Coding Agents Lunch & Learn – Session 12: Hermes, Sandboxes & Advanced Agent Workflows

In Session 12 of Coding Agents Lunch & Learn, we’ll explore practical workflows and infrastructure patterns powering modern AI coding agents. This session will feature a deep dive into Hermes, sandboxed execution environments, and the tooling that enables safer and more scalable agent-driven development.

We’ll also open up the discussion around advanced developer workflows, including skill evaluations, Git worktrees, multi-agent experimentation, isolated environments, and techniques teams are using to manage increasingly autonomous coding systems in production.

As always, this will be a collaborative and interactive session focused on real-world experimentation, practical lessons, and open discussion between developers building with AI agents every day.

Topics include:

Hermes and agent orchestration workflows

Sandboxed execution environments for coding agents

Skill evaluations and agent benchmarking

Git worktrees and parallel development workflows

Multi-agent experimentation and tooling

Open discussion and community Q&A

Whether you’re actively building agentic developer tools or exploring advanced AI-assisted engineering workflows, this session is designed to share practical insights you can immediately apply to your own projects.