Internal bug-triage agent

Notion built a Custom Agent that turns Slack bug reports into routed tasks.

Company: Notion
Approach type: Agent
Work: Maintenance
Human involvement: Unknown
Invocation: Event-driven
Interfaces: Slack
Deployment stage: Deployed
Evidence strength: Detailed primary
Entry reviewed: 2026-09-17

Copy as MD Ask ChatGPT

How it works

Slack bug report → routed task and channel post.

Read a bug report

A bug report posted in Slack starts the workflow.^{[Source 1]}

Route the issue

The agent applies a routing constitution to identify the responsible team.^{[Source 1]}

Create and announce the task

It creates a task-database entry and posts to the team’s Slack channel.^{[Source 1]}

Where people stay involved

People review, approve, or guide the agent’s work here.

Not reported: The source does not establish the required human review boundary.

Supervision level
Not classified
- Slack bug report → routed task and channel post^{[Source 1]}

How supervision levels work

Implementation details

Model

Not reported

Harness

Notion Custom Agents.^{[Source 1]}

Sandbox

Not reported

Tool access

Not reported

Knowledge

Team-routing constitution.^{[Source 1]}

Context management

Not reported

Credentials

Not reported

Interfaces

slack

^{[Source 1]}

Validation and failure handling

Not reported: The available sources do not describe how the team checks the output.

Reported observations

Not reported

Lessons

Not reported: The available sources do not report lessons from this work.

Back to agents

Improve this record

Give your coding agent the context and instructions to prepare a source-backed update.

Suggest on GitHub

Paste the prompt into your coding agent, then describe the correction or add a public source.

Preview prompt

Help me update the Internal Agents Map record for Internal bug-triage agent at Notion.

Repository: https://github.com/steel-experiments/internal-agents-map
Record: data/agents/notion-bug-triage.yaml
Published record: https://internal-agents.com/agents/notion-bug-triage
Readable context: https://internal-agents.com/agents/notion-bug-triage.md

Use the correction or public source I provide in this conversation. If I have not supplied either, ask what I want changed before editing.

Use an existing checkout of this repository, or clone it if needed. Read the current record from the repository. Follow AGENTS.md, CONTRIBUTING.md, and the relevant instructions in data/schema.md.

Verify that the evidence supports the requested change. Preserve uncertainty and distinguish reported facts from catalog judgments. Follow the repository process for capturing new sources. If evidence is insufficient, explain the gap instead of inventing details.

Make a focused change on a branch. Regenerate derived files and run the required checks. Do not edit generated content by hand.

Show me the change, supporting evidence, and check results, including any checks you could not run. Ask whether to submit a pull request unless I already requested one. Do not merge the pull request. If you cannot edit the repository, prepare a source-backed issue draft.

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

Notion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)https://latent.space/p/notionPodcast · Direct participant · Last source verification: 2026-08-31
Preserved copy

Question coverage and scope

purpose: Reported
workflow: Reported
human involvement: Not reported: The source does not establish the required human review boundary.
implementation: Reported
validation: Not reported
observations: Not reported
lessons: Not reported

Research details for every claim on this page

Summary
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Harness
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Knowledge
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Interfaces
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Read a bug report
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Route the issue
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Create and announce the task
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow
Operating model assessment
Statement type
Inference
Provenance
Catalog judgment
Confidence
Unverified
Confidence reason
The source describes Internal bug-triage agent and its work, but does not establish whether a person must approve or inspect each successful output.
Observation date
2026-04-14
- SupportsNotion's Token Town: 5 Rebuilds, 100+ Tools (Latent Space)Interview 34:07: first internally built bug-triage workflow

How it works

Where people stay involved

Implementation details

Validation and failure handling

Reported observations

Lessons

Related reading

Infrastructure used

Sources and research details