Understand the night.
Beyond the signal.
In-ear EEG and AI for sleep research.
Connect recording summaries, diaries and research into evidence-linked reviews—with the context intact.
LONGER CONTEXT.
Capture → context → evidence → review
FROM THE EAR TO THE RESEARCH QUESTION
A discreet interface.
A much wider
field of understanding.
MZR develops an in-ear EEG interface for brain monitoring, with a research focus on sleep.
Our AI-assisted workspace connects authorized signal summaries with the context around a study, keeps sources attached, and prepares better questions for qualified reviewers.
Explore sensing and analysisResearch foundation: UC Berkeley IPIRA ↗
AN OVERNIGHT RECORD, IN CONTEXT
Follow a night.
Keep the gaps visible.
Select a moment in an authored recording. See how acquisition records, a diary, and a reviewer question tell different parts of the story.
Capture context
Start with the recording—not a score.
The source window starts at 22:00. A review needs the device session, recording identifier, and analysis version before it can interpret any derived result.
Demonstration only. No patient data, live acquisition, diagnostic inference or model request is used on this website.
WHAT A NIGHTLY NUMBER CANNOT TELL YOU
A trace captures activity.
A diary captures experience.
Understanding needs context.
Not every difference is a trend.How the AI layer is designed
THE LANGUAGE-MODEL LAYER
More than a summary.
A review with a memory.
Explore how the AI layer connects recording summaries, diaries, protocols and prior review decisions—without hiding uncertainty.
Ask across sources.
Go back to the evidence.
LONGITUDINAL CONTEXT
PREPARED EXAMPLEMore reviewable minutes. A different method. Not yet a comparable trend.
N-03 has 48 more reviewable minutes than N-02, but its analysis version also changes the exclusion criteria. The AI needs to reconcile the method note, coverage register and reviewer context before calling the difference a study finding.
- Checked calculation: 440 − 392 = 48 more reviewable recording minutes.
- Method conflict: N-01 / N-02 use version 1.2; N-03 uses version 1.3.
- Next check: assess consistent processing and comparability. Do not infer better sleep from higher recording coverage.
SENSING AND INTELLIGENCE, CONNECTED.
Small enough to
change the interface.
Thoughtful enough
to keep the context.
The in-ear form factor is the research foundation. The software connects repeated recordings, study notes and review decisions rather than leaving them in separate systems.
Inside the technology directionTHE AI RESEARCH WORKSPACE
Six ways to make
the context useful.
Six connected capabilities bring recording summaries, study context and review history together. Each has defined inputs, reviewable outputs and a human decision boundary.
Longitudinal reasoningRead the whole study, not just last night.
Bring multiple recording summaries, quality flags, participant notes, and prior reviewer decisions into one contextual review. Separate a recurring observation from a gap in the data.
- CONTEXT IN
- Versioned session summaries, coverage records, diaries and annotations
- WORK OUT
- Cross-night narrative with explicit comparability limits
- REVIEW POINT
- Confirm that analysis methods and recording conditions support the comparison.
Diary & annotation alignmentConnect the signal story to the human account.
Extract reported events from a sleep diary or interview. Align approximate time references with recording intervals while preserving uncertainty and disagreement between sources.
- CONTEXT IN
- Consented diaries, study interviews and event annotations
- WORK OUT
- An aligned event register and questions needing clarification
- REVIEW POINT
- Do not infer symptoms, emotions or causation from a trace or a sentence alone.
Source-grounded study questionsAn answer with somewhere to go back to.
Retrieve relevant passages from an approved study context. Draft an answer that points to the recording summary, reviewer note, or protocol section behind each material statement.
- CONTEXT IN
- Authorized study records, source intervals and approved protocols
- WORK OUT
- A cited response separating observations, interpretations and unknowns
- REVIEW POINT
- Check citation support, source authority and unresolved evidence.
Protocol & documentation reviewFind what the review packet is missing.
Compare a study packet with its approved documentation requirements. Surface missing identifiers, absent approvals, mismatched versions, and unrecorded decisions for the study coordinator.
- CONTEXT IN
- Study-specific checklists, session metadata and review status
- WORK OUT
- Documentation exception list and a coordinator handoff
- REVIEW POINT
- A software flag is not an ethics approval or regulatory determination.
Research knowledge synthesisKeep the literature separate from the participant.
Organize a team-approved library of papers and method notes. Compare research questions, study populations, measurement methods and limitations without presenting a publication as evidence about an individual.
- CONTEXT IN
- Approved papers, method documents and structured research questions
- WORK OUT
- A referenced literature matrix and limitations summary
- REVIEW POINT
- Verify source access, quotation accuracy, applicability and publication context.
Structured reports & handoffsFrom a long review to a useful next step.
Draft research summaries, reviewer questions and study-coordination briefs using a defined schema. Carry source links, limitations, version references and ownership into the handoff.
- CONTEXT IN
- Reviewed findings, source references and the intended audience
- WORK OUT
- An editable brief, question list or structured JSON draft
- REVIEW POINT
- An authorized person approves the final interpretation and distribution.
BUILT AROUND THE PEOPLE ASKING BETTER QUESTIONS
For the next
generation of
sleep research.
Sleep research teams. Neurotechnology developers. Clinical innovation partners.
Different questions, one shared need: records that remain traceable from acquisition to interpretation.
Explore collaboration pathsA CLEARER PICTURE
Questions worth
asking early.
Is this a device, an AI platform, or both?
MZR’s research foundation is an in-ear EEG interface. This website develops a software layer around that foundation: signal-aware records combined with a source-grounded language-model layer for research review. It is not a claim that all displayed software is commercially available.
What does the large language model actually do?
It reads authorized summaries, diaries, annotations, protocols and approved research material. The intended tasks include cross-night synthesis, evidence retrieval, contradiction handling, documentation checks, and structured report drafting. It does not directly turn arbitrary raw EEG into a medical diagnosis.
What is different from an ordinary sleep score?
The emphasis is on reviewable context: which records support a statement, which intervals cannot be interpreted, what changed across nights, and what a qualified reviewer still needs to check. No proprietary scoring accuracy is claimed here.
Are the waveform and study examples real patient data?
No. All traces are synthetic and all demonstration records are authored. The website does not acquire EEG, access patient systems, or call a live language model.
Is regulatory clearance or clinical efficacy claimed?
No. This website does not establish FDA clearance, a cleared indication, clinical equivalence, diagnostic accuracy or treatment efficacy. Clinical claims and product availability require separate verification.
Can our team discuss a research collaboration?
Yes. Use the collaboration page to prepare a non-sensitive project brief and access the public company contact route. Define the research question, data scope, review roles and acceptance criteria before connecting records.
THE NEXT QUESTION IS WORTH EXPLORING