How Slack Manages Context in Long-running Multi-agent Systems

How Slack Manages Context in Long-running Multi-agent Systems - InfoQ

[BT](http://www.infoq.com/int/bt/ "bt")

InfoQ Software Architects' Newsletter

A monthly overview of things you need to know as an architect or aspiring architect.

View an example

Enter your e-mail address

Select your country - [x] I consent to InfoQ.com handling my data as explained in this Privacy Notice.

We protect your privacy.

Close

QCon San Francisco (Nov 16-20): What's next in AI? What's next in software? Learn from the teams already doing it.Register Now

Close

Toggle Navigation

Facilitating the Spread of Knowledge and Innovation in Professional Software Development

English edition

• English edition
• Chinese edition
• Japanese edition
• French edition

[Write for InfoQ](http://www.infoq.com/write-for-infoq/ "Write for InfoQ")

Search

RegisterSign in

Unlock the full InfoQ experience

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources.

Log In

or

Don't have an InfoQ account?

Register

• **Stay updated on topics and peers that matter to you**Receive instant alerts on the latest insights and trends.
• **Quickly access free resources for continuous learning**Minibooks, videos with transcripts, and training materials.
• **Save articles and read at anytime**Bookmark articles to read whenever youre ready.

Logo - Back to homepage

NewsArticlesPresentationsPodcastsGuides

Topics

[Development](http://www.infoq.com/development/ "Development")

• [Java](http://www.infoq.com/java/ "Java")
• [Kotlin](http://www.infoq.com/kotlin/ "Kotlin")
• [.Net](http://www.infoq.com/dotnet/ ".Net")
• [C#](http://www.infoq.com/c_sharp/ "C#")
• [Swift](http://www.infoq.com/swift/ "Swift")
• [Go](http://www.infoq.com/golang/ "Go")
• [Rust](http://www.infoq.com/rust/ "Rust")
• [JavaScript](http://www.infoq.com/javascript/ "JavaScript")

Featured in Development

• #### From VR to Flat Screens: Bridging the Input and Immersion Gap

Dany Lepage discusses the architectural journey of porting a hit VR title to seven non-VR platforms. He explains how his team solved the challenges of cross-progression, diverse input paradigms, and maintaining release velocity across Steam, iOS, and PlayStation. Beyond the tech, he shares candid lessons on the "product fit" gap when translating immersive social presence to 2D screens.


All in developmentFollow Topic

[Architecture & Design](http://www.infoq.com/architecture-design/ "Architecture & Design")

• [Architecture](http://www.infoq.com/architecture/ "Architecture")
• [Enterprise Architecture](http://www.infoq.com/enterprise-architecture/ "Enterprise Architecture")
• [Scalability/Performance](http://www.infoq.com/performance-scalability/ "Scalability/Performance")
• [Design](http://www.infoq.com/design/ "Design")
• [Case Studies](http://www.infoq.com/Case_Study/ "Case Studies")
• [Microservices](http://www.infoq.com/microservices/ "Microservices")
• [Service Mesh](http://www.infoq.com/servicemesh/ "Service Mesh")
• [Patterns](http://www.infoq.com/DesignPattern/ "Patterns")
• [Security](http://www.infoq.com/Security/ "Security")

Featured in Architecture & Design

• #### How to Build an Exchange: Sub Millisecond Response Times and 24/7 Uptimes in the Cloud

Frank Yu shares Coinbase’s engineering philosophy for building resilient, fair, and fast financial exchanges. He explains the power of a single-threaded architecture combined with the Raft consensus algorithm to maintain 24/7 availability. He discusses how determinism enables zero-downtime rolling deployments and the ability to replay production logs for perfect bug reproduction.


All in architecture-designFollow Topic

[AI Infrastructure](http://www.infoq.com/ai-ml-data-eng/ "AI Infrastructure")

• [Big Data](http://www.infoq.com/bigdata/ "Big Data")
• [Machine Learning](http://www.infoq.com/machinelearning/ "Machine Learning")
• [NoSQL](http://www.infoq.com/nosql/ "NoSQL")
• [Database](http://www.infoq.com/database/ "Database")
• [Data Analytics](http://www.infoq.com/data-analytics/ "Data Analytics")
• [Streaming](http://www.infoq.com/streaming/ "Streaming")

Featured in AI, ML & Data Engineering

• #### CodeGuardian: A Model Context Protocol Server for AI-Assisted Code Quality Analysis and Security Scanning

CodeGuardian is an MCP server that extends AI coding assistants with comprehensive code quality and security analysis capabilities. By implementing eleven specialized tools, CodeGuardian enables developers to access enterprise-grade analysis directly through their AI assistant, eliminating context-switching and reducing friction in adopting secure coding practices.


