Plain definitions for the terms on this site

Ayushman Bharat Digital Mission — India’s national digital health infrastructure, including the Health Information Exchange and the ABHA health ID.

ABDM defines the federated architecture for India’s health data, including a FHIR-based Health Information Exchange (HIE), the ABHA (Ayushman Bharat Health Account) ID, and the Healthcare Professionals Registry. Vihaya’s Context Mesh is designed to ingest structured ABDM data via FHIR R4. The ABDM HIE adapter would be built into engagement SOWs for ABDM-empanelled hospitals and insurers; it is not pre-shipped.

Related: Prior Authorization, Healthcare AI

AI systems where an LLM plans actions, calls tools, observes results, and iterates — rather than producing a single one-shot answer.

An agentic system gives the LLM a loop: read input → decide what to do → call a tool (search, database query, API request) → read the result → decide next step → eventually return a final answer. The loop is what separates agents from chatbots. Vihaya is an agentic platform because every solution it is designed to build runs an LLM through a multi-step pipeline of retrieval, reasoning, decisioning, and write-back.

Related: AI Decisioning, Tool Use

Production AI pattern where the model’s output is a structured decision (approve / deny / escalate) with attached rationale and citations, not free-form text.

Decisioning is the audit-friendly cousin of generative AI. Where a chatbot returns prose, a decisioning agent returns a typed JSON object: outcome, rationale, confidence score, citation IDs pointing to the policy text it grounded on. Every Vihaya solution is designed to produce one decision record per request; the record is immutable and links to its citations and to the audit-trail events that produced it.

Related: Confidence Floor, Audit Trail, Citations

Append-only log of every action the system takes: who did what, to which resource, with what outcome, with what metadata. Reconstructable from cold storage.

In Vihaya the audit trail is designed as a primitive, not a feature. Every step of every agent run is designed to write one immutable record to an append-only log. The trail is self-mapped to control frameworks (SOC 2 CC4.1 / CC7.2; an auditor’s formal mapping is on the roadmap) so audit-evidence collection becomes a side effect of normal operation rather than a quarterly fire drill.

Related: SOC 2, Compliance

Indian Computer Emergency Response Team — the national CERT under MeitY. Requires reporting of cyber incidents within six hours of detection.

CERT-In’s 2022 directions require any organisation processing data in India to report specified cyber incidents within six hours of noticing them. Vihaya’s audit primitive is designed to surface incident-detection events into the customer’s CERT-In reporting workflow so the six-hour window is operationally achievable, not theoretical.

Related: DPDP Act 2023, Audit Trail

Pointers from a decision back to the specific policy chunks the agent grounded its reasoning on.

Every Vihaya decision carries pointers to the exact policy passages the agent grounded on. The reviewer UI dereferences these to show the verbatim source text the agent based its decision on. Citations are how Vihaya makes LLM output reviewable: not ‘trust the model,’ but ‘here is what it read.’

Related: AI Decisioning, Audit Trail

A configured threshold below which a decision is force-escalated to a human reviewer, regardless of what the model said.

If the agent says ‘approve’ with confidence 0.62 but the floor is 0.75, the case routes to a human anyway. This makes confidence floor a safety primitive, not a UI flag. It’s the architectural way Vihaya guarantees human-in-the-loop coverage for low-certainty cases — without depending on the LLM to volunteer its uncertainty.

Related: Escalation Queue, Human-in-the-Loop

Vihaya’s hybrid-retrieval data layer: typed entities, relations, knowledge chunks, and episodic memory in one tenant-local store.

The Context Mesh is the substrate every Vihaya agent is designed to read from and write to. It combines vector similarity for semantic search, full-text search for lexical lookup, and a typed entity-relation graph for structured traversal. It is also designed to store episodic memory — past decisions for the same subject — so future agent runs have context. Implementation details stay between Vihaya and the design-partner customer.

Related: Hybrid Retrieval, Ontology, Episodic Memory

India’s federal personal-data-protection law. Establishes the data-fiduciary role, notice + consent, purpose limitation, and breach-notification obligations.

The Digital Personal Data Protection Act 2023 is India’s first comprehensive personal-data law. It applies to any entity processing personal data in connection with goods or services offered in India. Vihaya’s append-only audit trail, configurable PII redaction, and consent + notice integration points are designed to support data-fiduciary obligations under the Act — DPDP compliance is the data fiduciary’s organisational determination, not Vihaya’s certification. Penalties under the Act may extend to ₹250 crore, which is why audit-grade decisioning matters.

Related: Audit Trail, CERT-In

An agent run record that survives process crashes, restarts, and replays. Identity, state, and progress are persisted.

Long-running enterprise workflows can’t lose state when the host process dies. A durable agent run is designed as a record that captures who the agent is, what input it received, where it is in its plan, and what tools it has called. If the process restarts, the run is designed to resume from the last checkpoint — the call is idempotent on the decision ID.

Related: Idempotency, Agentic AI

The ordered list of cases the agent declined to decide automatically and routed to a human reviewer.

Cases land on the queue when (a) the agent’s own verdict was ‘escalate’ or (b) the confidence floor forced escalation. Every queue item is designed to carry the agent’s recommendation, rationale, and citations — so the reviewer is not starting from scratch. The queue surfaces as a first-class API endpoint and as the customer-facing reviewer UI.

