Skip to main content
Challenge

Build an Offline Multilingual Public Health Scheme Navigator for Asha Workers

Evaluate maternal and infant health milestones against national health mission support schemes on offline mobile devices. Synthesize actionable visit checklists and mock benefit explanations in local languages without external cloud connectivity.

Workflow AutomationHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Evaluate maternal and infant health milestones against national health mission support schemes on offline mobile devices. Synthesize actionable visit checklists and mock benefit explanations in local languages without external cloud connectivity.

Community health volunteer coordinator

Store prenatal visit records and immunisation dates locally in an offline SQLite mobile database.

Cross-reference mother and child health milestones against mock scheme eligibility rules and immunization schedules.

Identify pending nutritional cash assistance entitlements based on registered institutional delivery dates.

Generate multilingual household visit action sheets and document reminders in regional scripts.

Offline-ready mobile web view featuring high-contrast text, vernacular toggle switches, and visit planners.

Assemble synthetic maternal healthcare milestone tables and mock scheme rules in local SQLite databases. Starter examples below are synthetic. They are not downloaded records.

Bhashini documentation Adopts Bhashini language standardization codes and multilingual template structuring for local dialect scripts.

ollama, sqlite3, pydantic. Enables on-device local natural language checklist generation completely decoupled from network connections. Local small language model (3B to 7B parameters) running locally on edge hardware via Ollama.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Evaluates milestone completion dates against scheme qualification windows without network access.

Formats vernacular visit reminders with correct ISO-639 language tag handling.

Operates strictly on synthetic local records without connecting to central health registries.

```json [ { "input": { "record_id": "MCH-501", "gestational_weeks": 28, "anc_checkups_done": 3, "institutional_delivery_planned": true, "language": "hi" }, "expected_output": { "scheme_qualifications": [ "Matritva_Vandana_Installment_1", "Janani_Suraksha_Registered" ], "pending_milestones": [ "4th ANC Checkup", "Tetanus Booster" ], "advisory_cash_support_inr": 3000, "visit_note_hi": "कृपया चौथे प्रसव पूर्व जांच के लिए स्वास्थ्य केंद्र जाएं।" } }, { "input": { "record_id": "MCH-502", "gestational_weeks": 38, "anc_checkups_done": 1, "institutional_delivery_planned": false, "language": "hi" }, "expected_output": { "scheme_qualifications": [ "Pending_ANC_Completion" ], "pending_milestones": [ "Institutional Delivery Counseling", "Emergency Contact Registration" ], "advisory_cash_support_inr": 0, "visit_note_hi": "संस्थागत प्रसव के लाभ और सुरक्षा के बारे में परामर्श आवश्यक है।" } } ] ```

Provides advisory guidance only; strictly avoids real clinical diagnoses or actual disbursements of public welfare funds. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Provides advisory guidance only; strictly avoids real clinical diagnoses or actual disbursements of public welfare funds. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Evaluates milestone completion dates against scheme qualification windows without network access. Formats vernacular visit reminders with correct ISO-639 language tag handling. Operates strictly on synthetic local records without connecting to central health registries.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Store prenatal visit records and immunisation dates locally in an offline SQLite mobile database. Cross-reference mother and child health milestones against mock scheme eligibility rules and immunization schedules. Identify pending nutritional cash assistance entitlements based on registered institutional delivery dates. Generate multilingual household visit action sheets and document reminders in regional scripts.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Evaluates milestone completion dates against scheme qualification windows without network access. Formats vernacular visit reminders with correct ISO-639 language tag handling. Operates strictly on synthetic local records without connecting to central health registries.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

Offline-ready mobile web view featuring high-contrast text, vernacular toggle switches, and visit planners.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Provides advisory guidance only; strictly avoids real clinical diagnoses or actual disbursements of public welfare funds.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Store prenatal visit records and immunisation dates locally in an offline SQLite mobile database.

  • Cross-reference mother and child health milestones against mock scheme eligibility rules and immunization schedules.

  • Identify pending nutritional cash assistance entitlements based on registered institutional delivery dates.

  • Generate multilingual household visit action sheets and document reminders in regional scripts.

Resources and assets

Reference links and supporting material

Dataset notes

Assemble synthetic maternal healthcare milestone tables and mock scheme rules in local SQLite databases. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Ollama

Local LLM runtime for offline inference.

Evaluated output

No output checks are configured.

Evaluation checks
  • Store prenatal visit records and immunisation dates locally in an offline SQLite mobile database. Cross-ref...
  • Evaluates milestone completion dates against scheme qualification windows without network access. Formats v...
  • Offline-ready mobile web view featuring high-contrast text, vernacular toggle switches, and visit planners.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 1 configured tool

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Policy Serving
  • Ollama · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an Offline Multilingual Public Health Scheme Navigator for Asha Workers