From Validated Idea to Lovable App

To turn a ShipFit playbook into a working Lovable app, export your validated decisions as a Lovable brief, paste it as the initial prompt in a new project, and upload the knowledge file so the context sticks. Lovable then builds your validated V1 (buyer, scope, pricing, brand voice) instead of the generic SaaS app it defaults to.

Before you start

You need a finished playbook. Run the full 9-decision flow first (a Quick Take takes about 2 minutes, the full playbook 15 to 20 minutes). The export only works once the prior 8 decisions are locked, because that is what fills the brief with real content: your buyer, your above-the-line pains, your V1 cut, and your pricing model.

You also need a Lovable account. The free tier builds one project but limits messages per day, so iterative refinement burns through fast. Paid tiers lift that limit.

Step by step

1. Finish the playbook and reach the export step. The export is the last of the 9 decisions. Pick Lovable as a target (you can pick more than one tool at once). ShipFit packages your validated decisions into two pieces: a project brief and a knowledge file.

2. Create a new Lovable project. Start fresh rather than retrofitting an existing build. A clean project means the very first generation is shaped by your validated scope, not by whatever Lovable already guessed.

3. Paste the brief as the initial prompt. This is the seed. The brief covers your buyer, the V1 feature cut, the pricing model, and the brand voice, plus the cut features marked “do not implement.” Lovable’s first build follows it instead of shipping every panel it thinks a SaaS app should have.

4. Upload the knowledge file. Lovable’s agent is most useful across many chat turns, and a one-time prompt fades as the conversation grows. Drop the knowledge file into the project’s Knowledge feature so the validation context persists across sessions and survives a rebuild.

5. Smoke-test the context. In the chat, ask: “Who is this app for and what is in V1?” If Lovable answers with your validated buyer and your V1 scope rather than a generic guess, the context loaded. If it gives a vague answer, the knowledge file is missing or the brief was trimmed.

6. Build against the scope. When you ask for a feature, Lovable already knows whether it is in V1 or parked. Ask “let’s add team billing,” and a well-scoped project should push back if billing was cut. That pushback is the point: the MVP scope decision survives into the builder instead of dying in a doc.

Keeping it in sync

Re-run the export after any meaningful pivot, e.g. a new buyer segment or a changed pricing model. Replace the knowledge file with the fresh version and re-state the changed sections in chat. A stale knowledge file is worse than none, because Lovable will confidently build against decisions you have already abandoned.

When V1 is ready you can keep iterating in Lovable or export the codebase to GitHub and continue in Cursor or Claude Code with the same validated playbook.

For the product-side detail on what the export contains and how Lovable consumes it, see the Lovable integration page. This guide is the how-to; that page is the what-and-why.

Common mistakes

• Skipping the “do not implement” list. Without it, Lovable adds settings panels, notification preferences, and admin dashboards because they are standard. The export bakes the cut list in. Do not strip it.

• Re-prompting in casual language. Once the brief is loaded, keep prompts in the same structured style. Casual prompts pull Lovable back toward its maximalist defaults.

• Not uploading the knowledge file. The brief seeds the first build but does not load into every later chat. The knowledge file does. Skip it and validation context decays after a few iterations.

• Treating Lovable as the validator. Lovable builds; it does not validate. The validation happens upstream in the playbook, where roughly 1 in 4 ideas gets killed before it reaches a builder. If you have not done that work, see pricing to start (the free tier includes 3 credits a month, paid playbooks from $5).