14 systems in production across financial services, healthcare, logistics, retail and enterprise software. Open any project to read the full story.
Automated prospecting, enrichment, personalization, outreach and reply handling for a Wall Street brand targeting PE firms, hedge funds and family offices.
Entity-linked knowledge graph over documents with multi-hop reasoning, auditable citations and Salesforce integration.
A framework that synthesizes respondent data for text and image studies, benchmarked against live panels.
IVR with a real-time AI video consult for pre- and post-procedure guidance, with auto-logging and scheduling.
Diffusion-based try-on with conversational sizing and retrieval over the product catalogue, wired to live inventory.
Resilient data ingestion with fallback logic, gathering product data, reviews and listings from multiple sources.
A knowledge graph of routes, hubs and service levels, with optimization and exception handling exposed through APIs.
Anomaly detection on vibration and temperature for industrial conveyors, combined with retrieval and forecasting for planners.
Production-scale retrieval platform over millions of documents across many client deployments, with multimodal search and a mobile chatbot.
Domain-specific model tuning with LoRA and Q-LoRA, built as a repeatable framework rather than a one-off experiment.
Gradient-style optimization over prompts and pipelines, tuning systems against measurable objectives instead of intuition.
Clusters raw conversation logs into coherent intents without labelled data, so support taxonomies come from real usage.
Named entity recognition tuned for messy real-world documents, with evaluation harnesses and human review loops.
Usage dashboards and billing built into a client platform, with metering, invoicing and role-based access.
Tell us the problem and what needs to change. We will say honestly whether AI is the right instrument for it, or something else and how we would approach the solution.
