AI & developer infrastructure

AI assistant for ERM workflows

Key achievements

AI assistantEnterprise risk managementReal-time AI streamingSmart form autocomplete
featuring_image

"I've been very impressed at their openness to innovate, their openness to collaborate. And not just be an organisation that's there to do what they're told, but an organisation that's there to make our organisation much more technologically stronger."

Matt Hyne, CTO at Protecht

Client

company_logo

Protecht is a leading enterprise risk management software and advisory company, headquartered in Sydney, Australia, with operations across the US, UK, and APAC. Founded over 25 years ago by risk management experts, Protecht serves 400+ organizations - including governments, regulators, and central banks - across banking, financial services, insurance, fintech, manufacturing, and beyond. With 200,000+ users on the platform and a 98%+ customer retention rate, Protecht is one of the most trusted names in GRC globally. Hotovo has been a key development partner for over 15 years. Together, we built Cognita, Protecht’s AI assistant for enterprise risk management, now available to 400+ organizations.

AI assistant for enterprise risk management blog Cognita Protecht

Case study

The need

Protecht was developing an AI-powered chatbot to extend capacity in a market where AI-driven assistance is becoming standard.

In enterprise risk management, incomplete or inaccurate data does not only slow teams down, it can also create compliance blind spots that expose organizations to regulatory penalties and undetected threats. Protecht was focused on developing an AI assistant that could guide users in real time, reduce form errors, and support accurate data entry.

The solution also needed to improve usability while strengthening Protecht’s position as an AI-enabled GRC platform.

Core issue

  1. The development team in Košice led the React frontend, collaborating across multiple timezones.
  2. The chatbot also had to integrate into an existing large-scale enterprise application in active development for 20 years, with 15+ modules and 400+ customers, without disrupting ongoing development.
  3. The solution was delivered on time and launched without any integration failures despite parallel development across two continents.

Our solution

Hotovo took full ownership of the AI assistant frontend, with additional contributions to backend development and QA delivering a production-ready solution on time.

Key technical capabilities delivered:

  1. Real-time streaming AI responses — answers begin appearing immediately as they are generated, with the ability to interrupt generation
  2. Smooth streaming text experience achieved through adaptive rendering that preserves word boundaries and readability during generation
  3. Scalable conversation history handling using virtualized message lists to maintain UI performance even with large chat histories
  4. Context-aware AI suggestions system integrated directly with 10+ form fields for intelligent field-value autocomplete and contextual navigation
  5. Multi-format AI interactions supporting plain responses, contextual suggestions, knowledge base answers, form assistance, and save/submit confirmations
  6. Rich text AI responses with support for structured lists, headings, and other formatted content for improved readability
  7. Per-module enablement controls to activate or deactivate the chatbot contextually
  8. Error boundaries isolating chatbot failures from the main application, ensuring chatbot issues never impact core risk management workflows that are critical for enterprise reliability and compliance.
  9. Extensive 90%+ test coverage across the chatbot codebase to ensure reliability and maintainability
  10. On the backend side, built the initial proof-of-concept AI service architecture with Spring AI integration, contributed to register schema generation for the LLM model, implemented supporting UI changes in the existing application layer, and improved error handling
  11. QA team was involved from the early stages, building robust test automation coverage across E2E functionality, quality of AI responses, and LLM-specific scenarios

Key results

  1. Cognita - Protecht's flagship AI product, now available to 400+ organizations and central to their GRC market positioning as an AI-enabled ERM platform
  2. Full audit trail and explainability built in - every AI-assisted field is traceable, meeting compliance obligations with regulators and central bank clients
  3. Faster task completion for end users working with complex forms and risk management workflows
  4. Reusable, well-tested codebase as a foundation for expanding AI across the platform and supporting Protecht’s product roadmap
  5. Accelerated delivery through AI-assisted development across the entire team
  6. Delivered on time and showcased at the Gartner Enterprise Risk, Audit & Compliance Conference in the USA, attended by 1900 participants.

Tech stack

  1. Frontend: React, TypeScript, Redux Toolkit with RTK Query, Material UI, Jest, React Testing Library
  2. Backend: Java, Spring Boot, Spring AI, AWS Bedrock, REST
  3. QA: Robot Framework, Playwright, ReadyAPI, custom tools (made with NodeJS, NextJS)
  4. AI IDE: VS Code + Roo Code (LLM Provider: Requesty), IntelliJ Idea (Cline AI Agent)

Team size

  1. 4 Front-End Developers (including AI UI/UX integration specialists)
  2. 1 Back-End Developer (AI service architecture & LLM integration)
  3. 2 QA Engineers (including LLM-specific testing & AI response quality evaluation)
  4. 1 DevOps Engineer
  5. 1 Business Analyst
  6. AI-assisted development across the entire team using Roo Code and Cline AI Agent

Explore other projects

AiderDesk: AI orchestration platform

Software engineers

AiderDesk: AI orchestration platform

View case study
Multi-tenant hotel booking software

hivr.ai

Multi-tenant hotel booking software

View case study
From audit to platform takeover

HCS Safety

From audit to platform takeover

View case study
AI assistant for faster energy insights

Energy intelligence provider

AI assistant for faster energy insights

View case study
AI copilot for insurance underwriting

g-Xperts

AI copilot for insurance underwriting

View case study
API platform development

PolyAPI

API platform development

View case study
ERM migration powered by AI

Protecht

ERM migration powered by AI

View case study
Kubernetes OperatorHub rebuild

Red Hat

Kubernetes OperatorHub rebuild

View case study
Fintech payment modernization

ACE Solutions

Fintech payment modernization

View case study
Wastewater treatement systems

WTR Global

Wastewater treatement systems

View case study
Smart city civic engagement platform

Adaptie

Smart city civic engagement platform

View case study
Risk analytics for motor fleets

g-Xperts

Risk analytics for motor fleets

View case study
Braille to text OCR desktop tool

DotSight

Braille to text OCR desktop tool

View case study
MuleSoft connector development

MuleSoft

MuleSoft connector development

View case study
Jira reporting app built for acquisition

Old Street Solutions

Jira reporting app built for acquisition

View case study
BNPL platform development

credi2

BNPL platform development

View case study
Oracle Integration Cloud recipes

Oracle

Oracle Integration Cloud recipes

View case study
Enterprise risk management platform

Protecht

Enterprise risk management platform

View case study
Audio software modernization

Audinate

Audio software modernization

View case study
Seed management with modern digital tools

SeedBin

Seed management with modern digital tools

View case study
Braille translation desktop app

Braillee

Braille translation desktop app

View case study
Competition management software for climbing

Verti

Competition management software for climbing

View case study
Mobile app redesign for marketing platform

Seismic

Mobile app redesign for marketing platform

View case study
Call analytics platform and Wallboard app

Akixi

Call analytics platform and Wallboard app

View case study
Mobility and insurance app development

Mobly

Mobility and insurance app development

View case study
Contact us

Let's talk