simili.ai by Aquanta

Find the right remedy.

simili.ai is the first homeopathic remedy finder combining Bayesian statistical evidence with AI expert review. Validated on 1,700+ blind-tested clinical cases — on par with an experienced homeopath, 50% more accurate than traditional software. Describe symptoms in any language you speak.

Watch it work ↓ Try simili.ai free
“Similia similibus curentur”
— Samuel Hahnemann, Organon der Heilkunst, 1796

How simili.ai works

Four steps from symptoms to simillimum. In any language you speak.

1

Describe

Tell simili.ai about your symptoms in plain language. English, Dutch, French, German, Spanish — describe what you feel in whatever language comes naturally.

2

Clarify

simili.ai asks targeted follow-up questions to narrow down the differential. “Is the patient worse on the left side?” Each answer shifts the ranking.

3

Result

A Bayesian engine with 455,000+ symptom-remedy pairs ranks the most likely remedies. A confidence badge shows certainty. An AI expert reviews the ranking.

4

Explore

Dive into biochemical profiles, mechanism of action, and clinical signs for each suggested remedy. See where historical observations meet modern pharmacology.

Evidence + Intelligence

Two complementary approaches that cover each other’s blind spots. Together, they find the correct remedy in 94% of cases.

1

Bayesian Evidence

455,000+ symptom-remedy likelihood ratios from classical repertory sources and 1,700+ validated clinical cases. Each symptom shifts the probability of every remedy — pure statistical inference, no guesswork. Two modes in parallel: traditional repertory matching and AI-powered symptom extraction.

Statistical evidence
2

AI Expert Review

After the Bayes engine scores, an AI expert independently reviews the full case and the top-ranked remedies. It validates, challenges, or refines the ranking — and suggests differentiating questions to ask the patient. Like getting a second opinion from an experienced colleague.

Clinical intelligence
+

Better Together

The Bayes engine excels at systematic symptom-by-symptom analysis. The AI catches cases the statistics miss — rare remedies, unusual presentations, the “gestalt” of a case. In testing, Bayes rescued 64 cases the AI missed. The AI rescued 98 cases Bayes missed. Neither alone is as good as both.

1 + 1 = 3

Confidence: how certain is the result?

● High confidence
The top remedy stands out clearly, both engines agree
● Moderate confidence
A leading candidate emerges, but alternatives are close
● Low confidence
Several remedies score similarly, more symptoms needed

See it in action

A real rheumatic case — watch simili.ai work through it step by step.

simili.ai

What simili.ai does behind the scenes

Eight layers of technology that turn your words into evidence-based remedy suggestions.

19th-century English symptom texts are translated into modern clinical language, making them searchable and comparable. "Stitching pain in the praecordial region" becomes "sharp chest pain in the heart area."

Semantic embeddings map every symptom into a mathematical space where meaning matters, not spelling. This is why simili.ai understands any language and matches concepts, not just keywords. "Hoofdpijn" (Dutch), "Kopfschmerzen" (German), and "headache" all land in the same region.

An LLM reads your natural-language description and identifies specific symptoms, mapping them to the correct classical rubrics from Kent, Hering, Boericke, Allen, and Lippe. One sentence can contain multiple symptoms — the AI finds them all.

The Bayesian Evidence Engine uses 455,000+ symptom-remedy likelihood ratios from classical repertory sources for pure statistical inference — the same math used in evidence-based medicine. Two scoring modes work in parallel: traditional repertory matching maps your symptoms to graded Kent rubrics, while AI-powered extraction reads your natural-language description and identifies implied symptoms a keyword search would miss. Results are fused using Reciprocal Rank Fusion, combining the strengths of both approaches.

Each remedy ranking includes a confidence indicator based on two factors: how far the top remedy leads the second-place candidate (the score gap), and whether both scoring modes agree. When the top pick stands out clearly and both engines converge, confidence is high. When several remedies cluster together, confidence is lower — a signal to add more symptoms or ask follow-up questions.

After the Bayes engine scores, you can request an AI Expert Review. An AI expert independently reviews the full clinical picture and the top-ranked remedies, then validates, challenges, or refines the ranking. For each assessed remedy, it suggests a differentiating question to ask the patient — click Add to add the implied symptom and re-score. The expert also provides its own independent top-5 ranking with rationale. Like a second opinion from an experienced colleague.

We extracted the chemical compounds of remedy source substances and compared them against SIDER, a database of 163,000+ known pharmaceutical side-effects. For key remedies like Arsenicum album and Belladonna, the majority of known pharmaceutical effects were already described in 19th-century provings. This suggests that historical observers captured real, measurable pharmacological phenomena.

There is measurable overlap between homeopathic remedy indications and conditions treated by conventional pharmaceuticals. simili.ai surfaces this overlap — not to create conflict, but to assist integrative practitioners who work with both traditions. Same data, different lens.

Where 200-year-old observations meet modern pharmacology

We compared classical remedy descriptions against SIDER, a database of 163,000+ pharmaceutical side-effects. The data shows notable patterns.

