How to Set Up AI Agents in 2026 (Use this FREE AI Tool)
For AI filmmakers scaling production operations, setting up autonomous agents with persistent memory and precise operational boundaries streamlines daily research, scheduling, and asset management tasks.
What this lesson covers
This tutorial demonstrates how to generate a custom soul configuration file using the free Ordain tool to establish behavior and independence limits for an AI agent. It also outlines deploying the Hermes agent framework on a Hostinger cloud server integrated with OpenRouter for model access.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:36 ↗
AI agent output quality heavily depends on the underlying system configuration file (the 'soul file') that dictates behavioral rules and autonomy.
- 1:40 ↗
The Ordain tool automates the creation of a structured `soul.md` file by customizing agent roles, communication tone, and independence levels.
- 2:36 ↗
Setting an agent's autonomy to 'handle small stuff, ask for big things' prevents workflow friction while maintaining supervisory control over major decisions.
- 4:15 ↗
Running an agent on a dedicated cloud VPS prevents execution disruption caused by local machine sleep states and complex local SSH setups.
- 6:28 ↗
Connecting an agent through OpenRouter allows seamless switching between different foundational AI models using a unified API key with hard spending caps.
Workflow outlined in the video
- Access Ordain and select the agent framework (such as Hermes) to generate a customized `soul.md` file defining tasks, persona, and autonomy levels.
- Review and refine the generated markdown soul document, then download it locally.
- Provision a VPS instance on Hostinger (e.g., KVM2 tier) configured with the Hermes agent environment.
- Open the Hostinger server terminal, navigate to the Hermes directory, and initiate the interactive setup wizard.
- Create an OpenRouter account, set a strict monthly credit spending cap, generate an API key, and link it during the Hermes setup process.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
How to interpret the numbers
47,044 views captured 27 September 2026. ReelStack recommendation score: 53/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 2.29× views vs 3 other channel videos observed at a similar age. View-evidence factor 98% (views / (views + 1,000))
- 25% freshness: 34/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 3/100; likes + 4× comments, smoothed with a 500-view neutral prior