Use case · Builders

How to plan and ship a SaaS MVP with Claude Code

AI coding can make implementation fast while making product direction fragile. Without a durable brief, scope decisions and customer assumptions disappear into individual sessions.

The setup

A simple way to run it in Hark

  1. 01Draft the MVP project

    Use Business and Build docs to define the problem, audience, promise, scope, stack, and explicit non-goals.

  2. 02Connect Claude Code

    Install Hark's session flow so Claude Code reads the current agent brief whenever work starts.

  3. 03Track the living build

    Keep Current state current with what is in progress, what is blocked, and what should happen next.

  4. 04Record ships and decisions

    Add journal entries for releases and trade-offs so later sessions understand not only what changed, but why.

  5. 05Let the enforcement carry it

    Each session is locked to this one project, a quiet session still gets a handoff drafted from what happened, and with repo export on the brief is committed to your codebase as .hark/HANDOFF.md and .hark/DECISIONS.md.

Starter build

Hark’s public project page

Starter builds are coming. Until then, use Hark’s own documented build as the example structure for this setup.

View the public project page placeholder →
Use this setup

Common questions

Can I use this setup for an existing SaaS MVP?
Yes. Import a conversation or brain dump, review the drafted project, and connect the repository when you are ready. You do not have to start from scratch.
Do all collaborators and agents see the same information?
They work from the same Hark project and Current state, subject to the workspace and project permissions you choose.
Can I try this without adding a card?
Yes. Hark starts with a 14-day card-free trial, and your work remains readable if the trial ends before you choose a plan.