Skip to content
XSIS
Client AreaRequest a Proposal
An engineer walks a data-centre aisle between server racks

Client Stories

A Financial Institution Cut Its AI Running Costs by 52% With Private Models

Production AI that the security team approved and the finance team welcomed, with every record of client data kept in its own environment.

Book a Free SessionStart With Discovery and Design

At a Glance

  1. Client

    A regulated European and MENA financial services institution.

  2. Team

    1 principal AI and data architect, 2 AI and agent engineers and 1 cloud and post-quantum security engineer

  3. Duration

    10 weeks

The Challenge

The client wanted to automate complex bilingual (English and Arabic) KYC document extraction, compliance auditing and internal knowledge retrieval. Strict data residency laws, the MENA personal data protection laws (PDPL), the EU AI Act and DORA, prohibited sending raw customer personal data to public US consumer LLM APIs.

Its first cloud AI prototype also suffered from runaway token inference costs and the risk of hallucination.

What We Built and Connected

  1. Private Inference With Zero Data Egress

    A private inference cluster for large and small language models inside a private regional cloud VPC, with permission-aware GraphRAG that enforces role-based access to documents.

  2. Supervised MCP Agents

    Autonomous agents on the Model Context Protocol (MCP), supervised by people on the loop, that extract, cross-check and post KYC, trade-finance and onboarding documents directly into core systems (intelligent document processing, IDP 2.0).

  3. A Token FinOps Gateway

    Semantic caching and dynamic model routing that send 75% of routine tasks to quantised small language models and keep frontier models for complex reasoning.

Systems and Stack

AI and machine learning
  • Mistral

Measured Results

lower monthly AI token and GPU inference spend, through semantic caching and small-model routing
52%
faster KYC and document onboarding, with deterministic citation links for human compliance officers
78%
and zero external leakage of personal data, passing internal CISO and regulatory risk audits on the first review
100% data residency

XSIS gave us production-grade private AI that our CISO approved and our CFO applauded, cutting our inference bill in half while keeping every byte of client data inside our jurisdiction.

Chief Information and AI Officer

Start With a Conversation, Not a Contract.

Tell us what you need to build, connect or secure. An architect goes through it with you, then recommends where to start.

Book a Free SessionStart With Discovery and Design

What Happens Next

  1. Agreeing a Time

    Our team emails you to agree a time for the session.

  2. Pre-Consulting Session

    A free 30-minute online pre-consulting session: we go through your goals, systems and constraints.

  3. Readiness Review

    In a free 48-hour Readiness Review, a Principal Architect checks your project against What we need before we start and recommends the track that fits.

  4. Choosing the Track

    Scope-ready projects receive a binding proposal within 3 to 5 business days. Concept-stage projects start with Discovery and Design. A live system that is failing, undocumented or needs integration starts with the Live System Review of 1 to 2 weeks. Discovery and Design and the Live System Review each have a fixed fee, quoted in the proposal.