Projects and implementation scenarios.
A selection of projects — internal PoCs, partner pilots, reference architectures — showing how we apply our method in real contexts.
The cases published here are technical implementation scenarios: internal PoCs, pilots with synthetic or anonymized data, and reference architectures. As real customer projects reach production, we replace them with named cases with permission.
Legal sector · Internal PoC
AI Gateway for a 50-person law firm
Enabling ChatGPT and Claude for the firm without exposing client names, case numbers, or financial data. Result: 95% of prompts pass to the model PII-free, with <150ms latency.
- ▸95% PII masking accuracy
- ▸<150ms Gateway overhead
- ▸Zero client data in clear on OpenAI
- ▸200+ lawyers enabled in 2 weeks
E-commerce · Public demo
24/7 email triage agent for e-commerce
Automated classification and first response on 2,000 daily customer care emails. Human team only intervenes on the most complex 25%.
- ▸75% emails resolved autonomously
- ▸~8s average response time
- ▸60% team time reduction
- ▸CSAT stable above 4.2/5
Manufacturing · PoC
AI-powered expenses dashboard for manufacturing SMB
Automation of expense report process with OCR + AI. CFOs get real-time reports, employees just snap the receipt and they're done.
- ▸From 10 days to 2 days for monthly close
- ▸93% receipt extraction accuracy
- ▸Zero manual data entry
- ▸Automatic fiscal compliance
Cross-industry · Reference architecture
AI + HubSpot CRM integration for lead qualification
Automatic lead enrichment with public info, AI-based signal scoring, smart assignment to sales. Replicable setup on Pipedrive, Salesforce.
- ▸3x faster lead qualification
- ▸+45% conversion from MQL to SQL
- ▸Data enriched in <30 seconds
- ▸Zero PII exposed in clear