How this was made and checked
Every item on the list went through the same steps. This page says what they were, and where they stop.
Research
The list is split into four domains: treatment and care, daily systems, body and health, mind and relationships. GPT-6 Astra, an OpenAI model, researched each domain from public sources (ADHD guidelines, systematic reviews and large studies) against a fixed specification. Where the BMJ 2025 umbrella review (EBI-ADHD) covers an intervention, its numbers and certainty ratings win. Every item needs at least one Tier 1 or Tier 2 source and one number a reader can find at that source.
Tier 1 is a national ADHD guideline (NICE, AAP, CADDRA, AWMF), Cochrane, the BMJ 2025 umbrella review, NIMH, CDC or NHS. Tier 2 is a peer reviewed meta-analysis or large cohort. Tier 3 is a reputable secondary source such as CHADD or Harvard Health, and it never stands alone.
Fact-checking
Separate Claude Opus threads, Anthropic models working apart from the researcher, then fact-checked every item, one thread per domain, starting from the assumption that errors exist. They opened every link again, compared each number, certainty rating and population with what the source says, and flagged anything overstated, anything that reads like dosing advice, and anything unsafe. Their corrections were applied before publication.
Every source on this site is a link. No claim here is meant to be taken on trust: open the source, read the number, and if we got it wrong the source will say so. That is the whole point of building it this way.
Merging and spot checks
An orchestrating AI agent merged the checked domains into one list, ran a validator that enforces the specification on every item, and spot-checked items against their sources before publishing. Pawel Jozefiak publishes the site and is accountable for it.
Clinical review
None. No doctor, psychologist, nurse or other clinician has reviewed this site or any item on it. The checks above are made by AI models against published sources, and they do not replace clinical review.
Translations
The site is in English for now. Other languages will be translated from the checked English by Claude Opus. Only the prose is translated: numbers, sources and rules are copied. Until a language is fully translated its pages show the English text and ask search engines not to index them.
Evidence grades
- A Moderate or high certainty evidence in people with ADHD, or an explicit ADHD guideline recommendation.
- B Trials in ADHD with low certainty, or strong general health evidence with a sourced reason it matters more with ADHD.
- C Small or mixed studies, expert consensus or clinical practice.
The ranking
Every item gets a score from 0 to 100 for the benefit a typical reader it fits can expect. It multiplies how big the effect is by how sure the evidence is and by how common the gap is among people with ADHD. A large effect from small, shaky trials never outranks a moderate effect with solid evidence. The general list is that score, in order.
The benefit score is an editorial prioritization for the general list, weighted by certainty. It is not a prediction of what will happen for you.
You give a few facts, starting with who you are reading for. Each item can carry rules: a hard filter that decides whether it applies at all (parent training only when you read as a parent, for example), and boosts that add or subtract points. Your score for an item is its benefit score plus every boost that fires. What is hardest right now only ever boosts, it never hides an item. A question you skip fires no rule.
Tailoring uses rules written into each item. Every rule is listed on the home page, exactly as the engine reads it.
What this cannot promise
A second model checking a first is automated verification, not independent clinical review. Two models can misread a study the same way. Almost all ADHD trials last about twelve weeks, so for most items nobody knows the long-term effect, and the item says so. The numbers describe groups in trials, not you. Where evidence comes from the general population, the item is marked as general health evidence.
This is not medical advice. It is a reading list with the evidence attached. It cannot know your history, your diagnosis or your medication, and it never tells anyone to start, stop or change a medicine. Medication and diagnosis items point to a clinician. If something here contradicts what your clinician told you, your clinician has more information than this website does.
Corrections
If a number, a source, a certainty rating or a caution is wrong, email meet@jock.pl or message @joozio on X with the page address and what the source actually says. Corrections go into the data every page is built from.