Agentic AI

One agentic AI platform. Three products built on it.

LLM-powered agents, Vision AI, Document AI, generative evaluation and orchestrated automation — the shared engine behind Eklavvya, DocuExprt and ePravesh, running multi-cloud on Google Cloud and Microsoft Azure.

Book a Demo

How it works

Four capabilities, one engine

Every product draws on the same models. What we learn proctoring an exam improves how we read a marksheet.

Vision AI

Computer vision that verifies candidate identity, watches for exam-hall malpractice and reads handwritten answer sheets.

A proctor reviewing live candidate feeds with an identity check overlaid on one of them

Trained on

Live proctoring sessions and scanned answer scripts from Eklavvya exam deployments — not stock footage.

Used by

Eklavvya

Outputs

Real-time face detection and identity verification
Object and behavior flagging — phones, tab-switching, unauthorized apps
Handwriting OCR that converts answer scripts to searchable digital text

Document AI

Extraction and verification models that read and validate government IDs and academic documents.

Trained on

Government-issued IDs, marksheets, certificates and admission documents processed through DocuExprt.

Used by

DocuExprt

Outputs

OCR and field extraction from PDFs, images and scans
Government database checks — Aadhaar, PAN, DigiLocker
Tamper and signature detection across 20+ document types

Generative Evaluation

Models that assess free-form work and generate the instruments used to test it.

Trained on

Manually evaluated answer sheets — evaluators grade the first 20–25% of a batch, and the model learns the marking pattern before grading the rest.

Used by

Eklavvya

Outputs

Descriptive answer scoring with explained feedback
Question paper generation from a syllabus, tagged to Bloom’s Taxonomy
AI-conducted interviews and adaptive case-study assessments

Agentic Workflows

The layer that connects the platform to the systems an institution already runs — as an API, a no-code automation, or an AI agent.

Trained on

Built on documented REST endpoints, webhooks and Model Context Protocol servers shared across all three products.

Used by

Eklavvya and DocuExprt

Outputs

Documented API endpoints with webhooks for real-time status
n8n and Make workflow connectors
Model Context Protocol servers so AI assistants can query the platform directly

The agentic stack

LLMs, orchestration and automation — how the agents actually run

Large Language Models

Frontier LLMs — served through Vertex AI and Azure AI services — power descriptive answer evaluation, question paper generation, AI interviews and counseling agents. The platform is model-agnostic by design: the right model per task, swapped without rewiring the product.

AI Orchestration

Agents do not run alone. Self-hosted n8n engines, MCP servers and documented REST APIs orchestrate multi-step processes — retrieval, evaluation, verification, notification — across all three products and the systems an institution already operates.

Process Automation

The workflow around the AI is automated end to end: answer-sheet ingestion, document pipelines, admission rounds, result publication and follow-ups run as scheduled, monitored automations — humans review the exceptions instead of executing every step.

Applied AI Technology

Computer vision, OCR and generative evaluation models trained on the platform’s own production data — proctoring sessions, answer scripts and verified documents — not stock datasets, so accuracy is measured against real institutional workloads.

A graphical competency analysis breaking results down by subject with high, medium and low score bands

Reporting

The same reporting layer, whichever product produced the data

Scores, competencies and throughput come out of one analytics engine, so an exam result, a verified document and an admission round are all measured the same way and can be read side by side.

Competency and topic-level breakdowns
Cohort, centre and round comparisons
Exports and API access to every figure

Infrastructure and integrations

Runs on what you already trust

Splashgain is a partner of both Google Cloud and Microsoft Azure. Google Kubernetes Engine already carries exams at national scale, agent and automation workloads run on DigitalOcean and n8n, and the platform meets your stack through documented APIs rather than a migration.

Multi-cloud by design

Google Cloud — partner
GKE runs up to 50,000 concurrent exams at 100% uptime; Vertex AI and Vision AI extend evaluation and proctoring
Microsoft Azure — partner
Azure compute and AI services running alongside Google Cloud
DigitalOcean
Containerized AI agents and automation services
n8n workflow engines
Self-hosted automation orchestrating agent workloads behind every product
Multi-provider S3 storage
Documents and recordings distributed across multiple S3-compatible providers to scale
BigQuery
Rolling out as the assessment analytics warehouse

Plugs into what you already run

REST API
Documented endpoints with webhooks
n8n
Self-hosted workflow automation
Make
No-code system-to-system automation
MCP
Model Context Protocol servers for AI assistants

Security

CERT-IN certified, on infrastructure you can name

The platform runs multi-cloud on Google Cloud and Microsoft Azure with a MeitY-empanelled security audit behind it. Data residency, encryption and retention are configured per customer rather than assumed.