How Distil works.

Public evidence-review protocol.

Most supplement companies do not publish their methodology because hiding the reasoning is how they sell more. Distil's commercial position is the opposite of that. We earn when you are informed, not confused. So this page exists.

What follows is the actual rulebook: the compound database, the grading system, the exclusions that are off the table by rule, the personalisation pipeline, the independent safety check, and the limitations of what an evidence-graded report can and cannot do. All of it checkable.

The compound database.

Distil's database holds 105 compounds we evaluate for inclusion in personalised stacks, plus a set we explicitly track as "considered but not recommended" so the interactions checker can still flag them (St John's Wort, niacin, high-dose biotin, vitamin K2 on its own, yohimbe, echinacea, astragalus, kava, ginger, SAMe, L-tryptophan, red yeast rice, cinnamon). Each links to a short page explaining why it is left out and what to consider instead. There are thousands of supplements on the market. Most do not have enough peer-reviewed clinical evidence behind them to justify a recommendation. A report can recommend 81 of our 105. The rest, NMN among them, are graded for none of the goals we score, either on the evidence or because they are not permitted in supplements sold here, so a report never adds them to a stack; we keep them for the interactions checker.

Every compound is graded A, B, or C against the published research, by the rules below. Anything that does not reach Grade C is not in the database. Anything that drops below Grade C in a future review is removed. The database is a curated set, not a complete index.

The database is not fixed.

Evidence moves, so the database moves with it. Every compound is reviewed each quarter, or sooner when a major trial or meta-analysis is published. When a compound accumulates enough good human evidence to clear the Grade C bar, randomised controlled trials or meta-analyses in people rather than promising lab or animal work, it goes into the database at the next review rather than waiting. When the evidence for something weakens, it moves down a grade or out. A compound is only ever added if it clears both a benefit bar and a safety bar: meaningful benefit and a safety profile that holds up. Low or mixed evidence, or potential harm for little benefit, means it stays out until the evidence is there. This page reflects the database as it stands today, and the figure above will change as the research does.

What the grades mean.

Grade A. Several strong randomised controlled trials, and the meta-analyses that pool them, showing the claimed benefit in human populations relevant to who might take it. The effect size is meaningful, the evidence has been replicated, and the finding is consistent across independent research groups. Example: Iron for iron-deficiency anaemia confirmed by a blood test, Psyllium husk for gut health, Ashwagandha (KSM-66) for stress.

Grade B. Solid clinical evidence, typically several human RCTs with consistent direction but smaller sample sizes, or one strong RCT supported by clear mechanistic understanding. Less fully replicated than Grade A, but well supported. Example: L-Theanine for sleep quality, Saffron for mild to moderate depression, Omega-3 for cardiovascular health.

Grade C. Emerging evidence. Human trials that are few, small or inconsistent, or a well-understood mechanism that no trial has yet tested for this outcome. Laboratory and animal studies alone are not enough: that is Grade D. Reported as emerging in every report it appears in. Always flagged so the reader can decide whether the evidence threshold is enough for them. A Grade C compound is chosen only when the client's profile closely matches what it targets, and it can sit in any tier. Example: Magnesium glycinate for sleep, Lycopene for prostate health, Boron for cognition.

Grade D. Never recommended. Used in the database internally to mark compounds we have considered and rejected, so the same decision is not reopened at each review. Compounds in this category rest on laboratory or animal studies alone, have failed to replicate or shown no effect in large trials, or carry risks that outweigh the benefit. Grade D compounds are listed in the database with the reason, but they never appear in a recommendation.

Each card is graded for your goals.

A compound is graded outcome by outcome, so it can hold Grade A evidence for one outcome and Grade B for another. Its card shows the grades for the goals you chose that it addresses, and an outcome you did not choose never lifts it. Where those grades differ, the badge shows the highest and the lowest, as in Grade A/B, in the colour of the lower one, and a card that touches Grade C is flagged as emerging evidence. A compound added for a gap in your diet or sunlight rather than for a goal shows the range of its grades across the outcomes that can apply to you, or across every outcome it is graded on when none can. The grade is set by our rules, not written freely for each report. It deliberately claims less, never more.

