Automate scheduled GTM, research, and dev work
They used Hermes Agent to run recurring go-to-market, research, and development tasks, while Claude created GitHub issues that Opencode handled on a schedule.
- What they did
- The person divided the workflow between several tools. Claude, using Opus, handled planning and then filed GitHub issues, which Opencode, mostly powered by Deepseek, picked up on a set schedule. Hermes Agent ran a broad mix of scheduled jobs for go-to-market, research, and autonomous development loops, while Orca Dev was reserved for manual work.
- How it went
- Hermes became a mainstay in their setup, and the GitHub issue handoff into Opencode was described as easy and sturdy. They said the same approach in Openclaw unraveled and failed after about a week, so they abandoned it.
- Tips
- If you split work across agents, keep the handoff between planning and execution very simple. Also watch usage costs: they reported Opencode Go at $40, Claude at $20, and $0-100 for the Deepseek API depending on demand.
Try it yourself with Hermes Agent
Help me set up recurring agent jobs for [go-to-market], [research], and [development] work. First, propose a schedule, the inputs each job will use, and where each output should go. Then draft a separate GitHub issue for each task so another agent can pick it up on a schedule. Pause and ask for my approval before you create issues, start any runs, send anything, or make changes that can’t be easily undone.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Make an appraisal report generator with Claude
A South Korean appraiser used Claude Code to automate repetitive parts of appraisal report writing.
Set up an agent to handle calls on your behalf
David Ondrej gave Hermes Agent a phone number so it could place and answer calls while he slept.
Grade Canvas work with Claude before publishing scores
An instructor used Claude to rate Canvas submissions by rubric, then checked the results himself before any grades went back to students.
Use Claude to screen candidates before human interviews
micro1 used Claude to run live technical screens and produce reports before handing qualified candidates to human interviewers.
Turn Claude into teacher tools for reports and planning
A primary teacher used Claude to make tools for report comments, assessment tracking, and curriculum-aware planning.
Have Hermes watch blocked cards and clear easy blockers
A developer set Hermes to scan for blocked task cards every five minutes, investigate the cause, and report results in Discord.