← All Work/Satiaphic

Independent SaaS Project

Satiaphic — turning customer feedback into operational improvement workflows.

A multi-tenant B2B SaaS project that ingests Google Maps reviews and QR/link/widget feedback, then organizes them into triage workflows, AI-assisted feedback analysis, proposals, work items, and resolution tracking.

Visit Satiaphic ↗

189

Commits

3

User Roles

~40

Permissions

6-stage

AI Pipeline

6

Vercel Cron Jobs

20

SaaS Tools Researched

Problem

The gap this fills

Businesses collect reviews and customer feedback across public review platforms and direct feedback channels, but often lack a structured way to detect recurring issues, prioritize improvements, assign work, and track resolution.

Satiaphic was designed to connect feedback collection with operational follow-through, turning passive review data into practical internal workflows.

My Role

Product Builder & Full-Stack Developer

  • Product research and competitive analysis (20 SaaS tools)
  • SaaS workflow design and product architecture
  • Full-stack application development
  • Multi-tenant architecture implementation
  • Authentication and role-based permissions system
  • AI-assisted feedback analysis pipeline
  • Dashboards and operational workflow UIs
  • Billing and subscription workflow integration
  • Security-focused controls and audit tracking
  • Go-to-market materials and product documentation

Workflow

Product workflow

The product focuses on the full feedback lifecycle: from collection to triage, analysis, prioritization, execution, and follow-up.

01

Google Maps Reviews

02

QR / Link / Widget Feedback

03

Feedback Inbox

04

AI Theme Discovery

05

Proposals

06

Work Items

07

Resolution & Changelog

Features

Core features

01

Feedback Inbox

Triage, filter, assign, prioritize, and resolve feedback items. Provides a structured operational view of all incoming feedback across channels.

02

Google Maps Review Ingestion

Pulls public review data into the product workflow, making external review activity part of the internal feedback process.

03

QR / Link / Widget Feedback Collection

Supports direct customer feedback collection through public forms, QR codes, and embeddable widget touchpoints.

04

AI-Assisted Theme Discovery

Integrates LLM APIs into topic extraction and structured analysis, combined with deterministic clustering and quality review before proposal drafting.

05

Proposals and Work Items

Converts recurring feedback themes into internal improvement proposals and execution tasks assigned to team members.

06

Team Roles and Permissions

Supports owner, admin, and member role separation with approximately 40 granular permissions controlling access to features and data.

07

Billing and Subscription Workflows

Includes plan-based feature gating and subscription-related flows through DodoPayments integration.

08

Dashboards and Analytics

Gives business users visibility into feedback trends, resolution progress, and operational follow-up metrics.

Architecture

Technical architecture

Satiaphic is built as a multi-tenant SaaS application where business-level data isolation is enforced through authenticated session context and tenant-scoped database access.

Frontend

  • Next.js
  • React
  • TypeScript
  • Tailwind CSS

Backend

  • Next.js API route handlers
  • Nodemailer / SMTP

Database

  • MongoDB
  • Native MongoDB driver

AI

  • LLM APIs
  • LLM-assisted feedback analysis pipeline
  • Deterministic clustering

Payments

  • DodoPayments

Background Jobs

  • Vercel Cron (6 scheduled jobs)

Hosting

  • Vercel

Security

  • Zod validation
  • Rate limiting
  • Tenant scoping
  • Env-based secrets

AI Pipeline

How the AI pipeline works

Satiaphic integrates LLM APIs into a 6-stage feedback analysis workflow. The system combines LLM-assisted feedback analysis with deterministic clustering, quality review, and proposal drafting. LLM-based processing handles topic extraction only. Product logic, clustering, and execution are deterministic. No custom model training. No RAG.

01

Collect

Business-specific feedback gathered via Google Maps, QR codes, links, and embedded widgets.

02

Extract

LLM API extracts topics, signals, and patterns from raw feedback text.

03

Cluster

Related items are grouped using deterministic clustering logic.

04

Review

Generated themes are reviewed for quality before surfacing to users.

05

Propose

Improvement proposals are drafted from validated themes.

06

Execute

Proposals link to operational work items for team follow-through.

Security

Security-focused controls

The application includes layered controls for authentication, authorization, validation, and data integrity. The approach is appropriate for a multi-tenant SaaS product handling business-level data.

Session-based authentication
Role-based access control (owner / admin / member)
Business-level tenant scoping on all data queries
Protected API route handlers
Zod validation on all API inputs
MongoDB-backed rate limiting
Environment-based secret management
Encryption for sensitive stored data
AI input safety checks before processing
Audit and event tracking for key operations
Internal admin controls for platform operations
Layered access controls for sensitive administrative workflows

Research

Product and market research

Satiaphic was shaped through competitive research across 20 SaaS tools in review management and feedback management. The research helped define the product gap: many tools collect or display feedback, but fewer connect feedback directly to internal improvement workflows.

Categories analyzed included review management, feedback management, product feedback, and customer operations tools — informing Satiaphic's positioning around operational feedback follow-through rather than just feedback display.

Honest Assessment

What I'd improve next

Satiaphic is a working product, but it has gaps. These are the things I'd prioritize in the next phase.

01

Public demo environment with seeded data so visitors can see the product without a real account.

02

Automated tests around critical flows — particularly the AI pipeline, billing, and permission checks.

03

A demo video and screenshot set for the case study and marketing pages.

04

Integration options for Slack, Jira, or Linear to connect feedback workflows to existing team tools.

05

Public documentation covering the architecture, tenant model, and AI pipeline in more depth.

Next

See the Expenra case study →