Hard exclusions, off the table by rule.

Some compounds are excluded for specific clients regardless of how well they would otherwise score. The exclusions are absolute, not "use with caution":

• 5-HTP with any prescription medicine. Serotonin syndrome risk. Many medicines act on serotonin, from antidepressants and lithium to migraine triptans and some painkillers, and no list of them is ever complete, so we consider 5-HTP only when you tell us you take no prescription medicine at all. Naming a medicine or remedy bought without a prescription that carries a serotonin warning, such as St John's Wort, codeine or a dextromethorphan cough medicine, rules it out too. Hard exclusion, no exceptions.
• NMN and NR. Never recommended, for any goal. NMN is not authorised as a novel food in Great Britain, so it should not be sold here as a supplement. NR is authorised, but the two randomised trials of NR in our records that measured insulin sensitivity, both in overweight or obese adults, found no improvement in it. A history of cancer is a separate hard exclusion for both; it would stand even if the evidence changed: laboratory and animal studies suggest NAD+ precursors may help tumour cells survive and spread, and no study in people has tested whether either changes the chance of cancer returning or a new one developing.
• Iron without confirmed ferritin in the deficient range. Iron supplementation in a non-deficient person carries real oxidative-stress risk. We do not recommend iron unless a blood result confirms the need.
• High-dose biotin (over 5,000 mcg). Always flagged for interference with thyroid function tests and the troponin tests used to diagnose a heart attack.
• St John's Wort. Never recommended, and the reason is what it does to other medicines rather than any doubt about whether it works. It is a potent enzyme inducer that lowers the blood levels of oral contraceptives, warfarin, statins, immunosuppressants and HIV medicines. It also adds to the effect of antidepressants. We keep it in our interactions checker because so many people take it.
• Cancer treatment in progress. No supplement stack is produced. The intake form gates this answer before any payment is taken.
• Pregnancy or breastfeeding. Same. Defer to NHS antenatal prescribing and your midwife or health visitor.

There are more. The full list lives in the database itself. The principle is consistent: the report does not produce output we believe is unsafe for the specific client, even if the client wants it. The answer is sometimes "not for you, not yet, here is what to test first".

How a compound earns its place.

A compound enters the database only after a structured evidence review. The protocol:

One. A literature search across PubMed: meta-analyses and systematic reviews first, then primary RCTs in the relevant outcome and population. Laboratory and animal studies alone never qualify a compound for a recommendation, and a mechanism that no trial has tested for the outcome can earn no more than Grade C.

Two. Each citation supporting the entry must have a verified PubMed identifier (PMID). Citations written from general knowledge alone are not acceptable. The PMID is the auditable trace.

Three. A grade is assigned by the rules above, against the evidence. The grade follows what the published research supports, whatever the compound is marketed for.

Four. Population modifiers are documented. A compound that works for older adults may not work for younger ones. Effective doses for women may differ from doses for men. The database holds these qualifiers explicitly so the personalisation step can apply them.

Five. Drug interactions are checked against the master table and added to the entry. Any interaction that would make the compound dangerous on a common medication is written into the exclusion logic.

Six. A "Last PubMed review" date is stamped on the entry.

The database is recalibrated every quarter. The cadence is enforced by an automated forcing function: on the first day of January, April, July, and October, a GitHub workflow opens a tracked issue requiring the calibration to be completed before the issue closes. The full log of every calibration appears at the bottom of this page.

The personalisation pipeline.

A report is not a search of the database. It is a personalised stack built for one specific person, against their full health profile. The pipeline runs in five stages:

Compound scoring. Every compound in the database is scored against the client's profile: their goals, their conditions, their medications, their diet, their sleep, their bloodwork, their lifestyle, the supplements they already take. Most compounds do not score high enough to be included. Selectivity is the product.

