The toolbelt
There are pathways to build quickly and pathways to build right. These are the tools for the second one. They work on the part of the job that decides whether software launches or stalls: the thinking that happens before the first line of code.
You are given 24 credits when you sign up, which is roughly about 8 planning turns with idea8. More arrive with a membership, and a bundle comes with every live session seat. You never spend credits on a seat. That one balance stretches further as the toolbelt grows. PalateMCP is its own product, priced separately. Each tool below states its own cost.
The Jiffi build workflow as a Claude Code plugin: it takes a raw idea to a shipped, well-built product with real gates, in your own editor. No credits — it is the engine the hosted tools plug into, not one of them.
The flagship, live now
Talk through your idea and idea8 pushes back, then turns the whole conversation into the planning pack your build runs on. You walk away with an Idea Pack, a phased delivery plan, a competitive landscape, assumption and dependency registers, and an honest read on product-market fit. Together they give the build process everything it needs to stand up a solid PRD, ADRs, brief, plan and spec as you follow the guides. Where the two of you never settled something, the pack says so under “Open questions”, instead of inventing a tidy answer you would trust right up until it broke.
A separate product, worth unlocking
Most AI-built sites look AI-built, and that generic sheen is what marks the work as cheap. PalateMCP fixes it at the source: hundreds of real websites analysed to the inner page, and the design tokens behind them, handed to your AI as it builds. It stops guessing at taste and starts borrowing from work that already earned it, so what you ship looks considered instead of generated.
Every tool we add runs on the same balance you already hold. Your credits reach each new one the day it lands, so what a membership is worth keeps climbing while the price stays where it is. We ship them when they are right, not to hit a date.
Attacks your plan before reality does.
You wrote the PRD. You are now the worst possible person to review it. Critic takes a finished planning artifact and argues the other side: the assumption holding up the whole thing, the requirement that contradicts another one, the success measure nobody could actually collect, the alternative the ADR dismissed too quickly. It returns a ranked list of what is most likely to break and what evidence would settle each one. Not yet available.
What you walk away with
Turns planning into something a builder can start on Monday.
A PRD is not a build queue. Handover reads your artifacts and produces the thing that actually gets worked from: scoped units of work in dependency order, each with acceptance criteria specific enough to argue about, and each traced back to the decision that produced it. Works whether the builder is a person or a coding agent. Not yet available.
What you walk away with
Tells you where the build stopped matching the plan.
Decisions rot quietly. Six weeks in, the codebase has quietly done the opposite of what the ADR said, and nobody noticed because nobody was looking. Drift checks a codebase against the artifacts that specified it and reports where the two have separated: decisions silently reversed, requirements never implemented, and constraints the build has grown out of. Then it tells you which ones matter. Not yet available.
What you walk away with
Everything here exists to get one thing out of your head and onto paper: a decision you can defend later. Where a conversation does not settle a question, the artifact says so under Open questions instead of inventing a plausible answer. A named gap is useful. A fabricated one is a trap.
Every artifact you produce sits in your library, tied to your account. Put the credits, a toolbelt that keeps growing, and a stack of plans you keep on one side of the scale, and the spend on the other. It is not a close call.
Start building, free