Applied AI · Search & Retrieval · Math · Travel
Hi folks, thanks for dropping by. I’m Antaripa, 25 years young, remote-first, and happiest in my world of search, math and travel.
Currently building the intent layer at SpecStory that powers how you interact with your code.
I am also an Applied AI Consultant partnering with early-stage teams to bring AI native products to life. I consult across LLM systems, search, retrieval + eval pipelines, and memory systems.
My work blends hands on research with practical engineering, and everything I share reflects experiments, personal deep-dives, learnings, and client projects. I’m especially drawn to search and retrieval as a problem space, and it is the domain I enjoy exploring the most. I also do a lots of math in my free-time ;)
If you’re into intelligent systems and the future of developer tooling, you’ll probably feel at home here.
Featured writing
Writing in the Margins: Proposed solution to Lost in the Middle
Needle in haystack issue for long context, the margin workflow, chunked prefill, KV cache, and evaluation results.
Parse and Retrieve Dense Tables Accurately with Tensorlake
Handle messy and complex tables for accurate retrieval using hierarchies, coordinates, and summaries.
Fix Broken Context in RAG with Tensorlake + Chonkie
RAG pipelines break on real-world documents because parsers flatten structure and chunkers chunk blindly.
Build Schema-Enforced Pipelines with Tensorlake + Outlines
Pair Tensorlake with Outlines to keep document pipelines clean: structured inputs in, schema-validated generations out.
Building Reliable AI Financial Agents with Automatic Trace Analysis
Trace every tool call, visualize deviations, and stop hallucinated portfolio changes before they hit production workflows.