All in ai-ml-data-engFollow Topic

[Culture & Methods](http://www.infoq.com/culture-methods/ "Culture & Methods")

• [Agile](http://www.infoq.com/agile/ "Agile")
• [Diversity](http://www.infoq.com/diversity/ "Diversity")
• [Leadership](http://www.infoq.com/leadership/ "Leadership")
• [Lean/Kanban](http://www.infoq.com/lean/ "Lean/Kanban")
• [Personal Growth](http://www.infoq.com/personal-growth/ "Personal Growth")
• [Scrum](http://www.infoq.com/scrum/ "Scrum")
• [Sociocracy](http://www.infoq.com/sociocracy/ "Sociocracy")
• [Software Craftmanship](http://www.infoq.com/software_craftsmanship/ "Software Craftmanship")
• [Team Collaboration](http://www.infoq.com/team-collaboration/ "Team Collaboration")
• [Testing](http://www.infoq.com/testing/ "Testing")
• [UX](http://www.infoq.com/ux/ "UX")

Featured in Culture & Methods

• #### Panel: Building a Culture that Works

The panelists share insights on evolving company culture. They discuss leveraging feedback loops, lending social capital, and the friction between legacy bureaucracy and agile engineering. The panel explains how to maintain cohesion in remote teams and use interviews to uncover the true "unmanicured" culture of a firm.


All in culture-methodsFollow Topic

DevOps

• [Infrastructure](http://www.infoq.com/infrastructure/ "Infrastructure")
• [Continuous Delivery](http://www.infoq.com/continuous_delivery/ "Continuous Delivery")
• [Automation](http://www.infoq.com/automation/ "Automation")
• [Containers](http://www.infoq.com/containers/ "Containers")
• [Cloud](http://www.infoq.com/cloud-computing/ "Cloud")
• [Observability](http://www.infoq.com/observability/ "Observability")

Featured in DevOps

• #### AI-Powered SRE for Autonomous Incident Response

The presenters discuss incident response, how AI-enhanced SRE platforms connect signals from logs, metrics, traces, and historical incidents to enable autonomous decisions.


All in devopsFollow Topic

[Events](https://events.infoq.com/ "Events")

Helpful links

• [About InfoQ](http://www.infoq.com/about-infoq "About InfoQ")
• [InfoQ Editors](http://www.infoq.com/infoq-editors "InfoQ Editors")
• [Write for InfoQ](http://www.infoq.com/write-for-infoq "Write for InfoQ")
• [About C4Media](https://c4media.com/ "About C4Media")
• [Diversity](https://c4media.com/diversity "Diversity")

Choose your language

• [En](http://www.infoq.com/news/2026/04/slack-agent-context-management/# "InfoQ English")
• 中文
• 日本
• Fr


[InfoQ Homepage](http://www.infoq.com/ "InfoQ Homepage")[News](http://www.infoq.com/news "News")How Slack Manages Context in Long-running Multi-agent Systems

[AI, ML & Data Engineering](http://www.infoq.com/ai-ml-data-eng/ "AI, ML & Data Engineering")

QCon San Francisco (Nov 16-20): Deep technical sessions. Peer conversations that change how you think.

How Slack Manages Context in Long-running Multi-agent Systems

Apr 28, 2026 2 min read

by

• Sergio De Simone

Follow

#### Write for InfoQ

**Feed your curiosity.**Help 550k+ global

senior developers

each month stay ahead.Get in touch

Log in to listen to this article

Audio ready to play

Your browser does not support the audio element.

0:00 0:00

Normal 1.25x 1.5x

Like

• Reading list

To sustain productivity in long-running agent systems, Slack engineers moved away from accumulating chat logs and started using structured memory, validation, and distilled truth to maintain coherence and accuracy of long-running agent systems.

While short LLM sessions do not usually require explicit context management, this becomes essential in long-running sessions to ensure coherence, as the growth of the message history makes it impractical to include the full context with each request:

Agent frameworks solve the state management problem for users by accumulating message history between API calls. This fills the agent’s context window, which provides a hard limit on how much information the agent can handle. Even approaching an agent’s context window limit can degrade the quality of responses.

