A concrete multi-profile YouTube workflow: Qwen → Hermes → GPT
A real-world example of chaining multiple agent profiles: first, a researcher agent running on Qwen (a local model) gathers information for the script. That research is handed off to Hermes, backed by an Opus 4.8 model, which writes the actual script. Finally, the finished script is passed to a GPT-based profile connected to the ChatGPT image generator, which builds the thumbnail. Each step uses the model best suited for that job — local and fast for research, high-quality reasoning for writing, and image-capable for visuals.
Go deeper with Greg Isenberg
Ask anything about this, and Greg Isenberg answers from everything they've shared.
More to learn
See everything in Learn
Setting up a recurring daily content ideas email with an AI agent
You can turn any thread or task in Hyper Agent into a recurring scheduled job simply by telling it in the thread: 'Can you turn this into a recurring daily email at 8 a.m.?' The agent will save the thread as an agent with a run schedule — e
How to use feedback to immediately improve AI content output
When you get feedback on an AI-generated output — say a tweet that sounds too formal — you have several options right away. You can update the underlying skill based on that feedback, have the agent immediately regenerate a new draft that s
MembersStiff AI-generated content can be fixed in real time through skill feedback loops
When reviewing AI-generated tweet drafts, Greg Isenberg noted a common quality problem: the output felt too formal and stiff rather than sounding friend-to-friend, which is the tone that tends to perform well on social media. The fix isn't