[ New ] Prompt Optimization Shouldn't Require Rewriting Your App

Hi, I'm Sami!

AI ENGINEER & BUILDER

INPUT PORT: 01

user_profile: explorer · budget mid

constraints: max_travel = 40km/day

AGENT ENGINE SANDBOX

RUNNING TOOLS...

  .   .   ✶   .   .
    . ✶ ✶ ✶ .
  . ✶ ✶ ✶ ✶ .
    . ✶ ✶ ✶ .
  .   .   ✶   .   .

CPU: 4 · TOOLS: 5 MODE: multi-agent

OUTPUT PLAN: V1

Day 1 -

Day 2 -

Day 3 -

Latest Writing

Thoughts on software development, AI, and building systems

View all

Feb 25, 2026

Prompt Optimization Shouldn't Require Rewriting Your App

How come we have advanved agent tracing products with minimal setup, but prompt optimization itself needing rewriting your product in new frameworks in order to work. My attempt on showing that it does not need to be the case

Prompt Optimization Langfuse

Jan 8, 2026

Building Memory Systems that Learn Across Conversations

How to create AI systems that adapt and improve their performance over time by learning from past interactions. Going over the MemGPT and Letta AI frameworks approach on bulding agents with memory systems that evolve through conversations.

MemGPT Agents

Dec 18, 2025

Automated RAG Evaluation without Human Labels (Ragas in Practice)

Learning and building automated evaluation system with Ragas. Can LLMs automatically evaluate RAG systems? Are human labels always needed?

Ragas RAG Evals

View all posts

Hi, I'm Sami!

Latest Writing

Prompt Optimization Shouldn't Require Rewriting Your App

Building Memory Systems that Learn Across Conversations

Automated RAG Evaluation without Human Labels (Ragas in Practice)

Get in Touch