As Slack staff software engineer Dominic Marks explains, one of Slack's multi-agent applications can span over hundreds of requests and generate megabytes of output. To manage this complexity, they followed an approach based on three complementary context channels: a director's journal, storing the director's structured working memory; a critic's review, storing an annotated findings report with credibility scores; and a critic's timeline, storing chronological findings with credibility scores.

!Image 12/filters:no_upscale()/news/2026/04/slack-agent-context-management/en/resources/1slack-image-1777407895831.jpg)

Slack's approach follows a _coordinator/dispatcher_ multi-agent design, where a central the coordinator acts as a decision maker, receiving requests and dispatching them to specialized agents further down the line, namely experts and critics.

Critics evaluate experts's work, as a portion of their findings "could either be invented or grossly misinterpret the data". They receive summary reports from experts and assess the evidence they contain. This evaluation is the basis for the creation of a scoring system used to identify findings corroborated by multiple sources.

The director's journal includes findings, observations, decisions, questions, and hypothesis, and "provides the common narrative that keeps other agents on track".

The critic's review acts as a truth filter using evidence inspection tools to build a credibility-weighted list of findings. To reduce the risk of hallucinations, critics are narrowly instructed to "only make a judgement on the submitted findings".

Finally, the critic's timeline builds a coherent narrative from the director's journal, the latest critic's review, and the previous timeline, retaining only credible evidence, removing duplicates, and resolving any conflicts by preferring strongest sources.

While Slack's approach is strictly tied to their system, it illustrates a broader principle: rather than passing all information at every step, they build structured summaries that agents can reliably build on. The three channels:

work together to maintain coherence across rounds, while preserving the benefits of specialized agent roles. The Director can make informed strategic decisions. Experts can build on previous understanding. The Critic can objectively evaluate findings.

This approach, Marks says, has proven effective in addressing the limitations of complex, long-running agentic applications. For full details and extensive examples, refer to the original article.

About the Author


#### **Sergio De Simone**

**Sergio De Simone** is a software engineer. Sergio has been working as a software engineer for over twenty five years across a range of different projects and companies, including such different work environments as Siemens, HP, and small startups. For the last 10+ years, his focus has been on development for mobile platforms and related technologies. He is currently working for BigML, Inc., where he leads iOS and macOS development.

Show more Show less

#### This content is in the AI, ML & Data Engineering topic

Follow Topic

##### Related Topics:

• Development### Development

Followers: 4091

Follow Topic

• Architecture & Design### Architecture & Design

Followers: 10213

Follow Topic

• AI, ML & Data Engineering### AI, ML & Data Engineering

Followers: 5881

Follow Topic

• Agents### Agents

Followers: 41

Follow Topic

• Slack### Slack

Followers: 5

Follow Topic

• Large language models### Large language models

Followers: 140

Follow Topic

* #### Popular in AI, ML & Data Engineering

• ##### Anthropic Introduces Agent-Based Code Review for Claude Code

• ##### AWS Announces General Availability of DevOps Agent for Automated Incident Investigation

• ##### Anthropic Introduces Managed Agents to Simplify AI Agent Deployment

• ##### Meta Reports 4x Higher Bug Detection with Just-in-Time Testing

• ##### Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents

* #### Related Sponsors

• ##### Data as a Competitive Moat: Architecting for Durability, Portability, and Control

• ##### Advance your architecture career with the InfoQ Certified Architect Program—practical, peer-driven certification

• ##### Shipping Faster, Breaking More: Rethinking Delivery Systems in the Age of AI (Live Webinar May 28th) - Save Your Seat

• ##### [[Webinar] Creating Certainty in the Age of Agentic AI. Watch On-Demand.](http://www.infoq.com/vendorcontent/show.action?vcr=531d8edd-4f74-486b-aaca-10058c609c1c&primaryTopicId=4523&vcrPlace=BOTTOM&pageType=NEWS_PAGE&vcrReferrer=https%3A%2F%2Fwww.infoq.com%2Fnews%2F2026%2F04%2Fslack-agent-context-management%2F)

• ##### Before it Breaks: AI-Driven Azure Incident Response

• #### Related Sponsor

**Online InfoQ Certified Architect Program**

Bring a real architecture challenge and work through it with senior peers in a 5-week online cohort. **Reserve Your Place.**

