Frontend
Android (Java/Kotlin)
About Cleo
At a 15–20 person company, HR should be simple. But "simple" doesn't mean frictionless. TechCare's People & Culture team was spending a significant chunk of every workweek answering the same five questions on Slack: What's my leave balance? Has my request been approved? Did my check-in go through? The data existed. The problem was access. Cleo is TechCare's in-house AI HR agent built to solve exactly that — an always-on, RAG-powered assistant that handles routine HR operations end to end, so the team can focus on people instead of process.
Performance Highlights
10+
Hours Saved Per Week
<2hr
Leave Approval Time (was ~1 full day)
0
Leave Balance Discrepancies
Solutions & Impact
At a 15–20 person company, HR should be simple. But "simple" doesn't mean frictionless. At TechCare, the People & Culture team was spending a significant chunk of every workweek answering the same five questions on Slack: What's my leave balance? Has my request been approved? Did my check-in go through?
The answers were always in the system. The problem was access, or rather the lack of it. Employees had no way to check their own data without messaging HR directly. Attendance was tracked manually, and leave approvals occasionally fell through the cracks when a manager had competing priorities.
The result was an estimated 8–12 hours of HR admin per week that required no human judgment, just time.
"Most Slack messages to HR were the same five questions, and the answers were always in the system. The data existed. The problem was access."
— TechCare P&C Team
Why Off-the-Shelf Tools Weren't the Answer
TechCare had tried existing HR platforms, including Zoho. The integrations were limited, the workflows didn't match how a lean hybrid-remote team actually operated, and the team kept falling back on spreadsheets and direct messages to fill the gaps. Off-the-shelf solutions also came with enterprise-scale complexity that a team of 15–20 people simply didn't need.
The decision to build in-house was not about cost alone. It was about control — over the logic, the tone, the data, and the ability to evolve the tool as the company grows.
Meet Cleo
Cleo is TechCare's in-house AI HR agent, deployed on Slack and configurable for Telegram or any other preferred messaging stack. It was built by the TechCare team using a custom pipeline on top of FastAPI and LangChain, with a model-agnostic inference engine that runs across multiple LLM providers with a built-in fallback system.
At its core, Cleo uses a Retrieval-Augmented Generation (RAG) architecture, meaning every answer it gives is grounded in TechCare's own HR data, policy documents, and real-time database connections — not hallucinated from general knowledge. When Cleo cannot answer with sufficient confidence, a threshold mechanism triggers human-in-the-loop (HITL) escalation, automatically pulling in the HR admin.
From idea to beta-tested working prototype: less than one week.
What Cleo Actually Does
Leave Management
Cleo handles leave requests end to end. In guided mode, it captures the request from the employee, notifies the reporting manager instantly, and updates the employee as soon as a decision is made.
In autopilot mode, it goes a step further. Cleo applies the HR rule book on its own, checking leave availability and policy compliance before approving or declining the request.
What changed most is the follow-through. If a manager does not respond within two business days, Cleo escalates automatically. Before Cleo, there was no system to catch that delay, and requests often stayed unresolved until someone manually followed up.
Attendance Tracking
Daily attendance, which was previously logged manually, now syncs directly with the HR dashboard in real time. There is no manual entry step, and therefore no risk of miscounts — especially around half-days, which had been a recurring source of spreadsheet errors.
Employee Self-Service
Employees can ask Cleo anything HR related at any time, including leave balances, policy questions, check-in confirmations, and onboarding guidance. New hires no longer need to ping HR for basic orientation questions in their first week. Cleo handles these queries and flags anything that genuinely requires a human.
Admin Dashboard
HR administrators configure Cleo's behaviour, rules, and escalation logic through a dedicated dashboard. Full employee profiles can be uploaded into the system, and Cleo generates context-aware responses based on the HR rule book from day one. Onboarding introductions and shoutouts can also be pushed directly to Slack or any connected channel from the same dashboard.
The Technical Architecture
Layer
Approach
Framework
Framework
TechCare’s Journey With The Project
2016 — Ideation, Planning & Architecture
That client approached TechCare with a clear goal: expand beyond the web and reach the growing base of smartphone users across Bangladesh. The smartphone boom was creating a new class of mobile-first shoppers, and they needed a reliable tech partner to bring their buying experience to Android.
TechCare focused on building a complete mobile buying experience before adding advanced features. Key architectural decisions were made early:
MVVM pattern selected for modularity and maintainability
Agile, milestone-based development process established
User journey mapped as the foundation for data flow design
Performance benchmarking set as a core KPI given Android device fragmentation
2016–2017 — Development & MVP
With feature priorities set around the most impactful user actions first, TechCare built and iterated:
Complete end-to-end purchase flow on mobile
Centralized login and authentication system
Integration with the project's evolving API platform
Crashlytics (Fabric) integrated for real-time app health monitoring
2017 — Beta Testing & Launch
Before full release, TechCare ran A/B testing across a selected group of beta users. The existing feature roadmap made it straightforward to track completed, pending, and rework items. Key KPIs monitored through launch included:
API response logging
Latency benchmarking
Android build performance and stability
Security benchmarking and code obfuscation
2017 — Post-Launch Optimization
This approach proved valuable after launch. As client’s product team requested feature updates and changes, TechCare was able to deliver them quickly without affecting the overall system. This continued to add value beyond the initial project.
Results & Impact
5x user growth
Significant user base expansion following the mobile app launch.
2x customer engagement
Doubled interaction rates across key touchpoints and user journeys.
Mobile-first reach
Expanded access to mobile-first users and new market segments.
Tech Stack, How We Built It
TOOLS
Android Studio
LIBRARIEs
Retrofit, Glide, Volley,
Dagger 2
NOTIFICATIONS
OneSignal, Firebase GCM
ANALYTICS
Custom Analytics Framework, Fabric (Crashlytics)
Systems Delivered
USER-FACING MOBILE APP
Full book browsing and purchase experience
LOGIN SYSTEM
Centralized and frictionless authentication
NOTIFICATION SYSTEM
Order updates and engagement notifications
MODULAR ARCHITECTURE
Flexible system for continuous feature updates
Data-Driven Development
TechCare followed a structured and data-driven approach:
API response logging
Latency benchmarking
Integration with Rokomari's evolving API platform
Security benchmarking and code obfuscation
User journey data guided feature prioritization, ensuring
that the most important actions were optimized first.
Challenges We Solved Differently
Unlike typical implementations, TechCare focused on:
Building for low-end device performance
Maintaining cross-platform UX consistency
Handling constantly changing APIs
Creating a future-ready modular system
Other Case Studies
Mental Health Care
Scaling Access & Value
Our healthcare platform project raised $550K, sustained success for 5+ years, and expanded reach with powerful mobile and web experiences.
View Full Case Study
Education
Transforming Learning Platforms
Our dedicated tech teams delivered innovative tech solutions, optimizing operations and driving impressive cost savings and growth.
View Full Case Study
Artificial Intelligence / Healthcare
AI-Driven Doctor Recommendation System
Created an AI-powered matching engine using vector embeddings to connect patients with the most relevant healthcare specialists in seconds.
View Full Case Study
Artificial Intelligence / Productivity
AI K-Base Assistant for Multi-Stakeholder Teams
Built a Claude-powered chatbot that delivers real-time, personalized answers across teams, automating knowledge sharing and documentation.
View Full Case Study
Home Maintenance
Turning Yardly’s Website Into a Scalable Growth Engine
Yardly is a Canada-based yard care service provider offering year-round solutions including lawn maintenance, seasonal clean-ups, and snow removal across Edmonton and Calgary.
View Full Case Study