01
The Case for Planner–Executor Architectures in Agentic Coding
Why serious coding agents should separate judgment from execution—and spend frontier-model capability where it matters most.
Articles on models, methods,
and making things work.
Divyansh
Agrawal
A home for technical writing, work in progress, and the occasional useful rabbit hole.
Read my latest articles ↓DIVYANSH AGRAWAL / RESEARCH INDEXISSUE 001
∆
FIND THEINTERESTING
QUESTION.
QUESTION.
- NOW READING
- Evaluation as design
- IN THE LAB
- RAG, tools, and traces
- WORKING MODE
- Slow, explicit, curious
SELECTED WRITING
01 ARTICLE↗
CURRENT & PAST WORK
Small research systems with an opinion about the future.
01AGENTIC SYSTEMS
Trace
A multimodal support-to-engineering agent that investigates bugs, verifies fixes, and hands off evidence-rich pull requests.
02LLM INFRASTRUCTURE
Hyperion
An ultra-low-latency LLM gateway for routing, caching, budgets, analytics, and forecasting.
03MEMORY SYSTEMS
memlayer
Plug-and-play persistent memory and recall for LLM applications.
A LITTLE CONTEXT
I'm interested in the distance between a capable model and a useful system.
I'm Divyansh Agrawal, an AI/ML researcher and builder. I care about how learning systems reason, retrieve, evaluate themselves, and earn trust in the hands of real people.
This is a home for work in progress: ideas that are not yet papers, systems that are not yet products, and the questions that sit between them.
Say hello ↗