About
Why Overkill exists, what it refuses to be, how it is funded, and who writes it.
The project
Why it exists
Generative AI has become the default reflex. It gets called to filter a message, pull out a date, sort a form, search three hundred documents. In a large share of those cases, a rule, a query or a classic model of a few megabytes does the job, often better.
That reflex has a price few people work out at the moment of the decision: a recurring cost that grows with usage, latency, data leaving your infrastructure, a non-deterministic result that is therefore hard to guarantee, a dependency on a provider and on its deprecations, a regulatory scope you did not choose, and an energy footprint out of all proportion to the alternative.
The most exposed are those with no in-house expert and no consulting budget: junior developers, solo developers, small teams. They copy what they see, and what they see is an ecosystem with an interest in selling them AI.
Overkill exists to make the trade-off available. For each task, every known option from the simplest to the heaviest, with code that runs, orders of magnitude, real limits, and the precise condition that justifies moving up a rung.
What it refuses to be
This is not an anti-AI site. That point is not negotiable. The principle is “the right tool for the job”, not “AI is bad”. Some entries recommend a general-purpose model without hedging, and those are what make the entries recommending the opposite worth believing.
Nor is it a tool directory, an opinion blog, a legal advice service, or a piece of software as a service. No accounts, no payment, no database, no comments.
How it is funded
It is not.
No advertising, no sponsored content, no affiliate programme. Nobody pays to appear on an entry, and nobody can pay to disappear from one. That is the only rule, and it will not change: a catalogue that tells you what you do not need is only worth reading if it has nothing to gain by telling you otherwise.
That has a direct consequence for what you read: where an entry names a tool, it is because the code needs it to run. There is nothing to gain by steering you to the most expensive rung, and nothing to lose by telling you to buy nothing.
It also has a consequence for pace: the catalogue grows at the speed of what can be written and verified properly, not at the speed of a publishing calendar.
Hosting a static site this size costs little. The help page offers services related to the subject; that is the only thing resembling a business model, and it is kept separate from the content.
How it is built
The site is static, with no database, no cookie and no advertising tracker. The content lives in a public Git repository: each entry is a file, each code snippet is a real file with a test that runs it on every build of the site.
That constraint is not cosmetic. A catalogue whose code does not run is worthless, and the only way to guarantee it is to refuse to publish anything that has not been executed. See the methodology page.
The weight of each page is shown in the footer. A site arguing for frugality that weighed three megabytes would not be credible.
The author
Overkill is written by Florentin Biaou, an artificial intelligence and data engineer.
I am in my final year of engineering school at ESIGELEC Poitiers, specialising in artificial intelligence and big data, after two years of preparatory classes. I work as a data engineer at Soundcharts under an apprenticeship contract, and I build projects on the side, because that is how the craft is learnt.
The idea for this site came from a course on AI governance and compliance. The speaker explained that a share of the projects he saw were gadget AI: the company took on regulatory obligations and a recurring bill for a need a few lines of code would have covered. What was missing, he said, was something to help a company work out whether AI is necessary before committing to it. And, when it genuinely is, to point it towards the most frugal model rather than the largest one.
Overkill is my attempt at building that thing.
To get in touch, the help page gives an address.
Reviewed on