# Lou Bichard on Agent Swarms and the Missing Primitive _Lou Bichard of Ona discusses the challenges of agent swarms, the missing coordination primitive, and the future of software factories powered by AI agents._ **Published:** 2026-05-23 **Source:** https://www.startuphub.ai/ai-news/artificial-intelligence/2026/lou-bichard-on-agent-swarms-and-the-missing-primitive --- Lou Bichard, Field CTO at Ona, presented "The Missing Primitive for Agent Swarms" at AI Engineer Europe. Bichard discussed the challenges and solutions in building software factories powered by AI agents. He highlighted the need for better coordination mechanisms to manage the complex interactions and workflows inherent in agent swarms. Software Factories VisionContext automating software development lifecycle incrementallyFrom the article 2 mentionsBichard discussed the challenges and solutions in building software factories powered by AI agents.usesAI Agent SwarmsCoremultiple coding agents working together on tasksFrom the article 9+ mentionsLou Bichard, Field CTO at Ona, presented "The Missing Primitive for Agent Swarms" at AI Engineer Europe.createsCoordination ProblemDriverFrom the article 4 mentionsHe highlighted the need for better coordination mechanisms to manage the complex interactions and workflows inherent in agent swarms.due toMissing PrimitiveDriverlack of a fundamental mechanism for agent coordinationFrom the article 4 mentionsBichard identified coordination as the "missing primitive" in the current landscape of agent swarms.State MachinesContextpotential solution for structured agent communicationFrom the article 3 mentionsLooking ahead, Bichard suggested that state machines are a promising primitive for agent workflows, allowing agents to work with explicit states and transitions.CLI ToolsContextfuture development for managing agent swarmsFrom the article 3 mentionsHe also highlighted the importance of packaging these workflows as CLI tools.Improved OrchestrationEffectenabling proactive work without direct human engagementFrom the article 2 mentionsThis involves not just individual agents but also the orchestration of multiple agents working in concert. Bichard began by framing the current industry trend towards building "software factories." He defined this as a commitment to incrementally moving human involvement out of the loop across the entire software development lifecycle (SDLC). The goal is for work to proactively happen when humans are not directly engaged. ## The Vision for Software Factories The concept of a software factory envisions a highly automated process for software development. Bichard noted that many companies are exploring ways to leverage coding agents and apply them across the SDLC. This involves not just individual agents but also the orchestration of multiple agents working in concert. He illustrated this with examples of how agents can be used for various tasks, from planning and coding to review and deployment. The goal is to create a system where agents can autonomously handle complex tasks, minimizing the need for human intervention at every step. ## Background Agents and Their Roles Bichard introduced the concept of "background agents," which he described as autonomous entities that can perform tasks within an organization's infrastructure. He showcased different patterns of agent behavior: swarms where agents converge on a single result, fleets where agents work in parallel across repos, event-driven agents triggered by specific events, and scheduled agents for routine tasks. He emphasized that the platform Ona is building is designed to facilitate these background agents. The platform provides agents with isolated development environments, allowing them to execute tasks without interfering with each other or the broader system. This isolation is key for ensuring reliability and reproducibility. ## The Coordination Problem A significant challenge in building effective agent swarms is the lack of a robust coordination layer. Bichard pointed out that while tools like GitHub are essential for code management, they are not designed to handle the complex interdependencies and state management required for coordinating multiple autonomous agents. He explained that GitHub's pull request system, while useful for human collaboration, becomes overly noisy and difficult to manage when dealing with numerous automated agent interactions. The sheer volume of automated tasks, potential conflicts, and the need for precise state tracking makes existing tools inadequate. ## What is Missing: Coordination Primitives Bichard identified coordination as the "missing primitive" in the current landscape of agent swarms. He elaborated on the four key primitives needed for effective agent systems: runtimes (which are largely solved), orchestration (partially solved), triggers (solved), and coordination (missing). He stressed that while individual agents and their execution environments (runtimes) are becoming more mature, the ability for these agents to effectively collaborate, communicate, and manage shared context remains a significant hurdle. The industry is still in the early stages of building solutions for this critical aspect of agent swarms. ## The Future: State Machines and CLI Looking ahead, Bichard suggested that state machines are a promising primitive for agent workflows, allowing agents to work with explicit states and transitions. This approach provides a more structured and manageable way to define agent behavior and interactions. He also highlighted the importance of packaging these workflows as CLI tools. This allows for greater composability, scriptability, and version control, making it easier to manage and deploy complex agent systems. The goal is to create an environment where agents can operate autonomously and reliably, contributing to a more automated software factory. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.