📄️ Task Graphs and Branching
Bosun tasks can be expressed as graphs so you can branch, merge, and conditionally skip steps without writing imperative control flow. The manifest still lists the individual steps, but you describe how they connect by declaring start and end nodes plus the transitions between them.
📄️ Variables
Variables are fundamental to creating dynamic and interconnected Bosun workflows. They allow you to store and reference data throughout your tasks, enabling complex logic and data flow between different steps and agents.
📄️ Templating
Bosun workflows use a templating system to create dynamic, repeatable, and flexible tasks. Templating allows you to inject values, manipulate data, and generate instructions or configurations on the fly, making your workflows adaptable to various scenarios without hardcoding every detail.
📄️ Creating and Updating Pull Requests
Bosun workflows automate pull request (PR) creation and updates so larger changes stay visible, reviewable, and versioned without manual intervention.
📄️ Agentic Tools and Toolboxes
Bosun agents interact with your codebase and external services through specialized tools organized into toolboxes. Each toolbox gates a set of capabilities, giving you fine-grained control over what an agent may do.
📄️ Code Environment
In Bosun, a "code environment" is the isolated space where your automated tasks, specifically the code written or modified by agents, are executed. This environment provides a secure and consistent setting for all operations.
📄️ Usage Metrics
Bosun records model usage for every session so you can keep an eye on cost, performance, and capacity planning.
📄️ Billing and Credits
Bosun tracks billing at the organization level. Only members with the billing admin permission can access and manage billing settings. If you do not see the Billing screen in the app, contact an admin for access.
📄️ Custom Schemas
Define structured stop/fail payloads and structured prompt responses in Bosun manifests.
📄️ Error handling
Bosun's runtime surfaces step failures immediately, but you control whether those failures should stop the task. Every step honours the continueonerror flag so you can keep the workflow moving while still recording detailed diagnostics.