--- title: "Tilak Raj (@tilakraj) | Hashnode" description: "Founder and CEO of Brainfy AI, writing about AI products, SaaS architecture, and startup execution. Read the latest articles by Tilak Raj on Hashnode." url: "https://hashnode.com/@tilakraj" --- @tilakraj # Tilak Raj @tilakraj · Vancouver, Canada · Joined March 2026 Founder and CEO of Brainfy AI, writing about AI products, SaaS architecture, and startup execution. ### [TypeScript Patterns for AI SaaS. Type System Techniques That Prevent Production Bugs](https://tilakrajai.hashnode.dev/typescript-patterns-for-ai-saas-type-system-techniques-that-prevent-production-bugs?utm_source=hashnode&utm_medium=feed) AI SaaS products introduce type challenges not covered in standard TypeScript guides. Modeling uncertain AI outputs. Typed prompt templates. AI pipeline state modeling. Runtime validation for model responses. These are the patterns refined across 8 production products. 2 min read · [tilakrajai.hashnode.dev](https://tilakrajai.hashnode.dev/typescript-patterns-for-ai-saas-type-system-techniques-that-prevent-production-bugs?utm_source=hashnode&utm_medium=feed) [Apr 7](https://hashnode.com/posts/typescript-patterns-for-ai-saas-type-system-techniques-that-prevent-production-bugs/69d531103ef24c6671c3dcc4) ### [How to Build a Vertical AI MVP in 30 Days. Complete Technical Playbook](https://tilakrajai.hashnode.dev/how-to-build-a-vertical-ai-mvp-in-30-days-complete-technical-playbook?utm_source=hashnode&utm_medium=feed) I have shipped 8 vertical AI products. The fastest took 18 days. This is the technical process. What to build each week. What decisions to make early. What to delay. Code patterns that allow fast execution without technical debt. 3 min read · [tilakrajai.hashnode.dev](https://tilakrajai.hashnode.dev/how-to-build-a-vertical-ai-mvp-in-30-days-complete-technical-playbook?utm_source=hashnode&utm_medium=feed) [Apr 5](https://hashnode.com/posts/how-to-build-a-vertical-ai-mvp-in-30-days-complete-technical-playbook/69d28e539f5c9fccd1bf7f1e) ### [How I Built AgriIntel Real Time Agricultural Data Pipeline. Architecture and Lessons](https://tilakrajai.hashnode.dev/how-i-built-agriintel-real-time-agricultural-data-pipeline-architecture-and-lessons?utm_source=hashnode&utm_medium=feed) Building a pipeline that ingests sensor data from more than 1.2 million acres, combines satellite imagery, weather feeds, and commodity markets, and produces agronomic recommendations in near real time. This is the architecture. 3 min read · [tilakrajai.hashnode.dev](https://tilakrajai.hashnode.dev/how-i-built-agriintel-real-time-agricultural-data-pipeline-architecture-and-lessons?utm_source=hashnode&utm_medium=feed) [Apr 4](https://hashnode.com/posts/how-i-built-agriintel-real-time-agricultural-data-pipeline-architecture-and-lessons/69d13c9bdcf6dc85150489e2) ### [Building AI Products for Canadian Regulated Industries. The Technical Compliance Guide](https://tilakrajai.hashnode.dev/building-ai-products-for-canadian-regulated-industries-the-technical-compliance-guide?utm_source=hashnode&utm_medium=feed) PIPEDA, Quebec Law 25, AIDA, data residency requirements. Building AI for Canadian healthcare, insurance, finance, or government requires navigating strict regulations. This is a practical technical implementation guide. 3 min read · [tilakrajai.hashnode.dev](https://tilakrajai.hashnode.dev/building-ai-products-for-canadian-regulated-industries-the-technical-compliance-guide?utm_source=hashnode&utm_medium=feed) [Apr 2](https://hashnode.com/posts/building-ai-products-for-canadian-regulated-industries-the-technical-compliance-guide/69ce99ee610d1dbff51045f7) ### [How I Cut AI API Costs by 60% Without Sacrificing Output Quality](https://tilakrajai.hashnode.dev/how-i-cut-ai-api-costs-by-60-without-sacrificing-output-quality?utm_source=hashnode&utm_medium=feed) Running 8 AI products in production means AI API costs are a significant operating expense. Over 18 months I developed a systematic cost optimization approach that reduced costs by 60 percent while maintaining or improving output quality. Here is every technique I use. 3 min read · [tilakrajai.hashnode.dev](https://tilakrajai.hashnode.dev/how-i-cut-ai-api-costs-by-60-without-sacrificing-output-quality?utm_source=hashnode&utm_medium=feed) [Apr 1](https://hashnode.com/posts/how-i-cut-ai-api-costs-by-60-without-sacrificing-output-quality/69cd481354ba94a5cd2029ae)