Clinical review. A second pass, a model call, challenges every compound that scored in and removes the marginal ones: one that adds little beyond what the stack already covers, one with weak evidence and no direct match to the client's goals or conditions, or one whose interaction risk outweighs a weak case. It can only remove; it cannot add a compound.

Doses and safety rules. For every compound that survives both passes, a model sets the dose from the compound's evidence entry, adjusted for the client's conditions and medications. Anticoagulants cap doses of certain compounds. CKD changes thresholds. Then the safety rules run as code over that list: they remove any compound that clashes with a medicine or condition the client declared, and cap any dose a safety limit covers, such as vitamin D for everyone and certain doses in kidney disease or atrial fibrillation. Trying to conceive, where a report is still produced, limits the stack to compounds on a list judged safe in pregnancy. Safety rests on this step more than any other.

Personalised writing. The report itself is written section by section, against the locked manifest. Each model step is a call our own software makes to Anthropic's API with fixed instructions; nothing is typed into a chat app. The name, form, dose, timing and start week on each recommendation are placed by code from the manifest, and the model writes only the prose around them. The same compound recommendation appears identically in the introduction schedule, the daily timing table, the compound card, the interactions summary, and the sleep stack where relevant. Every section is written from that single locked manifest, and the safety review below checks that they agree.

Independent safety review. A second model call, separate from the ones that wrote the report, reviews the output against a full safety checklist: dose caps, exclusion rules, medication flags, language standards, missing GP review notices, banned claims. Any critical failure holds the report for manual review and prevents delivery.

The independent safety check.

The safety check is the most important step. It runs as a separate model call after the report is generated. It does not write the report; it audits it, and the safety rules run again in code beside it. If a safety check fails, or the check cannot run or be read, the report is not delivered. It is held until reviewed.

A failure can mean a dose that exceeds a safety cap. A compound that should have been excluded for a stated condition. A claim that crosses from "may support" into "will". A missing GP review notice on a compound that requires one. An interaction that was not flagged.

When a report holds, an alert reaches Sebastian directly. The report is reviewed, rebuilt if necessary, and only delivered when it passes. This has happened. Reports that were technically deliverable but visibly imperfect have been rebuilt rather than shipped.

The QC stage is why a Distil report is more than an AI-written supplement guide: every report is independently re-checked against a fixed safety checklist, and held for manual review if a safety check fails, before it can be delivered.

What Distil deliberately does not do.

The boundaries are as important as the methodology:

We do not sell supplements. We do not stock supplements. We do not have an associated brand of supplements.

We do not take affiliate commission from any retailer.

We do not recommend specific brands. The reports tell you what the product needs to contain (the form, the dose, the purity certifications, the things to avoid). You buy it from whoever you trust.

We do not run a subscription. The report is a one-time purchase. If your situation changes, you can buy a new report, and the link in your report's email takes 30% off one bought within 12 months. We do not auto-renew, and the only email we schedule is one reassessment reminder at twelve weeks.

We do not include a compound because it sells well. The selection is dictated by the evidence score, not by what would generate the highest cart value.

Naming what we do not do is part of the brand. Most supplement companies cannot honestly make these statements. Saying it directly is the point.

What this is, and is not.

Distil reports are personalised, evidence-graded information. They are not medical advice.

A Distil report does not replace a GP, a registered nutritionist, or a specialist. It does not diagnose or treat any condition. Where the report identifies that a condition or medication interacts with a compound, the report flags it and recommends discussion with your GP. Where bloodwork is the right next step before supplementation, the report says that.

Compounds are graded against published clinical research. That research has limitations. Sample sizes vary. Effect sizes vary. Replicability varies. The grade reflects what the evidence supports, but no Grade A claim is "this will work for you specifically". It is "the research suggests this tends to support this outcome in populations relevant to your profile".

Honest framing is part of the brand. Anyone who promises more than this is selling something else.

Reassessment, and what comes next.

The report you receive is built against the profile you submit. Profiles change. Conditions emerge. Medications start and stop. Children happen. Goals shift. The report includes a 12-week reassessment framework so you know what to track and when to revisit.

