--- title: An Accidental Blackboard | daily.dev description: Thoughtworks engineers describe a four-day experiment where ten engineers used agentic AI coding tools in one monorepo to build a complex airline IROps system.... canonical: https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: An Accidental Blackboard | daily.dev og:description: Thoughtworks engineers describe a four-day experiment where ten engineers used agentic AI coding tools in one monorepo to build a complex airline IROps system.... og:url: https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv og:image: https://api.daily.dev/og/posts/ghSzC5IyV.png og:image:alt: An Accidental Blackboard og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # An Accidental Blackboard **[Martin Fowler](https://daily.dev/sources/mafo)** · 7 min read · 0 upvotes · 0 comments ## Summary Thoughtworks engineers describe a four-day experiment where ten engineers used agentic AI coding tools in one monorepo to build a complex airline IROps system. While tuning their commit and rebase discipline to fix build pipeline strain, they noticed agents began coordinating implicitly through shared plan files committed to the repo—rediscovering the decades-old blackboard system pattern (from Hearsay-II and tuple spaces). The author reflects that this coordination was emergent and accidental rather than deliberately engineered, and argues that a proper agent coordination channel should exist independently of source control. They announce a new side project, Talwrn, intended to be a purpose-built blackboard tool for agentic engineering. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is a blackboard system in the context of coordinating multiple AI coding agents? A blackboard system is a shared memory space where autonomous agents independently read and write tuples of structured data, using it to coordinate on a decomposed problem without direct communication. The concept traces back to the Hearsay-II system in 1980 and was formalized as the tuple space model by Gelernter et al. in 1986. Ten Thoughtworks engineers observed their coding agents spontaneously adopt this pattern by using shared plan files committed to a monorepo to signal progress and avoid duplicate work. _daily.dev surfaces patterns like blackboard coordination for teams experimenting with multi-agent coding setups._ ### Why did frequent git commits and rebases cause AI coding agents to start coordinating with each other? Requiring agents to continually commit and rebase from main, originally introduced to catch build failures early, had the side effect of exposing each agent's progress-tracking plan files to every other agent working in the same monorepo. Agents began marking plan lines as in-progress or complete, letting other agents detect when dependent work was finished and integrate it automatically, effectively turning the repo into a shared coordination blackboard. _developers tuning agentic workflows track these coordination quirks and workarounds on daily.dev._ ## Similar posts on daily.dev - [Agentic coding finally clicked when I wired it to a kanban board](https://daily.dev/posts/agentic-coding-finally-clicked-when-i-wired-it-to-a-kanban-board-8oagsdeet) · XDA Developers · 1 upvotes · 0 comments - [Towards self-driving codebases](https://daily.dev/posts/towards-self-driving-codebases-wcvkyhvlb) · Cursor · 1 upvotes · 0 comments - [Agent-driven development in Copilot Applied Science](https://daily.dev/posts/agent-driven-development-in-copilot-applied-science-38qqgozp2) · GitHub Blog · 10 upvotes · 0 comments --- Tags: [#general-programming](https://daily.dev/tags/general-programming), [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"An Accidental Blackboard","url":"https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv"},"datePublished":"2026-09-02T14:55:08.833Z","dateModified":"2026-09-03T07:25:05.989Z","description":"Thoughtworks engineers describe a four-day experiment where ten engineers used agentic AI coding tools in one monorepo to build a complex airline IROps system....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fdba2315927b3b3d7066d9703c986bf2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fdba2315927b3b3d7066d9703c986bf2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Martin Fowler","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Martin Fowler","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/mafo","url":"https://daily.dev/sources/mafo"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"general-programming,ai-agents,ai-coding","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Martin Fowler","item":"https://daily.dev/sources/mafo"},{"@type":"ListItem","position":3,"name":"An Accidental Blackboard"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/an-accidental-blackboard-ghszc5iyv#faq","mainEntity":[{"@type":"Question","name":"What is a blackboard system in the context of coordinating multiple AI coding agents?","acceptedAnswer":{"@type":"Answer","text":"A blackboard system is a shared memory space where autonomous agents independently read and write tuples of structured data, using it to coordinate on a decomposed problem without direct communication. The concept traces back to the Hearsay-II system in 1980 and was formalized as the tuple space model by Gelernter et al. in 1986. Ten Thoughtworks engineers observed their coding agents spontaneously adopt this pattern by using shared plan files committed to a monorepo to signal progress and avoid duplicate work. daily.dev surfaces patterns like blackboard coordination for teams experimenting with multi-agent coding setups."}},{"@type":"Question","name":"Why did frequent git commits and rebases cause AI coding agents to start coordinating with each other?","acceptedAnswer":{"@type":"Answer","text":"Requiring agents to continually commit and rebase from main, originally introduced to catch build failures early, had the side effect of exposing each agent's progress-tracking plan files to every other agent working in the same monorepo. Agents began marking plan lines as in-progress or complete, letting other agents detect when dependent work was finished and integrate it automatically, effectively turning the repo into a shared coordination blackboard. developers tuning agentic workflows track these coordination quirks and workarounds on daily.dev."}}]} ```