Meet CEREBRA™
A mixture-of-experts medical model. Trained only on medicine.
Cerebra is the day-to-day clinical assistant inside the GutIQ stack — eleven specialist sub-models routed through a single conversation, every answer grounded in primary literature, and a strict guardrail that turns away anything outside medicine. Built for patients on a programme; useful for anyone asking a careful question.
One general model can't think like eleven specialists.
General-purpose chatbots are trained on the open internet — a corpus heavily weighted toward forum opinion, marketing copy, and old wives' remedies. They will happily compose a confident paragraph about a gut symptom while citing nothing more rigorous than a wellness blog. That is not what medicine looks like.
Cerebra is the opposite. It is a mixture-of-experts (MoE) system — a small constellation of specialist sub-models, each fine-tuned on its own narrow slice of the literature, with a router that picks the right experts for the question in front of you. You see one continuous conversation; underneath, the question on slow transit goes to the motility expert, the question on bloating after antibiotics goes to the dysbiosis and pharmacology experts. The result is an assistant that reasons like a tumour board, not a search bar.
Eleven experts. One conversation.
Each expert is fine-tuned on its own domain corpus. The router model — itself fine-tuned on 60,000 labelled clinical questions — chooses which subset to activate. Most queries route to two or three.
IBS, dyspepsia, slow transit, pelvic-floor dysfunction. ROME-IV grounded.
Dysbiosis, SIBO, post-antibiotic recovery, fermentation patterns.
FODMAP biochemistry, fibre fractions, micronutrient interactions.
Drug-induced GI effects, PPI tapering, prokinetics, antibiotic stewardship.
Vagal tone, stress–symptom coupling, visceral hypersensitivity.
Stool, breath, blood marker interpretation; when to escalate to imaging.
Reads your daily log series. Detects rebounds, plateaus, false-positives.
Migrating motor complex, shift-work patterns, melatonin–gut crosstalk.
Intensity–GI symptom curves, hydration, race-day protocols.
Always-on. Flags blood, weight loss, nocturnal pain, fever before answering.
Translates expert outputs into a single voice. Calibrates reading level to you.
Reads your question, picks experts, weights their answers, returns one response.
What we feed it. What we don't.
Cerebra is fine-tuned exclusively on medical literature and our own de-identified clinical record. No Reddit. No Quora. No wellness influencers. No raw web scrape.
GI, microbiome, nutrition, and adjacent specialties. Filtered to peer-reviewed primary research, systematic reviews, and meta-analyses.
The gold standard for evidence synthesis. Weighted heavily in expert e_06 (Diagnostics) and e_04 (Pharmacology).
Open-source medical Q&A and reasoning datasets used for instruction-tuning. Lets Cerebra answer in the way a clinician would, not the way an essay would.
Standardised terminology so symptom descriptions map cleanly to recognised conditions, not improvised labels.
NICE (UK), British Society of Gastroenterology, American Gastroenterological Association. Cerebra defaults to guideline-consistent guidance.
Across 25,000+ consultations: symptom progressions, what worked, what didn't, intervention sequences. The pattern library that gives Cerebra its bedside intuition. Every record is stripped of names, emails, phone numbers, dates of birth, and free-text identifiers before any model sees it.
Last full retraining: 2026-04 · Next scheduled refresh: 2026-08 · Continuous reference-document index updated weekly
Your record is yours.
You can opt out at any time.
We treat training data the way a regulated lab treats patient samples: identifiers stripped at source, access logged, and the right to withdraw is yours unconditionally.
Manage training-data preferencesName, email, phone, address, date of birth, and any free-text identifier are removed by a dedicated pipeline before training data is staged.
A single toggle in your settings excludes all of your data — past, present, and future — from any further retraining. Your reports, your plan, and the chat itself continue working unchanged.
Cerebra runs on infrastructure we control. Conversations are not shared with third-party LLM providers and are never used for advertising.
Delete your account and we expunge associated records from the training pool. The next retrain re-runs without them.
Ask a careful question.
Get a careful answer.
A sample conversation. Notice the routed-experts strip up top, the citations under each answer, and the medical-only guardrail at the bottom of the composer.
I've been waking up with bloating for three weeks. It's worst after dinner, and a glass of wine seems to make it worse the next morning. Anything I should look at first?
The pattern you're describing — overnight accumulation that's worse after dinner and amplified by alcohol — is most consistent with delayed gastric emptying or fermentation in the distal small bowel. A few practical first steps that are well-supported in the literature:
1. Shift dinner earlier. A 12-hour overnight fast (e.g. 7pm → 7am) gives the migrating motor complex time to sweep the small bowel. This alone resolves overnight bloating in ~40% of cases.
2. Cut alcohol for 10 days. Alcohol delays gastric emptying and increases small-intestinal permeability; both will amplify next-morning bloating even when intake feels modest.
3. Watch for FODMAP density at dinner specifically. Onion, garlic, legumes, and wheat carry more fermentable load than people realise. We don't recommend a full exclusion yet — just track the meal context for a week.
If the bloating is still present after 10 days of (1) and (2), that changes the picture and we should look at SIBO testing as the next step.
Should I just start taking a probiotic?
Not yet — and probably not the way the supermarket aisle implies. Three things to know:
First, generic multi-strain probiotics show essentially no effect on overnight bloating in randomised trials. The strains that have evidence (Bifidobacterium infantis 35624, Saccharomyces boulardii for post-antibiotic recovery) are specific.
Second, starting a probiotic now would confound the 10-day dinner-timing trial. You wouldn't know which change moved the needle.
Third, if your bloating turns out to be SIBO-pattern, certain probiotics can worsen it temporarily by adding to the small-bowel fermentable load.
So: hold off, finish the trial above, and if symptoms persist we'll look at a targeted strain — not a generic blend.
Cerebra is for information and triage; it is not a substitute for an in-person clinician. Anything that suggests urgent harm is routed straight to a human consultant.
What Cerebra will and won't do.
- → Interpret symptoms, food triggers, supplement choices.
- → Read your daily log series for trend signal.
- → Explain lab results in plain English with primary citations.
- → Suggest questions to bring to your consultation.
- → Compare evidence on common interventions (probiotics, fibre, FODMAP, etc.).
- → Triage red flags and recommend escalation when warranted.
- × Non-medical chat. Cerebra politely redirects.
- × Definitive diagnoses. Cerebra reasons; clinicians decide.
- × Prescriptions or dose adjustments without consultant approval.
- × Mental-health crisis management. Escalates to human + signposts crisis lines.
- × Areas outside its training: cardiology, oncology specifics, surgical decision-making.
- × Anything advisable only with imaging in hand.
Under the hood.
Common questions.
Is Cerebra ChatGPT under the hood?
How is this different from asking a general LLM?
What happens if I ask Cerebra something non-medical?
Can I really opt out of training and still use Cerebra?
Will Cerebra ever replace a doctor?
How often does Cerebra get retrained?
Cerebra ships inside every PURO™ and CORE™ programme.
And a free preview ships with every account. Take the quiz, get your gut profile, and the chat opens with the first three questions worth asking already drafted.
Cerebra is a registered research product of GutIQ. Not a medical device.