Skip to main content
MMohsin NaeemMohsin Naeem
AboutPortfolioUpwork
Book a call
About→Portfolio→Upwork→
Book a call
MMohsin NaeemMohsin NaeemFounder and CEO, Techtiz. AI-native software and engineering.
GitHubLinkedInBook a call
Last updated August 2026© 2026 Mohsin Naeem. All rights reserved.
AI Knowledge & Productivity | Portfolio | Mohsin Naeem
← All industries
5 PROJECTS

AI Knowledge & Productivity

AI-powered software and automation delivered in ai knowledge & productivity.

Healthcare & WellnessFinance & FintechReal Estate & PropertyLogistics, Warehouse & OperationsMarketing, Content & SocialSales, CRM & Lead AutomationLegal & ComplianceRetail & E-commerceMedia, Entertainment & TranslationEducationHR / RecruitingConsumer / LifestyleAI Knowledge & Productivity
AIBackend / AI Engineer

AskTiz

Internal AI Knowledge Assistant

AskTiz is an internal AI-powered knowledge assistant that transforms an organization's Slack workspace into a searchable knowledge base. The platform continuously ingests Slack conversations, indexes them using semantic embeddings and hybrid search techniques, and enables employees to ask natural language questions about company history, technical discussions, decisions, and documentation. By combining Retrieval-Augmented Generation (RAG), hybrid search, reranking, and streaming AI responses, the system delivers highly accurate answers with inline citations linking directly to the original Slack conversations.

TypeScriptPython (Fastify)Next.js 14Supabase (PostgreSQLpgvector
Read the case study→
AIProduct architecture & full-stack development

Something here look like your problem?

Thirty minutes, free. Bring the workstream and I will tell you straight whether it is worth building.

Book a callHire on Upwork

AI Assistant

Cross-platform AI productivity app: chat, calendar, search and document generation in one place

AI Assistant is a cross-platform AI-powered productivity app that brings chat, scheduling, document creation and search into one place instead of scattering them across separate tools. Built with Expo (React Native) on the frontend and a modular-monolith FastAPI backend, it runs natively on iOS, Android and Web off a single scalable, secure server. The AI layer, powered by Anthropic Claude and Google Gemini, drives a conversational assistant, retrieval-augmented (RAG) document generation, semantic search and voice-to-text transcription, grounded with pgvector for vector search. Around that sits a full production stack: MFA-backed authentication, calendar sync with Google and Apple, map-based location search, subscription and plan management, and background processing via Celery and Redis, deployed with Docker.

Expo (React Native)TypeScriptExpo RouterRedux ToolkitNativeWind
Read the case study→
AIAI Engineer / Agentic Workflow Architect

Claude Multi-Agent Orchestration

Multi-Agent Development Workspace with Claude Code

A multi-agent orchestration setup built on Claude Code that drives full-stack product development across a NestJS API and a React Native app from a single workspace. A coordinator agent plans each feature and delegates to specialised subagents for API contracts, cross-repo review and record keeping, while repo-level skills encode the build, check, review and sign-off loop. The result is a repeatable, auditable workflow where every task moves through contract, API, app, verification and documentation in a fixed order, with parallel reviewer agents gating each change before it ships.

Claude CodeClaude OpusCustom SubagentsAgent SkillsNestJS
Read the case study→
AIAI Engineer

Voice AI Agents

Real-Time Interview & Outbound Sales Voice Agents

Two production-grade real-time voice agents built on Vapi, served through a live browser demo in which either agent can be spoken to directly. The AI Interview Agent runs a staged screening interview across five roles — Frontend Engineer, Backend Engineer, Sales Representative, Customer Success Manager and Product Manager — asking adaptive follow-ups and scoring the candidate against a role-specific five-competency rubric. The Outbound SDR Agent runs a cold-call simulation covering a permission opener, discovery, objection handling and a written CRM record. Each call ends with a generated report rather than a chat log: the interview produces competency scores of 1-5 with supporting evidence, a recommendation and a coaching note, while a live stage rail is inferred from the transcript as the conversation progresses. Both assistants are defined in code and passed inline to the Vapi SDK, so prompts, voice configuration and analysis schemas live in version control rather than only in a dashboard.

Next.js 16React 19Tailwind CSS 4JavaScriptVapi (@vapi-ai/web)
Read the case study→
AIAI Engineer

Bland Voice AI Agents

Interview & Outbound Sales Agents on Bland's Web SDK

A second implementation of the real-time voice agent suite, rebuilt on Bland's Web Agent SDK to compare platform architectures against the earlier Vapi build. Two agents run in the browser: a staged screening interviewer that probes vague answers and scores against a five-competency rubric across five roles, and an outbound SDR that opens for permission, runs discovery, handles objections and asks for the meeting. The port surfaced real architectural differences — Bland web agents are persistent server-side objects created through POST /v1/agents rather than configs passed inline at call time, the transport is a raw WebSocket carrying PCM16 frames rather than WebRTC, and the platform exposes no model selection or declarative output schema. Scoring was therefore rebuilt on Bland's post-call /analyze endpoint, which returns a positional answer array, with a dedicated parser mapping those answers back to the rubric by index. The UI was redesigned as a light editorial layout: warm paper canvas, serif display type and hairline rules in place of stacked dark cards.

Next.js 16React 19Tailwind CSS 4JavaScriptBland AI (@blandsdk/client)
Read the case study→