Frequently asked questions
Runsight is a YAML-first workflow engine designed specifically for AI agents. It allows users to design agent workflows visually, with the canvas writing YAML directly to your filesystem. This means you can commit, diff, and review it in pull requests just like any other code. A unique feature of Runsight is its ability to pause a running agent, edit the prompt, and resume without needing to redeploy. This is particularly useful for engineering teams that require version control and the ability to manage processes effectively. Additionally, Runsight offers per-run cost tracking, allowing users to know the cost of each agent call before receiving an invoice.
Using a YAML-first workflow engine like Runsight provides several benefits. Firstly, it integrates seamlessly with version control systems, allowing teams to manage workflows as code. This enhances collaboration and code review processes. Secondly, the ability to pause and inspect workflows while they are running allows for real-time troubleshooting and adjustments, which can significantly reduce downtime. Lastly, the per-run cost tracking feature helps teams manage their budgets effectively by providing transparency on the costs associated with each agent call.
Runsight is designed primarily for engineering teams that run AI agents in production environments. These teams require a high level of rigor in their workflows, similar to what they apply to software development processes. The features of Runsight, such as version control, code review, and runtime intervention, cater specifically to the needs of technical teams looking to automate and streamline their business processes.