Building Conversation Repairer for Aishwarya: Grounded Relationship Memory with Gemma
My friend Aishwarya often runs into a tough communication pattern. When tensions or awkward moments happen in a chat, she swings between two extremes: either she feels too kind and shy to state what she needs, or she swings the other way and sounds completely nonchalant and detached. Both reactions cause confusion. People misread her silence as indifference, or her detachment as rudeness, even…
Aishwarya frequently struggles with communication in chats. She can either be too passive or become detached, leaving people confused about her true intentions. Aishwarya also has trouble remembering past commitments and preferences discussed weeks earlier in long chat threads. To help her, I created Conversation Repairer, a full-stack tool that turns WhatsApp chat logs into a searchable relationship memory dashboard.
When a tense message is entered, it retrieves relevant past promises, communication preferences, and quotes from the user's history and suggests three response options: Soft, Casual, or Direct. Using open-weight Gemma 4, the tool ensures privacy by storing memories strictly in the user's browser and does not rely on any proprietary APIs.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
