Sitemap - 2026 - Jagadeesh Rampam
The case for TypeScript SDKs in Grove
Building Grove v0.1: The Agent Harness as a First-Class Citizen (as well as first principle)
How We Cut AI Inference Cold Starts in Half: Optimising GPU Startup for Photo Analysis
The Image Was Fine. Our Pipeline Wasn't.
Parjanya 2.0 is open to everyone
Price Is Only Half the Compute Problem
N+1 Without an ORM: The Hidden Cost of Extra Round Trips
From Managed Services to Primitives (DX vs DIY)
When SageMaker Wasn't the Problem
Prompt Debt: How We Doubled Throughput Without Changing the Model
Why We Use Three AWS Accounts (Not Two) for Parjanya v2.0
Archetypes of the Southern Ocean
Valuing an Indian Octopus: Info Edge Through Damodaran’s Lens
Traditional Japan (Monochrome)
The ARM Wheel Problem: What's Actually Standing Between You and Graviton's 34% Cost Savings
TBIE in Practice: Designing Resilient AI Pipelines That Recover, Reconcile, and Re-run
Context Engineering and Context Debt
From Score Engine to Rule Engine: Why I Rebuilt the Decision Layer
Sonnet 4.6 Became My New Benchmark for Building an Infra-Heavy VLM Platform
Parjanya v2.0: From Localhost Headaches to CloudFront+ALB Architecture
From localhost friction to production-shaped architecture
The Hidden Runtime Failure Behind Claude’s Recent Regression
When Adaptive Thinking Goes Off the Rails
From 1/4 to 3/4: Re-architecting an ML Pipeline for Graviton
Cloud Bills as Lagging Indicators of Design Debt
Why We Could Only Use AWS Graviton for 1 of Our 4 ML Lambdas
VLM Batch Inference — 4-bit Quantization Deep Dive
Atlas — Manual + Auto-Research: an open-source system design playground
#CommitGoals: Writing Git Messages Worth Double-Tapping
Intelligent Model Orchestration for AI Agent Systems
Claude API Lock-in: Prevention & Recovery Guide
The Boring Moat: How Labware Becomes a Platform for Cell Culture
Databases, Caches and Queues: A universal Rule for Distributed Systems
Mastering Scalability: A 39-Point Analysis for Robust System Design
Wilderhood TV — Camera Roles & Field SOP (R5C • R6 • R50V • R7)
From diagnosing AI debt to durable fixes (Part-3)
Why Cash Beats Profit (Cash is the King)
3 Essential Claude Code Best Practices Every Developer Should Know
Why you should chose Haiku as Default model and escalate if needed
AWS Graviton4 vs Intel x86: From $10 POC to Production Validation