Emily

1. Context

New motherhood is an intense, under-supported period. Amid erratic sleep and a wide emotional range, new and breastfeeding mothers carry constant, low-grade questions about their own wellness — questions that rarely rise to the level of a doctor's visit but accumulate into real anxiety. Existing tools tended to solve for one thing at a time: a tracker logged feedings, a journaling app captured mood, a clinic ran a test. Nothing connected the emotional experience of new motherhood to concrete, actionable health insight.

New moms go through a lot. Amidst the wide range of emotions and erratic sleep schedules, it's understandable for new moms to have questions about their own wellness as they adjust to life with baby — especially if they're also breastfeeding.

— Maslo, Meet Emily

Maslo's opportunity was to combine its empathetic-companion platform with clinical partner Lactation Lab's expertise, and deliver companionship and clear wellness insight in a single, low-effort experience.

2. Problem & Constraints

Core problem: How might we give a new or breastfeeding mother emotional support and trustworthy health insight in the small, exhausted moments she actually has — without adding another chore, and without overstepping into unsafe medical territory?

• Minimal effort. A sleep-deprived parent won't complete long forms; input had to be as fast as speaking a sentence.
• Health-grade caution. Maslo's company-wide principle forbids autonomous diagnosis or prediction without human validation — especially in a health and mental-health context.
• Emotional and physical in one place. The tool had to treat 'I feel connected' and 'I have a sore ankle' as equally valid, capturable signals.
• Clinician-ready output. Anything logged had to be exportable in a form a doctor or lactation consultant could actually use.

We never ever deploy single algorithm approaches. And we simply do not allow diagnostics nor predictions without human validation. This shaped every decision below — the AI provides empathy and insight; a physical test provides data; a human clinician provides the judgment.

— Guiding principle carried from Maslo's research

3. Method Rationale

Voice-and-text journaling as the primary input

Rather than structured questionnaires, Emily uses personalized prompts that invite a mother to express her physical and emotional state in her own words, by voice or text. This lowers effort to near zero and captures the messy, mixed reality of how someone actually feels, which Maslo's empathetic AI then analyzes into insight per entry.

An empathetic companion, not a form

Framing the tool as a companion — something that responds with warmth to whatever is shared — was chosen to build the trust required for someone to disclose honestly during a vulnerable period. The companion accepts both wins and worries with the same openness.

A physical diagnostic wrapped in the companion

For the one area where real clinical value was possible — mastitis risk — the team paired a physical test strip with in-app scanning rather than relying on an algorithm to 'guess' from behavior. The AI's job stops at insight and a next-step suggestion; the data comes from chemistry, and escalation goes to a human.

4. Process

The Emily experience is built from four connected capabilities:

• Empathetic journaling. Personalized prompts encourage voice or text entries about physical and emotional state; Maslo's empathetic AI analysis returns insight drawn from each entry.
• Care tracking. Mothers log breastfeeding and diaper-change times, compiled into an exportable format that aids doctors and clinicians in reviewing patient health.
• At-home mastitis testing. The user applies a breastmilk sample to a test strip and scans it directly in the app. LDH levels in the sample provide insight into the wellness of both mother and baby.
• Guided next steps and escalation. Based on results, Emily suggests next steps and can connect the user directly with a lactation consultant when needed.

The critical UX moment is the scan-to-result-to-action flow — turning a physical strip into an immediate, understandable insight and, when warranted, a warm handoff to a human expert:

5. Synthesis

Individual journal entries and test results are only useful if they add up to something a person — and her clinician — can act on. Emily synthesizes across the streams in two directions:

• For the mother: per-entry empathetic insight in the moment, plus immediate interpretation of a physical test, so anxiety is met with an answer rather than a search engine.
• For the clinician: feeding and diaper logs compiled into an exportable record, giving a doctor or lactation consultant real longitudinal context instead of recalled fragments at an appointment.

6. Findings & Design Decisions

• Empathy earns disclosure. Treating emotional and physical complaints with equal, warm acceptance is what makes a vulnerable user willing to share the honest signal the product needs.
• Effort is the real adoption barrier. For an exhausted user, speaking a sentence beats completing a form; input friction, not feature count, determines whether the tool gets used at all.
• Put chemistry where you'd be tempted to put a model. A physical test plus a human handoff is more trustworthy — and safer — than an algorithm inferring health from behavior.
• Design the handoff, not just the insight. The moment of connecting a worried user to a lactation consultant is as much a part of the UX as the scan itself.

7. Outcome

Emily shipped as a released product, with mastitis test strips available to all Emily users through Lactation Lab. It stands as Maslo's clearest example of empathetic AI applied to a real, high-stakes moment: AI provides empathy and insight, a physical test provides data, and a human clinician is always one tap away.

Emily's simple at-home mastitis testing gives moms peace of mind with immediate results — so they can focus on connecting with their families.

— Maslo, Meet Emily

8. Reflection

Emily is a compact demonstration of a philosophy: keep the human in the loop, minimize effort, and pair emotional support with concrete utility. If I were extending it, the highest-value research questions would be longitudinal — does daily empathetic journaling change how supported mothers feel over the first postpartum months, and does the exportable log measurably improve the quality of clinician conversations? Those are exactly the outcome measures that separate a nice companion from a clinically meaningful one.