There is no subscription and nothing renews. The one scheduled email we send is a single reassessment reminder at twelve weeks, which your report is built around, and it carries a one-click opt-out. Beyond that, you decide when, or whether, to come back.

Two changes are coming:

A named clinical reviewer. A nutritionist registered with the Association for Nutrition will join as the named clinical reviewer of every Distil report. Their qualifications, registration number, and review responsibilities will be on this page when the relationship is signed.

Continued public log. Every quarterly calibration is documented in the calibration log below. The cadence is enforced automatically: a GitHub workflow on the first of each calibration month opens an issue that stays open until the calibration is complete. If a quarter passes without a new entry, it is publicly visible here.

Calibration log.

Every quarterly calibration of the compound database is logged here. The most recent calibration is at the top.

What this tool is, and is not.

The Distil interactions checker is a free reference for adults who take supplements alongside prescription or over-the-counter medications. You enter your supplements and your medications. We tell you which pairs interact, how seriously, and what the published action is. We list our reasoning per pair and link the primary citation.

It is not a medical device. It is not personalised. It does not store your inputs. It does not replace clinical advice.

The tool exists because the alternative reference resources have gaps. The British National Formulary, the UK clinical gold standard, restricts its scope to conventional medicines and only mentions supplements where they affect conventional therapy. The popular checkers cover supplements broadly but carry advertising, do not publish their inclusion rules, and tend to return a soft "no interactions found" message that does not distinguish "we checked and there is no interaction" from "we have not checked this combination."

We publish our rules. We separate those two cases. The sections that follow explain how.

How we built the medication list.

We check supplement interactions against 393 medications. The list comes from two sources.

The bulk: the drugs dispensed most in the UK. Most of the list comes from the top of the NHS Business Services Authority Prescription Cost Analysis for England 2024 to 2025. The top of that list is atorvastatin (73 million prescription items in a year), amlodipine, the proton pump inhibitors, levothyroxine, the antihypertensives, and SSRIs like sertraline. These are the drugs UK patients are most likely to be taking when they ask about supplement interactions.

The remainder: specialist additions where the stakes are high. Some drugs with narrow therapeutic windows or critical interaction profiles fall outside the volume cut. Sirolimus and everolimus (mTOR inhibitors used after a transplant). The older MAOIs phenelzine and isocarboxazid. Rasagiline and selegiline (MAO-B inhibitors for Parkinson's). Tacrolimus and ciclosporin (calcineurin inhibitors, used after a transplant). A real patient asking about a supplement interaction on any of these is in serious clinical territory, so we add them in despite the low volume rank. We have also extended the list over time to close class gaps a pharmacist would test first: the common antibiotics, the ADHD and mental health drugs and the GLP-1 agonists.

The substitution table below lists the most clinically important medications by category, including both top-volume drugs (warfarin, lithium, phenytoin, methotrexate, tamoxifen, the immunosuppressants) and the low-volume specialist additions. Every choice is published with its reasoning.

We record the volume rank or substitution reasoning behind every entry, and the list is regenerated quarterly when the next NHS BSA Prescription Cost Analysis release is published. Every one of the 393 is searchable in the checker itself, and the counts on this page are stamped from the same file the checker reads, so what you read here cannot drift from what the tool holds.

How we decide which interactions go in the database.

Most interaction checkers do not publish the rule they use for deciding whether a pair belongs. The British National Formulary lists about three thousand interactions but explains very little about why each one is there, a transparency gap an editorial in the British Journal of Clinical Pharmacology noted twenty years ago and which is largely unchanged today.

We publish our rule. It has two layers.

Layer 1. Does this pair belong in the database at all?

