I built a planning CLI for AI coding agents. Some developers like the idea, but nobody has bought Pro. What am I missing?
I’m building Archseed, and I’ve reached an uncomfortable point: some developers like the idea, a few have tried it, but nobody has bought the Pro plan. Rather than post another feature announcement, I’d like to understand what I might be getting wrong. The problem I’m trying to solve When you give a coding agent an incomplete request, there are decisions it still needs to make: What belongs in…
Archseed is a new tool that aims to help developers make crucial planning decisions before starting to code with an AI coding agent. However, despite receiving positive feedback on the free workflow and receiving some trial sign-ups for the Pro plan at $12/month, the tool has yet to see widespread adoption.
The core problem Archseed is trying to solve is the ambiguity developers face when giving an incomplete request to an AI coding agent. Decisions like determining what belongs in version 1, what should stay out, which architectural patterns to follow, and which assumptions need approval can significantly impact the final product. By making these decisions explicit beforehand, Archseed hopes to guide developers towards a more aligned and efficient coding process.
The tool is designed as a CLI-first interface, guiding users through scope, constraints, and architecture decisions and generating structured project files. However, Archseed is not meant to replace an IDE or another coding agent, nor does it automatically enforce architectural decisions through generated Markdown files.
The author of Archseed is unsure whether the problem is simply not painful enough to warrant a paid tool, if the benefits are not clear enough to justify the cost, or if developers already have a satisfactory workflow with their coding agents. They also question whether a subscription model is the best approach for a feature primarily needed at the start of a project.
To better understand potential users' experiences, the author is seeking insights from those who use coding agents. Specifically, they want to know how often developers have had to undo scope or architectural decisions made by an AI agent and how they handled those situations. Additionally, the author is interested in feedback on Archseed's approach, particularly any features that could seamlessly integrate into an existing workflow.
Ultimately, the author is open to all types of feedback, whether it be affirming the current direction, suggesting improvements, or simply sharing experiences with AI coding agents and scope decision-making. The goal is to gain a deeper understanding of user needs and pain points to refine Archseed's offering effectively.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
