Aniket Kulkarni
Aniket Kulkarni is the founder of Curlscape, an AI consulting firm that helps companies build and ship production AI systems. With experience spanning voice agents, LLM evaluation harnesses, and bespoke AI solutions, he works at the intersection of engineering and applied machine learning. He writes about practical AI implementation, model selection, and the tools shaping the AI ecosystem.
Articles by Aniket Kulkarni
Anthropic Claude API Pricing Guide 2026: Opus, Sonnet, and Haiku Compared
Complete Anthropic Claude API pricing for March 2026. Compare Opus, Sonnet 4.6, and Haiku 4.5 with batch discounts, prompt caching savings, rate limits, and real-world cost breakdowns.
OpenAI API Pricing Guide 2026: Every Model Compared
Every OpenAI API model priced and compared for 2026, from GPT-5.2 to o4 Mini. Includes real-world cost calculations for chatbots, pipelines, and more.
Fine-Tune an LLM to Mask PII in 2 Hours with Axolotl — Step-by-Step Tutorial
Learn to fine-tune an LLM for PII redaction using Axolotl and Modal. Step-by-step tutorial covering QLoRA, dataset preparation, and production deployment for GDPR compliance.
OpenAI vs Gemini vs Claude: Complete API Pricing Comparison (2026)
Compare API costs for OpenAI GPT-5, Google Gemini, and open-source models. See real pricing per 1M tokens, cost breakdowns for 1M document inference, and when self-hosting saves 5x.
Full-Text Search at Scale: PostgreSQL vs Elasticsearch vs Vector Search (2026)
Compare full-text search solutions for large datasets: PostgreSQL, Elasticsearch, DuckDB, and vector search. Benchmarks on 3.8M rows with BM25, query latency comparisons, and production implementation tips.
How to create a MCP Server - An Introduction using SEC EDGAR API
Step-by-step tutorial on building an MCP server using the SEC EDGAR full-text search API. Learn how to expose tools to LLMs and build AI agents with the Model Context Protocol.
Some Initial Thoughts on Llama 4 Models
Meta's Llama 4 Scout and Maverick models bring 10M token context windows and open weights. We break down the hardware requirements, practical use cases, and cost advantages over GPT-class models.
How to build Text2SQL Agent using MCP
Build a Text2SQL agent using the Model Context Protocol and a Postgres MCP server. Includes code walkthrough, Northwind database testing results, and comparison with LangGraph.