AMBUJA HEALTH · CLINICAL INTELLIGENCEHUMANE AI · LIVE

Issue No. 001  ·  Customer Study

How Ambuja Health reduced patient dropout 32% in six weeks — by giving their AI a memory.

Ambuja Health's clinicians ship longitudinal care to patients across mental health, chronic illness, and post-partum recovery. Their AI assistant forgot its patients every session. Humane AI gave it a behavioural memory — and the numbers changed fast.

Vertical
Clinical care · longitudinal
Deployment
6 weeks · single clinic pilot
Stack
Python SDK · GPT-4 class · BYOK
Outcome
−32% dropout · +41% adherence
Section · The Problem

The AI greeted a patient on session 47 the same way it greeted a stranger on session 1.

When Ambuja's team first shipped an LLM-backed assistant, the conversations were coherent. They were also context-blind. A woman with post-partum anxiety who had been talking to the system for two months was treated identically to someone opening the app for the first time — same greeting, same coaching cadence, same tone.

Patients noticed. Dropout climbed. Clinicians noticed too — handoff notes read like the AI had never met the person before. Raw GPT-4 is stateless by design; every session is session one.

The deeper problem surfaced when the system couldn't tell when a patient's mood was crashing across sessions. A declining trajectory — subtle across three messages on Tuesday, obvious across forty messages over six weeks — was invisible.

Section · The Mechanism

Humane AI sits between the LLM and the patient. On every message it ships five signals the model alone can't produce.

01

HumanState

Energy, mood, fatigue, and frustration tracked per-patient with temporal decay. Context emerges from state, not prompts.

02

Relational Memory

Semantic recall of the last 47 conversations, not the last 47 tokens. MemPalace (ChromaDB) retrieves what's relevant, not what's recent.

03

Timing & Delay

Responses pace with patient energy. A tired patient at 11 pm doesn't get the same reply cadence as a morning clinical review.

04

Values Boundary

Safety gate fires BEFORE the LLM — ~300 ms. Blocked messages never burn tokens; escalations reach a human in under a minute.

05

Proactive Triggers

Policy engine fires when a patient's trajectory matches a clinician-authored rule — sustained mood drop, silent re-engage, trust milestone.

06

Ambuja's own policies

Clinical team authored 12 rules in behavioral DSL (YAML). Post-partum crisis, dose-response escalation, caregiver burnout — all as code.

AMBUJA HEALTH · CLINICAL INTELLIGENCESATURDAY, APRIL 18HUMANE AI · LIVE
Ambuja. HEALTHAttending · Dr. Sharma

Patients · 5

Emma

recovery

James

chronic

Priya

anxiety

Marcus

fitness

Sarah

post-partum

E
Honestly I'm exhausted. I fell off the routine last week when my son got sick and now I just feel like I'm back to zero.
A
Eleven days ago you told me you were worried about exactly this — that being needed at home would knock you off your stride. You're not back to zero. You paused. That's different.
E
Why do I always do this.
Analyzing mood trajectory · Pulling session 23–31 context · Checking self-criticism pattern

Humane signals

Mood32%
Energy21%
Trust78%
Familiarity94%

Policy triggered

sustained_low_mood

Clinician notified

Session · 47 of 62Relational recall · 12 of 47 prior sessions referencedLatency · 280 ms
Section · The Numbers

What shifted when the assistant actually remembered.

Session-2 dropout

−32%

Before

38%

After

26%

Patients returning for a second session after their first interaction.

7-day adherence

+41%

Before

52%

After

73%

Patients completing their clinician-assigned protocol within a week.

Clinician handoff quality

+54%

Before

2.8 / 5

After

4.3 / 5

Internal rubric — did the human clinician receive usable context about the last session?

Dropout curve · Weeks 1–6 · Raw LLM vs Humane AI

10%20%30%40%W1W2W3W4W5W6RAW GPT-4HUMANE AI

Dropout on raw GPT-4 held at ~38% from week 2 onwards — about where every chatbot experiment lands at six weeks. Under Humane AI, dropout dropped fastest in weeks 3–4, after the behavioural memory had enough signal to personalise pacing.

SIGNALS · Proactive events from the policy engineLIVE · 12 events today
  • 14mSarah · post-partumSustained low mood — 4 sessions, trend −0.18. Clinician escalation triggered.crit
  • 1h 22mPriya · anxietySilent re-engage — 73 hours since last interaction. Reach-out message staged.warn
  • 3hJames · chronicTrust milestone crossed (0.70). Advanced protocol unlocked.info
  • 6hEmma · recoveryAdherence 7/7 — weekly affirmation cue queued.info
Section · Clinical verdict
“The difference isn't that the AI got smarter. The difference is that it started paying attention. Our patients feel recognised — and the retention data proves it isn't placebo.”
AS

Dr. Ananya Sharma

Clinical Director · Ambuja Health

Try it

Ship behavioural memory to your LLM in an afternoon.

Humane AI installs in front of any of 20+ LLM providers. Works with the same API key you already have. Ambuja's entire pilot ran on pip install humane-ai.

Numbers from Ambuja Health's pilot are directional; six-week single-clinic n = 127 patients. Full methodology available on request.