A supplement-medication pair belongs in the database if it meets at least one of five inclusion criteria:

1. Pharmacokinetic interaction with documented clinical impact. A published mechanism such as CYP induction or inhibition, transporter modulation, or protein-binding displacement, plus a measured clinical endpoint such as drug-level shift or AUC change of twenty per cent or more. Example: St John's Wort with warfarin via CYP3A4 and CYP2C9 induction.
2. Pharmacodynamic interaction with documented clinical impact. A published mechanism such as receptor co-agonism, additive physiology, or antagonism, plus a measured clinical endpoint such as serotonin syndrome event rate, INR shift, blood-pressure change, or hypoglycaemia event. Example: 5-HTP with SSRIs via additive serotonergic action.
3. Established absorption or chelation interaction. A physico-chemical mechanism such as cation-binding, complexation, or lipid-barrier effects, plus a clinical operational rule such as timing separation in hours or a formulation switch. Example: calcium with levothyroxine, four-hour separation per BNF.
4. BNF-listed pair. Any pair where the BNF Appendix 1 entry carries a "potentially hazardous" bullet is automatically included. BNF is the primary citation; we add our own mechanism and management note alongside.
5. Active-condition safety flag where mechanism is established and endpoint is serious. Examples include NAD+ precursors such as NMN with a history of cancer, and high-dose biotin with thyroid and troponin immunoassays. These flow through the optional context flag system, not the supplement-medication pair channel.

A pair is excluded if the only evidence is from cell culture, animal models, double-extrapolation chains across population and ingredient and mechanism and effect, or a single case report with no published mechanism to explain it.

Layer 2. What evidence quality is required for each call?

Every interaction-pair row in our database carries an evidence_grade field. The grade is set per pair using two published assessment tools:

• The Drug Interaction Probability Scale (Horn, Hansten, and Chan 2007), purpose-built for evaluating drug-interaction case reports. It adds DDI-specific questions that the original Naranjo nomogram (designed for single-drug adverse events) does not cover.
• The WHO-UMC causality scale for individual reports (certain, probable, possible, unlikely, conditional, unassessable).

The severity tier and the evidence grade are separate calls. A Red tier can rest on established or well-documented evidence, or, where the stakes justify caution before any harm has been reported, on a mechanism with little direct human data. When a Red call rests on limited or theoretical evidence, the row is flagged for clinical reviewer sign-off. We would rather tell you a high-stakes call is precautionary than wait for someone to be harmed.

When a pair sits at the edge of what evidence supports (a single strong case report, a plausible mechanism with sparse human data or a disagreement with a canonical source), we flag it for clinical reviewer escalation. Until a named clinical reviewer is appointed (an open work item against our first-revenue threshold), flagged entries are included with a visible "awaiting clinical reviewer sign-off" footer rather than silently demoted or omitted.

How a pair is checked before it goes live.

An inclusion rule and an evidence grade decide whether a pair belongs and how strong the call can be. Neither one checks that the citation behind it actually says what we claim. That is a separate job, and it is where most of the work is, so we made it a pipeline every pair passes before it is published.

One. The pair is researched and drafted against the primary literature, with the mechanism, the clinical endpoint and the candidate citations attached.

Two. A second, independent pass re-verifies every claim the grading rests on against PubMed: the direction of the effect, the dose, the numbers and each citation. It works with no sight of the first pass's reasoning, and its job is to disagree. It regularly catches a real paper cited for a claim it does not make, an effect stated in the wrong direction or a number that has drifted. Those are corrected, or the pair is held, before anything ships.

Three. Every citation's identifier is machine-checked against the National Library of Medicine to confirm the paper exists and is the one named.

Four. A standing probe re-runs the textbook interactions a pharmacist would test first: the chelation pairs, the serotonergic stacks, the CYP3A4 cases, the bleeding-risk additions. It fails the build if any of them ever comes back as anything other than the documented severity. It currently passes with zero misses.

We do this because the dangerous failure for a tool like this is not a missing entry, since the user is told when something is missing. The dangerous failure is a confident wrong answer. The pipeline exists to catch our own mistakes before a reader sees one.

Where coverage stands now.

