Rising CAC Is a Symptom, Not the Disease
A survey of more than a hundred Indian D2C founders this year surfaced a number that looks like a marketing problem and is actually…
Essays & Field Notes
The Journal
Essays on agentic AI and distributed systems, and the architecture that keeps them working under pressure.
total
105
span
10 yrs
topics
9
Machine Learning Types Are the Wrong Abstraction for Agentic Systems
Executive Summary We still classify machine learning systems by how they are trained. Supervised. Unsupervised. Reinforcement learning. That taxonomy made sense when models were…
Statistics: Why Intelligent Systems Must Admit Uncertainty
Executive Summary Most intelligent systems don’t fail because they lack data. They fail because they treat estimates as facts. Statistics exists to solve a…
PART I — Why Most Agents Fail: The Architectural Blind Spots Behind CoT and Tool-Only Models
Modern agent demos look impressive until you load them with real work. Real constraints. Real ambiguity. Real environments. That’s when most agents collapse. And…
What AI Exploit Benchmarks Actually Tell Us About System Architecture
Recently, researchers at Anthropic published a study showing autonomous AI agents discovering and monetizing real software failures in simulated environments. The headlines made it…
Embedding Drift: Why Changing Your Model Re-Indexes Everything
You upgrade your embedding model. The new one benchmarks better, so you point your pipeline at it, ship it, and within a day retrieval…
The Hidden Architecture Behind Dense Vector Search (and Why It’s Hard to Scale)
Most people think dense vector search works like this: embed your documents store the vectors run cosine similarity Done. This is the biggest misunderstanding…
The Hidden Complexity Behind Scaling Dense Vector Search
A systems-level explanation for engineers, architects, and anyone building RAG, search, or agent infrastructure. Dense retrieval looks clean on paper. You take an embedding…
Distributed Vector Search: How Real Vector Databases Scale Beyond One Machine
Why dense search becomes a routing, sharding, and distributed-systems problem Vector search looks simple when everything fits on one machine. It becomes a different…
The Write Path in Vector Databases (It’s a Distributed Systems Problem)
(Where Dense Search Becomes a Distributed Systems Problem) Most content about vector databases focuses on the glamorous part: fast queries, clever indexing, tight cosine…