Reperks
AI Agent Perk Eliminates 98% of Landlord Billing Work
Industry
Real Estate / Property TechnologyProject type
AI Agent Development, Document Processing AutomationProject duration
6 weeks MVP + Ongoing DevelopmentTeam size
5 specialists
At a glance
What Perk delivers for landlords:
Time savings
Complete annual billing in 15 minutes instead of 20+ hours (98% reduction).Legal protection
Automatic compliance with German rental law eliminates costly disputes.Zero manual entry
Upload documents in any format—Perk extracts and validates everything.Stress-free accuracy
Triple-validated calculations guarantee mathematical precision.Rapid deployment
Production-ready system delivered in 6-week MVP sprint.
What the client says
"The team has been highly engaged, proactive, responsive, and available to assist, and has participated actively in reviews and retrospectives. The team's collaborative and solution-oriented approach stands out."
Technical Founders
Reperks
About Reperks
Reperks is a German PropTech startup founded by experienced professionals from the real estate and technology sectors, focused on digitizing and automating manual processes that plague the €400+ billion German rental market.
After identifying utility cost billing ("Nebenkostenabrechnung") as one of the most pain-inducing annual tasks for Germany's 3+ million landlords, Reperks developed an initial prototype using conversational AI. However, they quickly discovered that production-grade AI agents require sophisticated orchestration, legal validation, and engineering rigor far beyond basic prompt engineering.
Reperks' vision extends beyond billing to a comprehensive suite of AI-powered tools for rental property management, positioning them to capture significant market share in Germany's digitization-resistant real estate sector.
Founded
Headquarters
Market
Problem space
The Challenge
Market context
German landlords must create legally compliant utility cost billing statements ("Nebenkostenabrechnung") annually for each tenant. This process is notoriously complex, involving multiple legal frameworks (BGB §556-560, HeizKV, CO2KostAufG), precise mathematical allocations based on different distribution keys (area, consumption, persons), and strict formatting requirements. Errors can result in legal disputes, lost revenue, or expensive property manager fees (€50-150 per unit annually).
Current solutions force landlords into rigid, form-based interfaces that don't match their actual workflows, require extensive manual data entry, and fail to provide intelligent guidance through the legal complexities.
Core business problems
The client faced critical technical and business challenges:
AI Reliability Gap
Initial prototype using Gemini 2.5 Pro achieved only 75% accuracy with a 95-page monolithic prompt that was unmaintainable and unpredictableDocument processing complexity
Landlords provide wildly inconsistent documents—handwritten notes, poor-quality scans, property manager summaries, individual invoices—requiring intelligent OCR with confidence scoringLegal compliance risk
Germany's rental law is complex and unforgiving; even small calculation errors or missing legal disclosures can invalidate entire billing statementsDual workflow challenge
System must support both landlords with property management (summary documents) and self-managing landlords (20+ individual invoices)Human-in-the-loop validation
Cannot fully automate due to document quality issues; must seamlessly integrate user confirmation without breaking conversational flow
Strategic constraints
Additional complexity came from:
Tight timeline
Q1 2026 launch target due to annual billing cycle (June-December prime season)Cost control
AI token costs can explode; needed efficient orchestration and caching strategiesRegulatory precision
Zero tolerance for mathematical errors; must implement deterministic calculation validation alongside LLM processingMarket education
Target users (50+ year-old landlords) unfamiliar with conversational AI interfacesScalability requirements
Architecture must support 10,000+ concurrent users during peak season without degraded performance
The Strategic Goal
Give landlords back their time by transforming 20+ hours of annual billing drudgery into a 15-minute conversation with Perk—so they can focus on growing their portfolio while Perk handles legal compliance and mathematical precision automatically.
Our solution
Why HyperSense
The client chose HyperSense after recognizing that production AI agents require deep architectural expertise beyond prompt engineering.
Our differentiators:
- Proven experience architecting agentic workflows, RAG systems, and multi-model orchestration on AWS Bedrock
- Prior work building compliance-focused systems where mathematical precision and audit trails are non-negotiable
- Ability to deliver production-grade systems in 6-week sprints through focused scope management and incremental validation
Our approach:
Discovery & Architecture Design
We began with intensive analysis of the client's 95-page prompt, existing user workflows, and German legal requirements. Rather than simply refactoring the prompt, we designed a proper agentic architecture separating concerns: document processing, conversational orchestration, calculation engines, and legal validation.