Arsenicum album

Arsenic trioxide (As₂O₃)
134 / 169 Pharmaceutical effects found in classical descriptions
79% Match rate with SIDER database

Key alignments

  • Decreased appetite — described 1828, confirmed by modern toxicology
  • Peripheral neuropathy — "tearing pains in limbs" matches arsenic-induced nerve damage
  • GI distress — classical "burning stomach pains" matches arsenic gastropathy
  • Eye irritation — exact match (similarity 1.000)

Belladonna

Atropine alkaloid (Atropa belladonna)
130 / 173 Pharmaceutical effects found in classical descriptions
51% Match rate with SIDER database

Key alignments

  • Dry mouth — xerostomia, classic anticholinergic effect described in provings
  • Tachycardia — rapid pulse and bounding heartbeat, a well-known atropine effect confirmed by modern pharmacology
  • Blurred vision — accommodation disorder, mydriasis still used in ophthalmology
  • Skin dryness — inability to sweat, parasympathetic blockade
Preprint

Systematic validation: 78 remedies tested

The SIDER comparison above illustrates individual cases. In a systematic study across 78 remedies, we used embedding-based semantic alignment to compare 19th-century proving symptoms against modern clinical toxicology. Result: 22 remedies show statistically significant alignment (22.6× enrichment, p = 9.8 × 10⁻²⁴), while negative controls (lactose, ethanol, mineral water) show no signal. This suggests that where a substance has known toxic effects, historical provers independently described them.

Read paper (PDF) →

All data on this page is extracted from our database — SIDER pharmaceutical side-effects, classical repertory sources, and the ATC drug classification system. Nothing is invented or generated. This demonstrates internal coherence between historical observations and modern pharmacology. It does not constitute evidence of homeopathic therapeutic efficacy.

Tested on 1,700+ clinical cases

simili.ai was blind-tested on real clinical cases from hpathy.com and peer-reviewed medical journals. No cherry-picking, no pre-selection.

Method Top-1 Top-5 Source
simili.ai 36–42% 65–72% 1,700+ blind cases
Experienced homeopath 25–55% 55–75% Literature consensus
Traditional repertory software 15–30% 40–60% Literature consensus
Homeopathic Housecall (AI) 17% — Gimeno-Miguel 2025
Top-1

The correct remedy is the system’s
#1 suggestion

Top-5

The correct remedy appears in the
top 5 suggestions

With Expert Review enabled, the combined system identifies the correct remedy in the top 20 in 94% of cases. Sources: Frei 2006 (Homeopathy), Gimeno-Miguel 2025 (Healthcare), Chand 2025 (Homeopathy).

For practitioners of all traditions

Whether you practice homeopathy, integrative medicine, or conventional medicine — simili.ai provides data-driven insights into 200 years of clinical observations.

Same mathematics

Bayesian likelihood ratios and AI expert review — grounded in the same evidence-based principles used in conventional medicine.

Same databases

SIDER pharmaceutical side-effects, ATC drug classifications — the same data used in drug safety research.

Different lens

Classical homeopathic observations viewed through the tools of modern data science. No conflict — just data.

"Can't I just ask ChatGPT?"

You can. But here's what happens behind the scenes — and why the answers are fundamentally different.

ChatGPT Large Language Model

How it works

A language model predicts the next most likely word. When you ask about a remedy, it retrieves whichever remedy appeared most often near those words in training data — a popularity contest, not a medical calculation.

  • ⚠ Frequency bias. Belladonna, Arnica, and Nux vomica dominate the internet. An LLM suggests these “big names” disproportionately — even when a less common remedy fits better.
  • ⚠ No combined reasoning. Adding a second or third symptom doesn’t mathematically shift the ranking. The model just produces a new best guess based on all words together.
  • ⚠ No confidence score. It cannot say “72% probability, HIGH confidence.” It gives you an answer that sounds certain, whether it is or not.

simili.ai Bayesian Engine + AI Expert Review

How it works

simili.ai matches your symptoms against a curated database of 455,000+ graded symptom-remedy pairs from classical sources. A Bayesian engine scores every remedy, an AI expert independently reviews the result. Every score is traceable — you can see exactly which symptoms drove each ranking.

  • ✓ No popularity bias. Staphysagria and Kali carbonicum get the same fair treatment as Belladonna. The math doesn’t care what’s popular on the internet.
  • ✓ Combinatorial reasoning. Adding “jealousy + loquacity” points to Lachesis. Add “thirst” and it shifts toward Hyoscyamus. Each symptom mathematically updates the entire ranking.
  • ✓ Probability + confidence. “Lachesis: 36.3%, HIGH confidence” — and you can see exactly which symptoms drove that score.

simili.ai uses an LLM too — to understand your natural language, extract symptoms, and provide an expert review. But the core remedy ranking uses Bayesian statistical inference on 455,000+ curated symptom-remedy pairs — not a language prediction.

Research

Water, quantum biology, and the science we find fascinating.

Preprint

Embedding-Based Semantic Alignment Between Provings and Toxicology

22 of 78 remedies show statistically significant semantic alignment with modern clinical toxicology (22.6× enrichment). Negative controls show no signal.

G. Pollet Aquanta Research, 2026
Hypothesis

The Elephant in the Water

Could water be a quantum computer? An exploration of quantum biology, graphene structures, and coherent water.

G. Pollet Aquanta Research
Article

The Unique Physiology of Water

Water defies known physical laws. A look at what we do and don't understand about the most common molecule on Earth.

K. Bongers VNIG 2019
Research

Water Separates into Two Liquids

At supercooled temperatures, water exists as two distinct liquids with different topological structures. Published in Nature Physics.

A. Neophytou et al. Nature Physics 2022
Research

Quantum Tunneling in Water

Protons in water trimers bypass energy barriers through coordinated quantum tunneling. Published in Nano Letters.

J. Heo et al. Nano Letters 2025
Research

Water Molecules Are Asymmetric

Each water molecule forms one strong and one weak hydrogen bond, creating organized structures that contradict assumptions about liquid disorder.

C. Schneider et al. Nature Comms 2024
View all research

Try simili.ai today

10 free consultations per month. No credit card required.

Create free account