Every supplement a report can recommend has been assessed against every medicine on our list at the time of its assessment (296 medicines), except 5-HTP, which we have not yet assessed against all of them. The list now holds 393, and a medicine added since a supplement was assessed shows as "Not yet assessed" for that supplement until the pair has been checked. The supplements we list only so that we can warn about them, such as St John's wort, have not all been assessed in full. 1283 combinations carry an individually researched, cited entry, every pair where the literature documents something, graded red, amber or green. For the remaining combinations of a fully assessed supplement with a medicine it was assessed against, other than those described next, no documented interaction was found, so the tool returns green, labelled "No known interaction" and worded "found no documented interaction at typical doses". A combination we have not assessed is labelled "Not yet assessed" rather than given a clear result. Where we hold an amber or red entry for a supplement with one medicine and none with another that works in a similar way, such as vitamin E with ibuprofen beside our amber entry for vitamin E with aspirin, we count that combination as not yet checked and label it the same way, naming the related medicine and saying a similar caution may apply, until we have checked it; 826 combinations show this way today. That is not the same as an explicitly studied "no interaction", and we word it differently, but it is emphatically not the silence other checkers return for things they have not looked at. Grey, "Not yet in our database", is reserved for a supplement or drug we do not yet cover at all, and we always say so rather than defaulting to green.

How we grade interaction severity.

Interaction checkers tend to overuse severity warnings. When the same pair gets a Major rating in one database, Moderate in another, and is silently ignored by a third, the warning loses its meaning. One published comparison found that across the four most-used commercial interaction databases, only eleven per cent of flagged pairs were detected by all four. Another study, conducted in an intensive care unit, found that database severity ratings agreed with experienced clinician judgment on three drug pairs out of more than four hundred.

We treat that as the integrity bar to clear, not the standard to aspire to.

Distil uses a three-tier rubric calibrated against four published frameworks: the Hansten and Horn Operational Classification of Drug Interactions (ORCA), Stockley's two-axis action-and-severity model, the Agency for Healthcare Research and Quality 2016 high-priority criteria, and the Tilton 2013 consensus on clinical decision support tiering.

Red Severe

Clinically reportable harm has been documented, or a published mechanism predicts a serious endpoint at standard doses. Combining a Red pair without direct GP or specialist supervision is not advised.

Examples in our database include 5-HTP with SSRIs (serotonin syndrome), St John's Wort with warfarin or with transplant immunosuppressants (tacrolimus, ciclosporin) via CYP3A4 induction collapsing therapeutic levels, and iron supplementation without confirmed ferritin status (overload risk in unrecognised haemochromatosis).

Red maps to ORCA Class 1 (Contraindicated) and Class 2 (Provisionally Contraindicated), to Stockley's "avoid" action, to the AHRQ "high seriousness" tier and to Lexicomp's X risk rating.

Amber Caution

A real clinical impact at typical doses, but operationally manageable. Most Amber pairs reduce to a specific action: separate the doses by a number of hours, hold within a stated dose ceiling, or monitor a specific lab value.

Calcium and levothyroxine separated by four hours is a typical Amber. Curcumin with warfarin, INR monitored, is another. Berberine with metformin, additive glucose-lowering monitored at initiation, is another.

Amber maps to ORCA Class 3 (Conditional), to Stockley's "monitor or adjust" action, to the AHRQ "medium seriousness" tier and to Lexicomp's C (monitor) and D (consider modification) ratings.

Green No known interaction (explicitly assessed)

The pair has been assessed against our inclusion rubric and no clinically meaningful interaction has been identified at typical doses. Green covers two cases we word differently on the result page: a pair we have explicitly studied and found clear, and a pair where a fully-assessed supplement has no documented interaction with that drug and no caution with a medicine that works in a similar way. Both are an answer. Neither is silence.

Green is not the same as silence. Most interaction checkers default to silence for anything they have not checked, which is indistinguishable from "we looked and it's fine." We separate those two cases. The next section explains how that separation renders on the result page.

Green maps to ORCA Class 4 (Minimal Risk) and Class 5 (No Interaction), to Stockley's "no action needed" action and to Lexicomp's A (no known) and B (no action) ratings.