Iterative Development with Client Validation
Using AWS Bedrock's flexible model routing, we built Perks as a Claude 4.5 Sonnet-based agent with Extended Thinking capability. We developed a dual-repository structure with Infrastructure as Code (Terraform) for rapid iteration. Reperks participated in weekly demos, providing real-world documents and landlord feedback.
Legal & Mathematical Hardening
Recognizing that LLMs can fail at complex arithmetic, we moved all calculation logic into deterministic code with triple-validation. We integrated German legal knowledge bases (BGB, HeizKV, CO2KostAufG) as structured context, enabling Perks to provide precise legal citation and compliance checking.
What we delivered
Core platform capabilities:
Conversational billing interface
Conversational interface that guides landlords through billing in natural language—no forms, no frustrationIntelligent document processor
Intelligent document processor that reads any format (handwritten notes, scans, PDFs) and extracts data automaticallySmart workflow detection
Smart workflow detection that adapts to each landlord's situation (property manager or self-managed)Built-in legal expert
Built-in legal expert that validates compliance with German rental law at every stepError-proof calculation engine
Error-proof calculation engine that triple-checks every number so landlords never worry about mistakesProfessional PDF generation
Professional PDF generator that produces legally compliant statements tenants can't dispute
Supporting Services:
AI agent architecture
Agentic workflow design with AWS Bedrock orchestration, cost controls, and multi-model routing strategyBackend development
Node.js/Express RESTful API with PostgreSQL for conversation state, user data, and historical billing recordsInfrastructure as Code
Terraform-managed AWS infrastructure with Lambda functions, S3 storage, CloudWatch monitoring, and Cognito authenticationQuality assurance
Real-world document validation with 20+ property portfolios, weekly demos, and iterative refinement based on landlord feedbackDevOps & deployment
Dual-repository structure for rapid iteration, automated deployment pipelines, and comprehensive monitoring for production reliability
Architecture & technology
Our architecture prioritizes reliability, cost-efficiency, and maintainability. We designed for the MVP constraint while enabling seamless evolution toward a multi-agent system as the product matures.
AI/ML
Technologies
AWS Bedrock, Claude 4.5 Sonnet (Extended Thinking)
Purpose
Conversational orchestration, document understanding, legal reasoning. Extended Thinking enables complex multi-step legal analysis.
Document Processing
Technologies
AWS Textract, Bedrock Data Automation
Purpose
OCR with confidence scoring for handwritten and low-quality scans. Textract for structured extraction, Bedrock for intelligent correction.
Backend
Technologies
Node.js, Express.js, PostgreSQL
Purpose
RESTful API with conversation state management, calculation engines, and property context persistence. PostgreSQL for ACID-compliant audit trails.
Frontend
Technologies
React, Axios
Purpose
Conversational UI with document upload, real-time feedback, and data confirmation flows. Mobile-responsive for on-the-go landlord access.
Infrastructure
Technologies
AWS Lambda, S3, CloudWatch, Terraform
Purpose
Serverless for cost-efficiency and auto-scaling during peak season. Terraform for reproducible infrastructure deployments.
Authentication
Technologies
AWS Cognito
Purpose
Multi-tenant authentication with landlord/property manager segmentation for future pricing tiers.
Monitoring
Technologies
CloudWatch, Mattermost
Purpose
Real-time alerting for critical errors, token usage spike detection, and system health monitoring.
Technical Highlights
Agentic orchestration with cost controls
Rather than relying on heavyweight frameworks (LangChain), we built a lightweight orchestration layer that routes conversations through specialized processing nodes based on intent detection. This gives us fine-grained control over token usage and enables request-level caching for repeated legal queries.
Deterministic math + LLM reasoning
All financial calculations run through three independent validation methods (percentage-based, unit-based, reverse-calculation) in hardened code, while the LLM handles conversational guidance and legal explanation. This hybrid approach eliminates mathematical hallucinations while preserving the natural language interface users need.
