Customer Service Automation
Last Mile Health found that medical and community health advice delivered through Ethiopia's new health-system call centers was not standardized across districts, while community health workers could not realistically memorize hundreds of pages of guidelines, training content, and diagnostic protocols for unusual cases.
Reported impact
The initiative is intended to standardize medical guidance across districts, help community health workers deliver better care, support faster and more appropriate referrals, improve efficiency for call center agents, and reduce unnecessary strain and costs in hospital systems.
Last Mile Health, working with the Ethiopian Ministry of Health and technical partner IDinsight, created HEP Assist to support community health workers through 10 call centers embedded in Ethiopia's health system. The implementation combines HEP Assist with a case management system and a question-answering service trained on Ethiopian Ministry of Health guidelines, training materials, and diagnostic protocols. In the current operating model, frontline workers call center agents when they encounter unusual symptoms or difficult cases. Agents then use the AI to connect symptom lists, surface standardized medical guidance, and determine whether a patient should be referred for specialized or emergency care. Ministry experts guided the design, and the rollout is structured as an agent-mediated pilot first, with longer-term plans for direct access via mobile devices. The source does not name the underlying model, storage platform, or cloud infrastructure.
Community health workers call center agents with symptom descriptions or difficult cases; agents submit those questions to HEP Assist and its question-answering service, which uses Ethiopian Ministry of Health guidelines, training content, and diagnostic protocols to return standardized guidance and referral recommendations, including when to escalate patients to nearby health facilities.
“All of that not only will improve health outcomes but also will lower costs and reduce strain on hospital systems.”
“More than 40,000 workers are responsible for providing health care for anywhere from 2,500 to 3,000 people each.”
“The community health workers call into center agents, who can ask the AI to do things such as connect a list of seemingly random symptoms to come up with an accurate diagnosis or determine whether a patient needs to be referred for specialized or emergency care.”
“The medical and community health advice they were providing was not standardized across the various districts that were providing support. We thought AI could help.”
“The plan is to pilot HEP Assist at all 10 existing call centers. This includes a case management system and a question-answering service trained on comprehensive Ethiopian Ministry of Health guidelines.”
“With IDinsight’s technical support, Last Mile Health created HEP Assist, a health extension program assistant designed to offer real-time medical guidance for Ethiopian health workers.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The Organization JSON-LD lists addressLocality "Boston", addressCountry "US", and numberOfEmployees value 61.
Related
In-house Sample Sep 3, 2026 Grupo Falabella Grupo Falabella needed to turn AI into a cross-functional business capability that improves customer experience, sales conversion, service responsiveness, and logistics efficiency across its five business units rather… US$265 million to technology in 2026 Banco Falabella app · Falabella.com · cameras In-house Sample Aug 27, 2026 Lenovo Lenovo needed to handle customer support at very large scale across its global device support operation, where routine issues created cost and complexity and human-led resolutions costing $30 to $50 could delay simple… $30 to $50 Lenovo Intelligent Voice Agent · Lenovo Machines Fix Machines Agent · Lenovo Smart Repair Agent In-house Sample Aug 13, 2026 BBVA BBVA needed to improve customer service, streamline risk analysis, boost commercial productivity, and reduce administrative effort across commercial banking processes while giving bankers more personalized, faster… 86 percent of BEI agents in Spain AI Banker · Akira Project · AutoPF 