← All implementations

Slack · Supporting pattern

Multi-agent context system

Slack's engineering team runs an agentic service that investigates security alerts. A Director agent orchestrates rounds, Expert agents gather evidence, and a Critic scores each finding for credibility. Instead of message history, three written channels carry the state between rounds.

1 Supports2 Supports

Supporting infrastructure

This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a supporting pattern. The record also reports a workflow.

Approach type
Supporting pattern
Work
Research
Human involvement
Human in loop
Deployment stage
Research
Evidence strength
Mixed
Entry reviewed

How it works

The workflow the sources report for this implementation.

Where people stay involved

  • long-running investigation → synthesized reportUnknown · Level unknown

Unclassified for long-running investigation → synthesized report; human attention boundary: unknown.

1

Observation date
2026

Implementation details

Harness

Coordinator/dispatcher: a central coordinator dispatches to expert agents and to critic agents

1 Supports2 Supports

Tool access

Expert agents produce reports; critic agents evaluate them using evidence-inspection tools

1 Supports2 Supports

Context management

Three channels; Director's Journal (working memory), Critic's Review (credibility-weighted findings), Critic's Timeline (deduped chronological synthesis)

1 Supports2 Supports

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Reported metrics

Headline claim

Context management for security investigations spanning hundreds of inference requests and megabytes of output

1 Supports2 Supports

The source does not report the denominator of this figure.

Reported by
Slack
Scope
Complex security investigations requiring tailored multi-agent context; qualitative workload scale
Key observation

Handles multi-agent runs spanning hundreds of requests and megabytes of output

1 Supports2 Supports

The source does not report the denominator of this figure.

Reported by
Slack
Scope
Complex security investigations requiring tailored multi-agent context; qualitative workload scale

Lessons and interpretation

Don't pass all information at every step; build structured summaries agents can reliably build on

1 Supports2 Supports

Separate expert agents (produce) from critic agents (evaluate); corroborated findings are prioritized

1 Supports2 Supports

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.

  1. Managing context in long-running agentic applicationshttps://slack.engineering/managing-context-in-long-run-agentic-applications/Engineering blog · First party · Last source verification: 2026-08-31
  2. How Slack manages context in long-running multi-agent systemshttps://www.infoq.com/news/2026/04/slack-agent-context-management/News · Independent secondary · Last source verification: 2026-08-31
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  2. Headline claim
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Slack
    Scope
    Complex security investigations requiring tailored multi-agent context; qualitative workload scale
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  3. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  4. Model
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  5. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  6. Context management
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  7. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  8. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  9. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  10. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Slack
    Scope
    Complex security investigations requiring tailored multi-agent context; qualitative workload scale
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  11. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  12. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  13. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  14. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Unverified
    Confidence reason
    The research pattern documents agent coordination and criticism but not the normal human attention boundary.
    Observation date
    2026

The catalog records no related implementation for this entry yet.