Document classification & templated extraction
We implemented a two-phase document processing pipeline: first, Claude classifies the document type (invoice, property manager summary, rental contract, meter reading); second, type-specific extraction templates optimize OCR accuracy and validation rules. This dramatically improved extraction reliability for non-standard documents.
Key Features & Capabilities
Upload any document, Perk handles the rest
What landlords get
Simply take photos of invoices, contracts, or statements with your phone—Perks reads everything automatically, even handwritten notes or faded faxes. You review and confirm the extracted data in seconds, then move on.Why this matters
You'll never spend hours retyping invoice data again. Perks eliminates 100% of manual data entry while keeping you in control—you see exactly what was extracted and confirm it's correct before proceeding. This means you save time without sacrificing accuracy or peace of mind.Technical approach
AWS Bedrock Data Automation for initial OCR with confidence scoring, followed by Claude-powered extraction against document-type-specific schemas. Extractions below 98% confidence trigger user confirmation flows with highlighted fields.
Perk adapts to your workflow, not the other way around
What landlords get
Whether you have a property manager or handle everything yourself, Perks automatically detects your situation from the first document you upload and guides you through the exact steps you need—no irrelevant questions, no wasted time.Why this matters
You're not forced into a one-size-fits-all process that doesn't match your reality. Property manager clients get a streamlined 5-minute experience verifying summary documents. Self-managing landlords get intelligent guidance organizing 20+ invoices. Either way, you complete billing faster because Perks understands your unique workflow.Technical approach
Intent classification on initial document upload triggers pathway selection. For property manager pathway, agent validates summary document against legal requirements. For self-managed pathway, agent orchestrates multi-document collection and validates completeness across required categories.
Sleep better with built-in legal protection
What landlords get
Perks acts as your personal legal expert, continuously checking every piece of data against German rental law (BGB, HeizKV, CO2KostAufG). If something's wrong, you'll know immediately—before you send anything to tenants.Why this matters
You avoid costly legal disputes and tenant payment withholding. One missing disclosure or incorrect heating cost split can invalidate your entire billing and tie you up in months of legal headaches. Perks catches these errors automatically, so you can send billing statements with complete confidence that tenants can't challenge them.Technical approach
Legal knowledge bases structured as JSON schemas with rule definitions are loaded into Claude's context using RAG. For each data point, the agent cross-references legal requirements and flags violations. Final validation runs a comprehensive checklist before PDF generation.
Never worry about math mistakes again
What landlords get
Every euro, every allocation, every percentage—calculated three different ways automatically and cross-checked for perfect accuracy. If the numbers don't match down to the cent, Perks won't let you proceed.Why this matters
You'll never lose sleep wondering if you made a calculation error that could cost you thousands in disputes. Mathematical mistakes destroy tenant trust and create legal liability. Perks' triple-validation system guarantees perfect accuracy every time, so you can focus on landlord-tenant relationships instead of spreadsheet formulas.Technical approach
All calculations moved outside the LLM into hardened TypeScript/Node.js functions. Each allocation runs through percentage-based, unit-based, and reverse-validation methods. Results are compared; mismatches trigger error logs and block progression.
Professional billing statements your tenants can't dispute
What landlords get
Two versions of every billing automatically: a quick-scan overview so you can review in 2 minutes, plus a formal, print-ready PDF that meets every German legal requirement—perfectly formatted, completely professional.Why this matters
You save hours on formatting and legal compliance research. The professional PDF includes everything German law requires: objection deadlines, tax-deductible classifications, itemized breakdowns. Your tenants receive bulletproof documentation they can trust, which means fewer disputes and faster payment collection.Technical approach
LaTeX-based PDF generation engine with template injection. Quick overview renders as Markdown tables in-app. Full legal PDF includes property/tenant headers, structured cost tables with allocation key explanations, heating cost distributions, CO2 cost splits, and all legal disclosures.
