AI platform combines portfolio analytics, transaction execution and deterministic compliance controls
KFin Technologies Limited (KFintech), a technology-driven financial services platform, has announced enhanced details of ARYA, its next-generation Conversational Intelligence & Investor Servicing Platform. ARYA enables investors to move from queries and portfolio analysis to compliant transaction execution through natural language conversations.
The platform brings scheme discovery, portfolio analytics and transaction execution together through an Ask → Understand → Analyse → Act journey. While additional lump-sum purchases and SIP registration are currently in live testing, redemption, fund switching, STP and SWP are planned for future releases.
ARYA uses deterministic software for compliance checks, including OTP-based identity verification, PAN masking and eligibility gates, while transactions execute directly on KFintech-serviced AMCs. Portfolio calculations such as XIRR, asset allocation and rebalancing are also computed programmatically.
Nazish Hussain, Chief Technology Officer, KFintech, said, “The future of financial AI is moving from answering questions to executing secure, auditable actions. By building a deterministic compliance engine underneath our Small Language Models in ARYA, KFintech allows investors to evaluate portfolios and execute transactions in plain language knowing that every rule is checked and every transaction is securely recorded.”
Proof-of-concept testing completed in July 2026 showed fact accuracy improving from 41% to approximately 90%, sub-second retrieval latency and a 100% refusal rate for out-of-scope questions in the evaluation set.
ARYA is scheduled to launch as an invite-only standalone app in September 2026, followed by distributor access through IRIS in October and investor access through KFintech’s investor portal in November. Future plans include WhatsApp and voice interaction, multilingual support, non-commercial transactions, and adapters for NPS and wealth servicing.

