AI Stack Builder

The Rules

Each job has its own ladder of plain rules, read from the top: if you already pay for a tool that does it, use that; if you asked for privacy, a tool that keeps your work private; if less than a set amount is left for this job, a cheaper or free plan; otherwise the tool built for it. Jobs run in your priority order, the first with all the money and each next with what is left. Every pick shows the step that chose it under "Why this pick", and "Why this stack" lists every decision in order. The whole rule list is public: stack-rules.json, with the tool list beside it, under CC BY 4.0. Prices come from the tool list, never from the rules.

When one step names more than one tool, the tool's strength decides before its price: the tie goes to the tool rated highest for the job, then to the one more people use and rate (privacy fit and signal below); the plan's size was already settled by the step's own money condition. A plan over twice the cheapest plan of a tool rated as well for the job stays in the tie only with a capability line from our list, such as Premiere's text-based editing. An even tie goes to the cheaper plan. The full score, used to fill gaps the rules leave:

score = coverage × budget fit × privacy fit × (0.8 + 0.2 × signal)

• Coverage adds, for each thing you want done, how much better this tool does it than the stack so far (each tool is rated 1 to 3 per job), weighted by your priority: the first counts as many times as you ticked things, the last counts once.
• Budget fit is 1 for a free plan and falls toward 0.5 as the plan's price nears your whole budget. A plan that does not fit what is left is skipped, and the tool's free plan is used if it has one.
• Privacy fit is 1, or 0.6 for a cloud-only tool when you prefer tools that run on your machine.
• Signal comes only from public counts: the App Store rating weighted by how many people rated it, GitHub stars, and Hacker News stories in the last 30 days. Hacker News leans to developer tools, so a mention can lift the signal and never lowers it. Signal can move a score by a fifth at most, and a tool with no public counts gets 0.4 out of 1, a little under a tool with modest counts, since no counts is no evidence.

Once every job has its step, the builder spends the rest of your budget on the tools already in the stack, one plan at a time, first job first, and only to a plan whose extra it can say in one line, shown on the card as "Why this plan". How far it goes follows your answer to how much of your week this work takes: a few hours keeps every tool on the plan a small team starts on; most days moves every job's tool up one plan, first job first; all day goes round by round, one plan per tool per round, until the money runs out or every tool has topped out. A plan is a step only when it serves the job you ticked: a store plan is never a raise for a landing page, and a bundle of every Adobe app is a step only when it also replaces another pick of yours. A raise that more than doubles what you pay now gives way when another tool built for the job does as much at half that price or less and more people use it. A raised plan that already covers another job you ticked, such as ChatGPT Pro with Codex, replaces that job's pick, and one subscription is never paid twice. A pick that costs more than twice a cheaper tool built for the same job needs a capability line from our list, or the cheaper tool takes the job; with privacy asked for, a free plan that makes your work public is passed over. A pick that no longer does any job best once the stack is in is dropped. When a tool could climb no further, it adds a second tool built for that job on its starting plan, but only where makers mix models (AI clips, images, 3D and voice), never an editor, presenter, scheduler, store, site or email tool, never an API or model unless you code, and never beside a plan you already pay for on a budget under $100. When money is still left, it names the cheapest step up that fits, priced as the extra per month, or says nothing on the list would help. A tool bought once, such as Reaper, shows its price as paid once, outside the monthly total, and is offered only when a month of your budget covers it. The model line prices a rough monthly volume of tokens for your jobs at OpenRouter's live prices and picks, among four models, the one rated best for your kind of work (coding, writing or analysis) in LMArena's public categories whose cost stays under a quarter of what is left; its card names the rating, the rank and the leaderboard date. The model line appears only when you ticked coding or building an app, and it is only for calling a model from your own code or automations, so it is always marked optional and never counted in the total; at a $0 budget it is not shown. There is no input for commissions anywhere in the formula. The scoring guide walks through each part.

Each pick opens a card with its public counts, marked live or dated, the latest Hacker News headlines about it, and notes on what people say. The notes are filed by hand from Hacker News comments, as a complaint or a highlight, each with its date, a link and the account that wrote it; the account was at least a year old when it posted and has no affiliate links in its profile, and the quote is under fifteen words. Notes never enter the score.

Related