Related Content

• ##### Legare Kerrison and Cedric Clyburn on LLM Performance and Evaluations

Apr 28, 2026

• ##### Anthropic Introduces Managed Agents to Simplify AI Agent Deployment

Apr 21, 2026

• ##### Designing Memory for AI Agents: inside Linkedin’s Cognitive Memory Agent

Apr 20, 2026

• ##### Google ADK for Java 1.0 Introduces New App and Plugin Architecture, External Tools Support, and More

Apr 20, 2026

• ##### Google’s Aletheia Advances the State of the Art of Fully Autonomous Agentic Math Research

Apr 19, 2026

• ##### Meta Reports 4x Higher Bug Detection with Just-in-Time Testing

Apr 17, 2026

• ##### CNCF Warns Kubernetes Alone Is Not Enough to Secure LLM Workloads

Apr 17, 2026

• ##### Anthropic Introduces Agent-Based Code Review for Claude Code

Apr 17, 2026

• ##### Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents

Apr 16, 2026

Related Sponsors

• #### Stateful agents, stateful infra: The transport gap AI teams are patching by hand

Ably Realtime

• #### Does your AI stack need a session layer? A maturity framework for teams building AI agents

Ably Realtime

Related Content

• ##### Google Opens Gemma 4 Under Apache 2.0 with Multimodal and Agentic Capabilities

Apr 16, 2026

• ##### Cursor 3 Introduces Agent-First Interface, Moving beyond the IDE Model

Apr 16, 2026

• ##### Google’s TurboQuant Compression May Support Faster Inference, Same Accuracy on Less Capable Hardware

Apr 15, 2026

• ##### Anthropic Paper Examines Behavioral Impact of Emotion-Like Mechanisms in LLMs

Apr 14, 2026

• ##### Google Released Gemma 4 with a Focus on Local-First, On-Device AI Inference

Apr 13, 2026

• ##### Lyft Scales Global Localization Using AI and Human-in-the-Loop Review

Apr 13, 2026

Related Sponsors

• #### Does your AI stack need a session layer? A maturity framework for teams building AI agents

Ably Realtime

• #### Scalable Enterprise Java for the Cloud - Download the eBook

Payara

**The InfoQ** Newsletter

A round-up of last week’s content on InfoQ sent out every Tuesday. Join a community of over 250,000 senior developers. View an example

Enter your e-mail address

Select your country - [x] I consent to InfoQ.com handling my data as explained in this Privacy Notice.

We protect your privacy.

• Development

• ##### [QCon San Francisco 2026: 12 Tracks Announced](http://www.infoq.com/news/2026/04/qconsf-2026-tracks-announced/ "QCon San Francisco 2026: 12 Tracks Announced")

• ##### [Microsoft's Russinovich and Hanselman Warn AI Is Hollowing Out the Junior Developer Pipeline](http://www.infoq.com/news/2026/04/junior-developer-pipeline-crisis/ "Microsoft's Russinovich and Hanselman Warn AI Is Hollowing Out the Junior Developer Pipeline")

• ##### [C++26: Reflection, Memory Safety, Contracts, and a New Async Model](http://www.infoq.com/news/2026/04/cpp-26-reflection-safety-async/ "C++26: Reflection, Memory Safety, Contracts, and a New Async Model")

• Architecture & Design

• ##### [Uber Migrates 75,000+ Test Classes from Junit 4 to Junit 5 Using Automated Code Transformation](http://www.infoq.com/news/2026/04/uber-junit4-junit5-migration/ "Uber Migrates 75,000+ Test Classes from Junit 4 to Junit 5 Using Automated Code Transformation")

• ##### [How to Build an Exchange: Sub Millisecond Response Times and 24/7 Uptimes in the Cloud](http://www.infoq.com/presentations/exchange-systems-cloud/ "How to Build an Exchange: Sub Millisecond Response Times and 24/7 Uptimes in the Cloud")

• ##### [Dropbox Collaborates with GitHub to Reduce Monorepo Size from 87GB to 20GB](http://www.infoq.com/news/2026/04/dropbox-reduces-git-optimization/ "Dropbox Collaborates with GitHub to Reduce Monorepo Size from 87GB to 20GB")

• Culture & Methods

• ##### [How Observability and Telemetry Can Enhance the Practice of Software Engineering](http://www.infoq.com/news/2026/04/observability-telemetry/ "How Observability and Telemetry Can Enhance the Practice of Software Engineering")

• ##### [Panel: Building a Culture that Works](http://www.infoq.com/presentations/panel-positive-culture/ "Panel: Building a Culture that Works")

