Adelina Martiniuc

Adelina Martiniuc

RoryPlansRoryPlans
RoryPlans.ai - your AI PM
#833583641 followers9 following
#1,276Last month
108 KP
#7,164Last year
261 KP
>10,000All time
379 KP

About

Product Engineering Leader with 15 years of experience, driving successful launches at Google, Cruise, and Vercel. Passionate about AI and planning—a focus that began with my university thesis and led me to found RoryPlans. Mom of two, always building for the future. 🚀

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

  • RoBrain
    RoBrainShared AI memory that stops agents from repeating mistakes
    May 2026
  • Function-Calling Dataset Generator
    Function-Calling Dataset GeneratorData Generation Tool for Function Calling, built for teams.
    Nov 2025
  • RoryPlans
    RoryPlansA shared brain for your agents and team
    Jun 2025
    • 🎉
    Joined Product HuntMarch 28th, 2025

Forums

Adelina Martiniuc•

1mo ago

RoBrain - Shared AI memory that stops agents from repeating mistakes

RoBrain is open-source shared memory for teams using AI agents. It captures every decision and the alternatives you ruled out — automatically, across every developer's sessions — and flags when a new decision contradicts an old one. Your team revisits past decisions intentionally, with the original rationale in front of them, instead of re-litigating from zero. Works across Claude Code, Cursor, and Copilot.
Adelina Martiniuc•

8mo ago

I'm Adelina, obsessed with making agents faster and more reliable. Ask me anything!

Hey PH Community!

I m Adelina, co-founder and CEO at RoryPlans.dev, part builder, part dreamer, and fully obsessed with making AI agents faster, smarter, and more reliable

Function-Calling Dataset Generatorp/function-calling-dataset-generatorAdelina Martiniuc•

8mo ago

How do you make your agents more reliable?

Many of the agents being built today rely heavily on tool use, calling APIs, functions, or external services to perform tasks. However, these agents often struggle with reliability: they can hallucinate, select the wrong tools, or pass incorrect arguments. While prompt tuning can help to some extent, it usually leads to oversized and hard-to-maintain models. How are you approaching this challenge and ensuring that your agents use tools accurately and efficiently?

View more