Case Studies

Real client builds. Architecture detail, stack breakdown, and the specific engineering choices that made each one ship.

Hair Time Salon

Hair Time Salon: 24/7 AI Voice Receptionist

24/7 AI voice booking agent on the salon's existing line, $35-55/mo at pilot volume, multi-tenant from day one — second location ships in 3 hours of engineering

VapiGPT-4oDeepgramElevenLabsn8n cloud+4 more

recruitRyte

800M-Profile Vector Search at sub-second latency

sub-900ms p95 search across 800M+ indexed candidate profiles with under 2% recall loss after quantization

QdrantHybrid RetrievalCross-Encoder RerankingFine-Tuned EmbeddingsBinary Quantization+3 more

Demandfarm

Demandfarm: Account Research Workflow Automation

automated account intelligence agent that pulls SEC filings, earnings calls, financial data, and competitor signals into a single research report for Key Account Managers

PythonPortkey AI GatewaySEC APIYahoo Finance APIGoogle Search+4 more

Alacer (Velocity FinCrime Solution Suite)

Alacer: Real-Time Fraud Detection with Explainability

production fraud detection with per-decision SHAP explanations, sub-second Redis-backed inference

Isolation ForestSHAPRedisPythonUnsupervised Learning

FamePilot

FamePilot: Aspect-Based Review Sentiment at Scale

aspect-level sentiment extraction with LLM-generated review reports across customer feedback at scale

spaCyRelation ClassifierPrompt EngineeringPythonNLP

P

Personal projects

10+ Productized AI Agents I Built and Use Daily

productization pattern in practice: 4 production AI agents (GEO audit, competitor analysis, market demand, content gap) plus 6+ supporting workflows.

PythonClaudeGeminiFirecrawlPDF Generation+2 more