• ##### [Platform as a Product: Delivering Value While Balancing Competing Priorities](http://www.infoq.com/news/2026/04/platform-product-deliver-value/ "Platform as a Product: Delivering Value While Balancing Competing Priorities")

• AI, ML & Data Engineering

• ##### [How Slack Manages Context in Long-running Multi-agent Systems](http://www.infoq.com/news/2026/04/slack-agent-context-management/ "How Slack Manages Context in Long-running Multi-agent Systems")

• ##### [Google Cloud Introduces Agents CLI to Streamline AI Agent Development Lifecycle](http://www.infoq.com/news/2026/04/agents-cli-google-cloud/ "Google Cloud Introduces Agents CLI to Streamline AI Agent Development Lifecycle")

• ##### [Legare Kerrison and Cedric Clyburn on LLM Performance and Evaluations](http://www.infoq.com/news/2026/04/kerrison-clyburn-llm-performance/ "Legare Kerrison and Cedric Clyburn on LLM Performance and Evaluations")

• DevOps

• ##### [GitHub Uses eBPF to Eliminate Deployment Risks and Prevent Circular Failures](http://www.infoq.com/news/2026/04/github-ebpf-deployment/ "GitHub Uses eBPF to Eliminate Deployment Risks and Prevent Circular Failures")

• ##### [AI-Powered SRE for Autonomous Incident Response](http://www.infoq.com/presentations/ai-sre-incident-response/ "AI-Powered SRE for Autonomous Incident Response")

• ##### [Week-Long Outage: Lifelong Lessons](http://www.infoq.com/presentations/outage-lessons/ "Week-Long Outage: Lifelong Lessons")

**The InfoQ** Newsletter

A round-up of last week’s content on InfoQ sent out every Tuesday. Join a community of over 250,000 senior developers. View an example

• Get a quick overview of content published on a variety of innovator and early adopter technologies
• Learn what you don’t know that you don’t know
• Stay up to date with the latest information from the topics you are interested in

Enter your e-mail address

Select your country - [x] I consent to InfoQ.com handling my data as explained in this Privacy Notice.

We protect your privacy.

**May 7 | June 10, 2026 | Online** Architecture decisions are hard to validate while shipping. Join a **5-week online cohort** for **senior engineers, architects, and team leads** to pressure-test real decisions, apply practical frameworks, and work through challenges with a confidential peer group. Facilitated by Luca Mezzalira, Principal Architect at AWS, this cohort helps you: * Pressure-test real decisions. * Apply frameworks to real problems. * Publish on InfoQ.com and earn your certification. **RESERVE YOUR PLACE**

[Home](http://www.infoq.com/ "Home")[Create account](http://www.infoq.com/reginit.action "Create account")Log In[QCon Conferences](http://qconferences.com/ "QCon Conferences")Events[Write for InfoQ](http://www.infoq.com/write-for-infoq/ "Write for InfoQ")[InfoQ Editors](http://www.infoq.com/infoq-editors/ "InfoQ Editors")[About InfoQ](http://www.infoq.com/about-infoq/ "About InfoQ")[About C4Media](https://c4media.com/ "About C4Media")[Media Kit](https://get.infoq.com/infoq-mediakit/ "Media Kit")[InfoQ Developer Marketing Blog](https://devmarketing.c4media.com/?utm_source=infoq "InfoQ Developer Marketing Blog")[Diversity](https://c4media.com/diversity "Diversity")

#### Events

• ##### Online InfoQ Architect Certification

May 7, 2026

• ##### QCon AI Boston

June 1-2, 2026

• ##### Online InfoQ Architect Certification

June 10, 2026

• ##### QCon San Francisco

November 16-20, 2026

#### Follow us on

Youtube 232K FollowersLinkedin 26K FollowersInstagram NewRSS 19K ReadersX 57.1k FollowersFacebook 21K LikesBluesky New

#### Stay in the know

The InfoQ PodcastEngineering Culture PodcastThe Software Architects' Newsletter

General Feedback [feedback@infoq.com](mailto:feedback@infoq.com) Advertising [sales@infoq.com](mailto:sales@infoq.com) Editorial [editors@infoq.com](mailto:editors@infoq.com) Marketing [marketing@infoq.com](mailto:marketing@infoq.com)

InfoQ.com and all content copyright © 2006-2026 C4Media Inc.

Privacy Notice, Terms And Conditions, Cookie Policy

Close

[BT](http://www.infoq.com/int/bt/ "bt")