Related: Confidence Floor, Human-in-the-Loop

A CI-blocking test suite that runs a golden dataset through the live model on every deploy. Drift below threshold exits non-zero; deploy is blocked.

Evals are the unit tests for AI systems. The eval gate runs a hand-curated scenario set through the production model, scores outcome match + citation grounding + confidence on approves, and refuses to ship if the average drops. The golden dataset is built collaboratively with the customer’s SME (e.g. medical director) and reviewed when policies change. Scenario count is sized per pilot.

Related: Golden Dataset, CI/CD

The successor to SEO: optimizing content so it surfaces inside LLM-powered answer engines (Google AI Overviews, Perplexity, ChatGPT browsing, Claude).

Where SEO targeted SERP rankings, GEO targets the answers LLMs synthesize from many sources. Winning GEO requires: clear factual statements, defined-term content, FAQ schemas, citation-friendly stats, llms.txt / llms-full.txt files, and machine-readable structure (JSON-LD). This page is itself a GEO play — answer engines preferentially cite glossary entries because they have a clear term-definition shape.

Related: AEO, SEO

A workflow where AI handles routine decisions automatically but routes uncertain or high-risk cases to a human.

HITL is the only viable production pattern for high-stakes decisioning. Vihaya is designed to bake HITL in three ways: (1) confidence-floor escalation forces human review below threshold, (2) policy-spec escalation rules allow per-class always-escalate cases, (3) the model itself can return ‘escalate’ as an explicit outcome. The human reviewer sees the agent’s full recommendation chain.

Related: Confidence Floor, Escalation Queue

Retrieval that combines vector similarity, full-text search, and graph traversal in one query — not just embedding cosine match.

Pure vector RAG misses on exact-term matches (drug names, policy codes). Pure lexical search misses on paraphrase. Hybrid retrieval runs both and merges the results, then optionally traverses typed relations from each hit to pick up related entities. This is what makes citations actually useful — the passages retrieved are the passages a human reviewer would have pulled.

Related: Context Mesh, RAG

Insurance Regulatory and Development Authority of India. Issues the cyber-security and IT-outsourcing guidelines that bind Indian insurers.

IRDAI’s cyber-security and IT-outsourcing guidelines bind India’s life and general insurers. The guidelines require board-level oversight of outsourced IT, defined audit rights, and incident reporting. Vihaya’s pilot SOW template for Indian insurers includes the IRDAI artefacts — board-approved outsourcing policy mapping, audit-trail evidence packaging, and the exit-management plan that mirrors RBI’s outsourcing direction structure. No insurer engagement has been delivered yet.

Related: DPDP Act 2023, Audit Trail

A typed schema declaring which entity kinds and relation kinds the system understands — domain, range, cardinality, properties.

An ontology lets a tenant declare ‘patient’, ‘policy’, ‘provider’ as entity kinds, and ‘covers’, ‘authored-by’, ‘requested-for’ as relation kinds with domain/range constraints. Writes to the system’s knowledge store are validated against the ontology before they land — which is what stops a misclassified entity from quietly poisoning the agent’s view of the world months down the line.

Related: Context Mesh, Schema Validation

The healthcare payor process where a clinician requests insurance approval for a procedure or drug before delivery.

Prior auth is the highest-volume, most expensive paperwork in healthcare payor operations — payors spend substantially on utilisation management to review PA requests against clinical guidelines (Milliman, InterQual, internal policy bulletins). Vihaya’s first solution-in-development is PA decisioning end-to-end, designed to keep every decision audited, cited, and escalation-protected. Pre-revenue; no paid pilot has completed.

Related: Utilization Management, Healthcare AI

The Reserve Bank of India’s framework governing how banks and NBFCs may outsource IT services — including data localisation, audit rights, and exit-management requirements.

Formally the ‘Master Direction on Outsourcing of Information Technology Services, 2023’, this RBI direction requires regulated entities to retain examiner audit rights, maintain BCP/DR plans, and ensure data does not leave India without explicit approval. Vihaya is designed to deploy inside the bank’s VPC (typically AWS Mumbai or Azure South India) so the framework’s data-localisation expectations are met by the deployment model, not by paperwork. No bank has deployed Vihaya yet.

Related: DPDP Act 2023, BFSI

AICPA framework for evaluating service-organization controls across security, availability, processing integrity, confidentiality, and privacy.

Vihaya’s compliance package is designed to seed the SOC 2 baseline. Audit-trail events are designed to link as evidence under CC4.1 (monitoring) and CC7.2 (incident detection). A Type II audit attests that controls operated effectively over a period — Vihaya is pre-Type-II as of May 2026 with auditor engagement on the roadmap. The mapping is currently self-asserted, not auditor-reviewed.

Related: Audit Trail, Compliance

Healthcare payor function that reviews requests for medical services against clinical and policy criteria to decide coverage.

UM teams operate the prior-authorization, concurrent review, and retrospective review functions. They are typically staffed with nurse reviewers reading PDFs and EHR exports. Vihaya’s PA solution is designed to operate within UM, automating the front end of nurse-reviewer screening with an audit chain built for regulator reconstructability.

Related: Prior Authorization, Healthcare AI