Grey Not in database

If you enter a supplement or medication outside our coverage, we say so. We do not return Green by default. The result page shows a clear message above any per-pair findings, asking you to tell us, and the request joins the queue of what we add next.

Of the eight interaction checkers and references we audited, described below, none surface "assessed → no interaction" as a distinct user-facing state different from coverage silence on a public consumer UI. We do.

How we render results.

Interaction-checker user interfaces tend to fail in one of two directions. They either return a flat list of pair-by-pair findings, weighted equally regardless of stakes, or they hide a lot behind disclaimers and the user does the prioritisation work themselves. Both end the same way: a clinically significant finding gets missed because it was surrounded by visual noise.

The clinical literature on alert fatigue is consistent on this point. A 2006 review of 17 studies found that clinicians overrode drug safety alerts in 49 to 96 per cent of cases, in hospitals and in primary care alike. A 2020 evaluation of 1,599 US hospitals suggested that some may score higher on a medication safety test by alerting too often, which the authors warn could add to clinician burnout and may even make care less safe. A 2006 study in 31 primary care practices let only the critical and high severity alerts interrupt the prescriber and showed the rest quietly; clinicians accepted 67 per cent of the interrupting alerts, where an earlier study had found only 11 per cent of high severity alerts accepted.

We took the principle and translated it for a consumer surface.

The result page renders in four bands.

Header band. The scope statement at the top names how many pairs we checked and when the database was last updated.

High-stakes band. Red and Amber severity findings render in full above the fold, in tier order, each with the specific action it implies. Each says in plain words what to do, such as separating the doses or asking your GP or pharmacist before taking the two together, rather than using informal severity adjectives.

Not-yet-assessed band. Pairs we have not yet assessed come next, labelled "Not yet assessed" in a neutral colour, never green. A pair beside a caution we hold for a medicine that works in a similar way comes first and names that medicine.

Assessed-no-interaction band. Green findings render below: a pair with its own researched green entry in full, and the pairs a fully assessed supplement has no entry for behind an explicit counter you can expand when there are more than three. The counter is named so you can verify that nothing was silently dropped, for example "Show all 12 assessed-clear pairs".

Per-pair detail is on demand. The default render shows the severity tier, the paired names and a plain English line. Mechanism, citations and dose notes sit behind a "Read more" expand on each finding. The principle is to keep the baseline density low enough that the high-stakes findings are visible without scrolling and to put the depth where users go when they want it.

If you entered something we do not have data on, the "Not in database" message renders at the top of results, visually distinct from any severity finding, with a feedback button that adds the gap to the queue of what we add next.

How we compare to other interaction checkers.

Before we built this tool, we audited eight existing reference resources. Each does something well. Each has gaps. We made our design decisions against that landscape.

The free consumer checkers cover the most medications and supplements. The largest of them uses a familiar three-tier severity scheme. They carry advertising on the results page. They publish no inclusion methodology and show no per-pair citation. We do not place programmatic advertising on a health-decision surface.

The independent evidence services are the closest to us in voice, and the strongest of them takes no advertising and no industry sponsorship. Its drug-supplement checker sits behind a paid subscription. We chose to make our equivalent free.

Memorial Sloan Kettering About Herbs is the best free evidence-led supplement reference and uses inline PMID citations on every monograph. It is monograph-format, not a pair-checker, and covers 290 herbs, botanicals and supplements rather than drug-anchored stacks. We adopted the per-pair PMID anchoring; we built the pair-checker UX they do not have.

NHS BNF is the UK clinical gold standard and free, and it grades each interaction's severity on four levels and its evidence on three, which is finer than ours. Its scope is explicitly restricted to conventional medicines; supplements are mentioned only where they affect conventional therapy. We fill the gap on supplement-medication coverage and we cite the BNF as a primary anchor whenever a pair is BNF-listed.

The professional clinical database built for prescribers is fully paywalled. We acknowledge it as a clinical reference; we publish our methodology where it requires a subscription.

