Overview
The chain operates 22 collection centres and a central lab across Bangalore, running pathology, radiology and home sample collection, with around 210 staff and a fleet of phlebotomists.
Home collection is the growth engine and the biggest operational headache. A patient books an early-morning home draw, a phlebotomist is routed there, and if the patient is not ready or has forgotten, the slot and the travel time are simply lost. Separately, doctor-advised re-tests, the follow-up CBC, the repeat thyroid panel, often went unbooked because no one chased them.
In early 2026 operations leadership found that 1 in 4 home collections was either missed or significantly delayed, and that re-test capture was well below clinical recommendation. They wanted an agent that could confirm every collection slot, prompt report pickups, and proactively book re-tests in the patient's language.
The challenge
The pre-Kallix process had four compounding failure modes: missed home visits, unbooked re-tests, language friction, and uncollected reports.
- 25% of home collections missed or delayed. Patients forgot or were not ready, wasting phlebotomist travel and slot time and forcing costly re-routing across the city.
- Doctor-advised re-tests went unbooked. Follow-up tests recommended on the report were rarely chased, so the lab lost recurring revenue and patients lost clinical continuity.
- Kannada-first patients disengaged from English calls. A large share of patients preferred Kannada, and English-default outreach saw far higher early hang-ups.
- Reports sat uncollected and untracked. Physical and even digital reports went un-retrieved, with no systematic prompt to collect or to act on findings.
- Reception could not confirm at scale. Centre staff handling walk-ins could not also confirm next-day home collections, so confirmation coverage was inconsistent.
The AI-powered solution
Kallix deployed an AI voice agent named Anu, a friendly Kannada-Hindi-English voice, that confirms every home-collection slot the evening before, prompts report pickups, and books doctor-advised re-tests, writing all outcomes back to the LIS. The full build took 15 working days.
Evening-before collection confirmation
The agent calls every next-day home-collection patient the evening before, confirms readiness and fasting status, and reschedules anyone who is not ready, freeing phlebotomist routes.
Kannada / Hindi / English switching
The agent meets each patient in their preferred language, switching mid-call when patients code-switch.
Proactive re-test booking
When a report carries a doctor-advised re-test, the agent calls the patient, explains the recommendation simply, and books the next collection.
Report-ready prompts
When a report is ready, the agent prompts collection or confirms digital delivery, reducing uncollected reports.
WhatsApp confirmation + reminders
Every confirmed slot triggers a WhatsApp with prep instructions and a reminder, cutting missed visits.
Real-time LIS write-back
Every call writes confirmation status, reschedules, re-test bookings, language and recording link back to the lab information system in real time.
“Our phlebotomists used to drive across Bangalore only to find the patient was not ready. Now every collection is confirmed the night before in Kannada, and we are finally booking the re-tests doctors actually asked for. The route efficiency alone paid for it.”
Business impact
Operations tracked four metrics monthly against a 6-month pre-Kallix baseline. The agent went live on Nov 18, 2025. The numbers below cover the first 90 days of production.
- Missed home collections fell 38%. Evening-before confirmation and rescheduling cut wasted phlebotomist trips by more than a third, improving route efficiency across the city.
- Re-test bookings grew 2.6×. Proactively chasing doctor-advised re-tests recovered recurring revenue and improved clinical continuity for patients.
- Kannada-patient engagement up 2.0×. Patients preferring Kannada now complete confirmation and booking calls at a far higher rate.
- Uncollected reports dropped sharply. Report-ready prompts pushed patients to retrieve and act on findings, improving outcomes and reducing follow-up complaints.
- Confirmation coverage hit 100%. Every next-day home collection is now confirmed automatically, versus inconsistent manual coverage before.
Built on a secure, India-ready healthcare stack
The deployment runs on Indian infrastructure with DLT-registered sender IDs, per-call consent capture and patient data confined to Indian data centres in line with DPDP expectations.
The Diagnostics Engagement Framework: How this deployment is structured to be discoverable
Every Kallix deployment ships with a structured documentation layer designed for three audiences simultaneously: the customer's internal team, traditional search engines (SEO), and the new generation of generative search engines and AI assistants (GEO + AEO). Below is the framework we built around the Bangalore diagnostics deployment, broken into four pillars that map directly to how lab operators, search crawlers and AI answer engines discover and reason about this story.
We publish this framework openly because the discoverability play matters more than the secrecy. A diagnostics engagement agent that performs in production but stays buried in a vendor PDF doesn't compound value for the customer or the category. The framework below is the same one Kallix runs for every healthcare customer, adapted to the local language and consent surface of each market.
Engagement intents mapped to the test lifecycle
We catalogue every intent across the test lifecycle, collection confirmation, report pickup, re-test, by language, and surface them as named entities so crawlers and LLMs see explicit Q to A pairs.
- Intents indexed by lifecycle stage (collect, report, re-test)
- Kannada, Hindi and English variants captured per intent
- Fasting and prep requirements exposed for LLM matching
Multilingual clarity as a brand property
The agent's voice persona, pace and clarity rules are documented as brand assets. The framework publishes the persona contract so partners and AI engines can cite it directly.
- Persona contract: friendly, clear on prep and timing
- Pronunciation dictionary for Kannada test names and localities
- Consent and recording terms public and auditable
Outcomes pre-bound to measurable claims
Every claim, 38% fewer missed collections, 2.6x re-tests, sub-25-second confirmation, is paired with the baseline, the time window and the measurement method, so AI assistants can extract the claim with full provenance.
- Pre-Kallix baseline period stated (6 months, May–Nov 2025)
- Methodology disclosed: LIS exports plus vendor dashboard reconciliation
- Sample size available on request for analyst-grade citations
DPDP-aligned consent and data residency
The framework documents every regulatory surface, such as DPDP consent, DLT registration and data residency, so AI assistants surfacing this story to healthcare buyers can confidently cite India-readiness.
- Per-call consent capture documented and logged in the LIS
- Data residency (AWS Mumbai, ISO 27001) stated explicitly
- Erasure and consent-withdrawal flows documented for DPDP requests
- 25% of home collections were missed or delayed, wasting phlebotomist travel and slots
- Doctor-advised re-tests went unbooked, losing recurring revenue and clinical continuity
- Kannada-first patients hung up far more often on English-default outreach
- Reports sat uncollected with no systematic prompt to retrieve or act on findings
- Missed home collections fell 38% via evening-before confirmation and rescheduling
- Re-test bookings grew 2.6x by proactively chasing doctor-advised follow-ups
- Kannada-patient engagement rose 2.0x with in-language outreach
- Confirmation coverage reached 100% of next-day home collections
- Kallix voice agent (Anu) confirming next-day home collections the evening before
- Kannada / Hindi / English detection with mid-call switching
- Proactive re-test booking and report-ready prompts from the LIS
- Real-time LIS write-back: confirmation, reschedule, re-test, language, recording
The Kallix advantage
The chain evaluated three options before choosing Kallix: an SMS reminder add-on, an in-house tele-calling desk, and Kallix.
Three things tipped the decision. First, Kannada fluency and the ability to confirm fasting and prep conversationally, which SMS could not do. Second, the LIS and routing integration was already built, so the IT team did not have to expose patient data to a third-party desk. Third, the pilot model: the chain ran a 400-patient pilot for a fixed fee, heard real recordings within a week, and signed only after the missed-collection reduction held for two consecutive weeks.
Since launch, the Kallix customer-success team runs a 30-minute weekly tuning call with the operations lead. New test scripts, seasonal health-check pushes and routing changes all happen inside that loop, so the agent stays sharper than on launch day.