Implementation journey
Discovery & architecture design (1 week - November 3-8, 2025)
- Deep-dive analysis of 95-page prompt and client's Gemini-based prototype
- Workflow mapping: property manager pathway vs. self-managed pathway
- Legal requirements documentation (BGB, HeizKV, CO2KostAufG)
- Architecture design: agentic orchestration, calculation separation, RAG integration
- Technology selection: AWS Bedrock (Claude 4.5 Sonnet) over client's Gemini approach
- Infrastructure planning: Terraform-based IaC, dual-repo structure (frontend/backend)
Core development & iteration (4 weeks - November 11 - December 6, 2025)
- Sprint 1: Document processing pipeline (OCR, classification, extraction, validation)
- Sprint 2: Conversational orchestration engine with intent detection and workflow routing
- Sprint 3: Calculation engines with triple-validation and legal compliance checks
- Sprint 4: PDF generation system and end-to-end testing with real landlord documents
- Agile sprints with weekly client demos
- Real-world document validation (handwritten invoices, poor-quality scans)
Launch & stabilization (2 weeks - December 9-20, 2025)
- Beta launch with 50-100 early-access landlords
- Performance optimization and token cost monitoring
- User onboarding refinement based on actual usage patterns
- Comprehensive error logging and monitoring dashboard setup
- Final legal review with German rental law attorney
Growth & optimization (Ongoing - Q1 2026+)
- Monitor peak-season performance (June-December billing cycle)
- Implement advanced features: year-over-year property data persistence, proactive legal update notifications, multi-agent workflows for complex scenarios
- A/B testing for UX optimization and conversion rate improvement
- Cost optimization: model fine-tuning, prompt compression, caching strategies
- Expansion to adjacent use cases: rent increase calculations, contract clause generation
Business Impact & Expected Results
What Landlords Will Achieve with Perks:
Time Back in Your Life
Complete annual billing in 15 minutes instead of 20+ hours—that's 98% of your time backNo more spreadsheet chaos, manual calculations, or stressful weekends before billing deadlinesLandlords report feeling relief and confidence instead of dread when billing season arrivesPeace of Mind Through Accuracy
Triple-validation system ensures cent-perfect calculations across all cost allocations100% compliance with German rental law eliminates tenant disputes and legal riskAutomated legal validation catches errors before bills go out, preventing costly mistakesBetter Experience for You & Your Tenants
Natural conversation interface replaces confusing form flows—upload documents in any orderProfessional, transparent bills that tenants actually understand reduce payment disputes95%+ completion rate proves the interface works for non-technical users
Strategic advantages gained
Market Differentiation Through AI-First Design
While competitors force landlords into rigid form-based interfaces, Perks meets users in natural conversation. Landlords can upload documents in any order, ask questions mid-process, and receive intelligent guidance through legal complexities.
This represents a fundamental UX paradigm shift in a market dominated by legacy software that makes people feel stupid instead of empowered. The conversational interface is particularly valuable for the target demographic (50+ year-old landlords managing 5-15 units) who appreciate the human-like interaction over complex form flows.
Regulatory Moat Through Compliance Automation
Deep integration of German rental law (BGB §556, HeizKV, CO2KostAufG) creates defensibility that competitors cannot easily replicate. Perks doesn't just automate forms—it embeds legal expertise into every calculation and validation step.
As German climate legislation evolves (2024 CO2 tax changes, upcoming heat transition requirements), Perks' structured legal layer adapts through schema updates rather than code rewrites. This positions the platform as the safest choice for risk-averse landlords who fear tenant disputes or regulatory penalties.
Platform Foundation for Ecosystem Expansion
The agentic architecture supports Reperks' broader vision beyond billing. The same conversational orchestration engine, document processing pipeline, and legal validation infrastructure can power adjacent landlord use cases with minimal marginal engineering cost.
Planned features include rent increase calculations (§558 BGB Modernisierungsumlage), rental contract generation, tenant communication templates, and maintenance cost tracking. Each new feature leverages existing infrastructure, positioning Reperks to capture wallet share across the full property management lifecycle rather than remaining a point solution.
Data Flywheel That Compounds Value Over Time
Each completed billing cycle adds structured property data—meter readings, consumption patterns, unit configurations, heating system details—to the landlord's private knowledge base. Year-over-year, Perks becomes smarter: pre-filling data from last year, detecting anomalies (why did Unit 3's heating usage spike 40%?), and requiring progressively less manual input.
This creates natural lock-in and switching costs as landlords build comprehensive multi-year property histories in the platform. The accumulated structured data becomes increasingly valuable for predictive features: forecasting utility costs before bills arrive, benchmarking against similar properties, and identifying maintenance issues through consumption anomalies.