OpenFDA and DrugBank are developer-facing APIs. DrugBank's clinical API covers more than 1.3 million drug-drug interactions with a severity-and-evidence-separation architecture that informed our own. Both are drug-anchored; supplement coverage is secondary.

Compliance and regulatory posture.

Medical device classification.

The Distil interactions checker is a rule-based reference tool. It looks up pre-curated pair data in a static database and returns published clinical findings with citations. There is no novel calculation, no machine learning, no personalised risk scoring, and no device-specific calibration. Every call on this page shows the evidence it drew on. Some rest on studies of the exact supplement and medicine together; others rest on mechanism evidence, which is how the standard clinical references handle pairs no one has trialled directly. The difference is that we mark which is which on every entry, so you can weigh it yourself.

We have assessed the checker against the Medicines and Healthcare products Regulatory Agency's guidance on stand-alone software, and our position is that it is not a medical device. It reports pre-curated findings from published literature rather than analysing your data to produce a new result about you. That position is our own reading of the guidance rather than a determination a regulator has made for us, and we will update this page if it changes.

Advertising standards.

The tool is an information surface, not product marketing. It reports documented interactions between products users already have or are considering. It does not promote a specific product, claim to treat or cure any condition, or recommend a supplement as a treatment. The brand-voice rules we apply to all customer-facing copy (probabilistic language, no medicinal claims) extend to the tool.

Data protection.

A pair check does not ask who you are. You type in supplement names, medication names, and optional context flags. We do not set a cookie or an identifier, build a profile, or keep a record of you as a user, and what you type is never stored against you. Like every page on the site, a check passes through our server logs, which hold your IP address for 30 days for security, and our usage log notes that a check was run under a daily code made from your IP address that cannot be turned back into it. The privacy policy sets out both. No personal data is used to decide anything about you: the answer depends only on the names you check.

The missing-item feedback form is the only part of the checker where you give us personal data (an email address and a free-text item description). It is opt-in, used only to acknowledge your submission and to tell you when the missing item is added, and you can opt out at any time. The lawful basis is consent under UK GDPR Article 6(1)(a).

UK GDPR Article 22 gives you the right not to be subject to decisions based solely on automated processing where those decisions have legal or similarly significant effects. The interactions checker does not engage Article 22, for three independent reasons. The pair-query flow captures no personal data for decision-making purposes. The tool returns information about documented interactions, not a decision about you. And where you act on the output, your GP or pharmacist is the gating reviewer for any clinical change.

NHS Digital Technology Assessment Criteria.

The DTAC framework applies when a digital health technology is procured or used by the NHS. The interactions checker is a consumer-facing free tool, not procured by the NHS. DTAC is not applicable at our current scale. If we ever pursue NHS partnership or NHS app library inclusion, DTAC assessment becomes required and we will publish that submission.

How we update the database.

The database is regenerated quarterly. Every quarter we publish:

• An updated data/interactions.yml reflecting any new evidence, withdrawn calls, or escalated reviews.
• An updated data/medications.yml against the most-recent NHS BSA Prescription Cost Analysis release.
• A calibration report listing every change since the prior quarter, with reasoning per change.

Each quarterly update ships to the live checker as soon as it lands, and the coverage counts on this page are stamped from the same data files the checker reads, so they cannot drift from what the tool holds.

If you cannot find a supplement or medication in our coverage, tell us. The feedback button on any result page adds the missing item to the queue of what we add next.

A note on what this section does not cover.

This part of the methodology page describes the interactions checker as it ships at launch. The compounds database that powers our supplement reports (the product described in part one above) has its own methodology, calibration log, and evidence-grading framework. The two methodologies share principles (probabilistic language, transparent inclusion rubric, quarterly cadence, published calibration reports) but the evidence base differs because supplement clinical literature is structurally thinner than drug-drug literature, a point Williamson's review of Stockley's Herbal Medicines makes explicitly.

When you click into a Distil supplement compound from a pair finding, you arrive at the relevant entry in our compounds database. The same evidence-grading rules apply on both surfaces.