Talkstore Begins Now! 🟢 Building to $100K
Want to back the stream? The «داعم» membership on YouTube is EGP 60 a month: badges, emoji, and I answer your questions first on stream. Become a supporter
The gist
The stream documents the public start of building Talkstore: a proposed Shopify-specific AI assistant through which merchants could manage products, storefront work, and commerce intelligence conversationally. Its capabilities and possible expansion beyond Shopify are presented as conditional directions, not validated outcomes. Practical work covered Shopify app and development-store setup, Supabase integration and Prisma migrations, secret handling, and repeated diagnosis of session, connection, preview, and Railway deployment problems. The preview and some setup steps worked, and the service later appeared active, but several database, network, build, and deployment issues remained intermittent or unresolved in the covered segments. This led to useful lessons about starting with logs, documenting a stubborn problem, seeking a fresh diagnostic perspective, and reviewing coding-agent compromises rather than accepting a result merely because it works temporarily. The stream also presents a multi-agent command center that separates research and task preparation from implementation, code, security, and compliance review, using dependencies, an adaptive timeline, and human approval gates. Luqman felt this structure accelerated and preserved the context of the work, while still questioning whether every agent was running and visibly logged. He emphasized that authentication, secrets, and nuanced decisions continue to require human intervention, and that task count is a poor measure of difficulty. Work later shifted toward pre-launch distribution: a simple but polished Astro waitlist site kept separate from the Shopify app, with email capture, analytics, social metadata, a teaser, and a distribution campaign. The first landing-page draft had missing hero content and styling or rendering failures, so it was treated as an unfinished iteration. Other useful discussions included audience questions about using AI to explore income paths from existing expertise, SaaS unit economics, choosing between ads and SEO/GEO, Arabic-market WhatsApp automation, and targeting external markets, plus local voice dictation, content automation, and Telegram community options. Stream lag and interruptions were also investigated without a conclusive cause, while music licensing and gym culture appeared as brief secondary discussions.
121 moments from the stream
- 0:00:17
Troubleshooting the Stream Connection
He explains that the stream was restarted several times because of a connection problem and another unspecified issue. Disconnecting one Ethernet cable appeared to improve the connection, while stream statistics were monitored for stability.
- 0:01:48
Building and Marketing a Project in Public with AI
He describes the channel’s approach: showing the workflow from initial project construction through marketing in live streams. He says his background is digital marketing rather than software development, and that he uses AI to turn ideas into projects.
- 0:04:26
Why Build an App for the Shopify Ecosystem
He introduces Shopify as a platform entrepreneurs use to sell goods and services, explaining that his prior experience was primarily from the merchant side. He is now moving into the app side while drawing on his broader familiarity with the ecosystem and its apps.
- 0:05:27
Red, Blue, and Purple Ocean Markets
He contrasts a red ocean, where competition and demonstrated demand are high, with a blue ocean, where an unfamiliar idea faces little competition but requires customer education and demand validation. In his opinion, Talkstore is closer to a “purple ocean” combining traits of both.
- 0:07:20
Talkstore: Operating a Shopify Store by Conversation
He outlines Talkstore as a conversational AI agent through which Shopify merchants could perform store tasks instead of navigating products, the website, and analytics dashboards. Proposed capabilities include live storefront edits and a focus on GEO, which he describes as analogous to SEO and related to AI and product management; these are planned capabilities, not documented test results.
- 0:11:59
Organizing Work with a Timeline and Agent Hub
Luqman outlines a command center with a roadmap that shows task timing, a hub for agents and subagents configured with specific goals and instructions, and a task board designed for agent-managed workflows.
- 0:12:54
When Automation Becomes a Way to Delay the Core Work
Luqman reflects that automation work can be genuinely useful, but it can also become a response to anxiety about starting the core business work. He compares it to hesitating before entering cold water and finding side activities that postpone the decisive step.
- 0:15:58
Preparing Context-Rich Tasks with MCP and Specialized Agents
Luqman explains that sending a bare task description to an agent lacks sufficient context and guidance, so he connected the command center to an MCP server that exposes project history, status, and task dependencies. During task preparation, specialized agents inspect the codebase and perform external research when needed before their findings are combined.
- 0:20:26
A Multi-Agent Workflow for Preparing, Executing, and Reviewing Tasks
He explains a workflow that creates a Markdown task file and detailed prompt, hands implementation to a builder agent, and assigns another agent to review the codebase from a different perspective, with the agents collaborating after each task in the command center.
- 0:22:19
A Dependency-Aware Task Board and an Adaptive Timeline
He presents a weekly board where completing one task can unblock others and move them into the to-do list, creating game-like progression. He notes that task count does not equal workload and that the initial timeline estimate remains uncertain and can be adjusted periodically according to actual progress.
- 0:24:59
Starting the Shopify App and Development-Store Setup
He resumes the Talkstore build from domain and initial scaffolding work, then introduces the Shopify Partner Dashboard and a development store as the environment for hosting, testing, and following the app’s development, while its exact eventual behavior remains to be established.
- 0:27:52
Running Independent Tasks in Parallel
He explains a visual marker for tasks that can run together in the development environment, using parallel execution to reduce idle time and move faster when he can coordinate them.
- 0:29:28
Separating Task Preparation from Execution
He demonstrates a command pattern that separates preparing a task from starting it: the agent first produces a detailed implementation prompt, which is then used when execution begins. Simpler tasks may need only brief guidance about requirements or permissions.
- 0:30:55
Using AI to Explore Turning Expertise into Income
Answering an audience question, he says many kinds of expertise may offer income paths but that he cannot give specific advice without knowing the person’s background. He suggests describing one’s skills and experience to an AI assistant and discussing the question in Arabic to explore suitable options, as a starting point rather than a guaranteed formula.
- 0:32:37
Configuring Shopify App Secrets Off-Screen
While configuring the app, he moves off-screen to protect client identifiers, API keys, and secrets, and discusses storing them in environment variables and files excluded from Git.
- 0:41:47
A Qualified First Look at an Automation Tool
The presenter describes an automation tool he had been exploring and postpones a detailed explanation until he understands its complexity better. In his opinion, superficial use may make it seem overhyped, while serious use could materially affect how someone works; this is a personal assessment, not a documented test result.
- 0:43:35
Automatically Advancing Tasks as Dependencies Clear
The presenter shows a workflow where an automated task moves through states such as in progress, review, and done. After one task completed, he observed several blocked tasks move into the to-do list, which he says helps organize time and clarify what should be done next.
- 0:46:46
Coordinating Multiple Agents to Prepare and Execute a Task
The presenter explains an example of a task that may be completed automatically by preparing it and assigning research and oversight to specialized agents. He describes a project-manager role that considers project context, the current week, and progress before execution; the task remains in to-do while being prepared and advances when the start command is given.
- 0:48:55
Verifying That an App Loads Inside the Admin
The presenter discusses how to verify that an app loads inside the admin, asking for the verification steps and where the development command should run. The exchange clarifies that it runs in a terminal, while the exact command and parts of the verification procedure remain unclear in the captions.
- 0:50:29
Setting Up Shopify CLI and a Development Store for Talkstore
A walkthrough of starting a Shopify app-development flow from the Partner Dashboard and CLI, including login, creating a development or test store, and returning to the app development command. The discussion suggests the store may support implementation testing, while some on-screen option details remain unclear in the captions.
Got a question about something in this stream?
Ask in the group