Architectural Decisions Enabling Future Scale
Multi-model flexibility
AWS Bedrock's model routing enables the client to optimize cost/performance as AI models evolve. Currently using Claude 4.5 Sonnet (Extended Thinking), they can switch to more cost-effective models for simple tasks or more powerful models for complex legal reasoning without code changes.Separation of concerns
By moving calculations into deterministic code (rather than relying on LLM arithmetic), we created a reliable foundation that can integrate third-party verification services or even blockchain-based audit trails as the market demands. The LLM handles only the aspects it excels at: conversation and reasoning.Observability & learning
Comprehensive logging of user interactions, document uploads, and calculation validations creates a rich dataset for continuous improvement. Future ML models can be trained on this data to improve document classification, extraction accuracy, and conversation quality without human labeling.
Key Takeaways & Lessons
What's Making This Successful
Right-Sized Architecture for MVP Stage
We're resisting over-engineering (e.g., multi-agent systems, vector databases for RAG) in favor of simpler patterns that meet current needs. This keeps the 6-week timeline achievable while designing for future evolution. Complex systems can always be added; simplicity cannot be retrofitted.Hybrid AI + Deterministic Approach
Recognizing that LLMs excel at reasoning but fail at precise arithmetic, we separated concerns aggressively. The LLM orchestrates conversation and explains legal requirements; hardened code handles all calculations. This hybrid model is replicable across any regulated industry where compliance and precision are non-negotiable.Human-in-the-Loop as Feature, Not Bug
Rather than pursuing full automation (which would fail given document quality variability), we designed explicit confirmation flows that build user trust. Users see the system's work transparently and feel in control. This is especially critical for demographics unfamiliar with AI, where "magic" creates anxiety rather than delight.Legal Knowledge as Structured Data
Instead of embedding laws as raw text in prompts (the client's initial approach), we structured legal requirements as JSON schemas with rule definitions. This makes the system testable, maintainable, and auditable—essential for regulated domains. Future legal changes require updating schemas rather than rewriting prompts.
Technical Innovations
Context-Aware Calculation Validation
Our triple-validation approach (percentage-based, unit-based, reverse-calculation) doesn't just catch errors—it provides context-specific error messages. When validation fails, the system can explain why in terms of German rental law (e.g., "Total allocation exceeds 100% because heating costs must follow HeizKV distribution rules"). This level of domain-specific error handling is rare in AI applications.
Document-Type-Specific Extraction Pipelines
Rather than generic OCR, we implemented classification-first processing that routes documents through specialized extraction templates. This pattern is replicable across any document-heavy automation: legal discovery, medical records processing, financial audits. The key insight: classification accuracy > extraction accuracy in determining overall system reliability.
Cost-Aware Model Routing
We implemented basic but effective cost controls: expensive models (Extended Thinking) only for complex legal reasoning; cheaper models for simple extractions; aggressive caching for repeated legal queries. As LLM costs remain a key barrier to AI adoption, this engineering discipline must become standard practice.
HyperSense Services & Solutions Featured
This project showcases our expertise across multiple capabilities:
AI/ML development
Agentic workflow architecture, AWS Bedrock integration, multi-model orchestration, and cost-optimized LLM engineering for production systemsCloud architecture
Serverless AWS infrastructure design, scalability planning for 10K+ concurrent users, Infrastructure as Code implementation for rapid iterationProduct development
Rapid MVP methodology, user research integration, technical roadmap planning aligned with market windows (seasonal billing cycles)Document processing solutions
Intelligent OCR with confidence scoring, classification-first extraction, human-in-the-loop validation flows
Ready to Build Production-Grade AI Agents?
Building reliable AI agents requires more than prompt engineering. It demands architectural rigor, domain expertise, and engineering discipline to handle edge cases, cost controls, and regulatory requirements.
Whether you're tackling document automation, conversational AI, or compliance-heavy workflows, our team brings proven experience shipping production systems that users trust with high-stakes tasks.
Transform your operations with production-grade AI solutions.
Contact us and get your project moving
Describe your needs to us and we'll work together to craft the perfect software solution. Tell us your timeframes, your targets or KPIs, and any critical challenges or difficulties. You're at the right place — our team is eager to study and prioritize next steps together with you.Have a project in mind?