4. Save your changes

Examples

Include:
production
critical
P0
incident
Exclude:
staging
development
test

Best Practices

Start with keywords

Begin with a few high-signal include keywords rather than monitoring everything. Expand as you gain confidence.

Use exclude keywords for noise

Filter out staging alerts, test messages, and resolved notifications to keep investigations focused.

Scope to specific teams/projects

For Linear and Asana, select only the teams and projects that contain actionable engineering issues.

Review and refine

Check your investigation history periodically and adjust keywords to reduce false positives.
Need help configuring auto-investigations for your workflow? Reach out at team@edgedive.com.