Rifki Rosada | Android + AI

Media Android App - AI Chat + Search UX

Improved AI chat entry, suggestion handling, and search state behavior in a live Android product flow.

Android AI UX Engineer 3-week delivery sprint Remote contract delivery
  • Problem

    Users lacked a clear transition from AI chat prompts to meaningful search actions, and state sync issues reduced UX reliability.

  • My scope

    Worked inside the existing WebView-based AI entry path so the feature fit the live app architecture.

  • Result

    Stabilized AI chat-to-search state sync in production — eliminated mismatch issues that broke the discovery flow for end users.

Problem

Users lacked a clear transition from AI chat prompts to meaningful search actions, and state sync issues reduced UX reliability.

Constraints

  • AI entry needed to integrate through an existing WebView pathway
  • Search state had to stay consistent across intents, suggestions, and results
  • Changes had to be shipped safely in an active production app

System workflow

  • Worked inside the existing WebView-based AI entry path so the feature fit the live app architecture.
  • Added suggestion bubbles to reduce first-action hesitation and guide search intent.
  • Stabilized state transitions between selected intent, query text, and results.
  • Documented edge cases and implementation constraints for future iteration.

Result

  • Stabilized state transitions across chat → suggestion → query → result flow in a live production app.
  • Eliminated state-mismatch issues that broke discovery for users in key search paths.
  • Documented edge cases and behavior expectations so the next iteration ships without rediscovery cost.

Tech stack

  • Android
  • Kotlin
  • WebView
  • Search UX

Related delivery proof across internal tools, automation, Android + AI, and supporting product systems.

Public Android + AI

Public build

OffScan AI

Android Product Engineer6-week build and release

Published an Android workflow that performs OCR locally without cloud upload requirements.

  • Android
  • On-device OCR
  • Edge AI
Read the case study

Client Systems

Client delivery

Enterprise CRM - Sales Pipeline & Performance System

Lead Full-Stack Engineer6-week delivery sprint

Cut the weekly pipeline review cycle from ~2 days of spreadsheet reconciliation to ~15 minutes — single source of truth across sales, ops, and management.

  • Laravel
  • Next.js
  • PostgreSQL
Read the case study

Automation Systems

Client delivery

Inbound Order & Lead Ops Automation

Automation Engineer2-week delivery sprint

Eliminated an estimated 60–80 hours/month of manual data entry across multi-branch operations. Booking + reporting now flow automatically into a single source of truth.

  • n8n
  • Google Apps Script
  • Google Sheets
Read the case study

Have a similar workflow?

Share what your team needs to improve. I can help define the first useful milestone.