SPEEDRUNNING TALKSTORE
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 centers on building TalkStore, envisioned as a Shopify agent that can take store actions rather than merely return text. Luqman tests the app incrementally, from fixing product access, enriching data, and preparing human test checklists to creating metaobjects and trying prebuilt storefront blocks after a write_themes exemption was rejected. The work exposes an unresolved architectural problem: deep links do not automatically bind a metaobject entry to a theme block, while alternatives involving an app embed, an app proxy, and how to decompose their implementation remain under consideration without a clear final decision. In one inspection, the feature grid did not appear even though no console errors were reported; in a separate post-deployment test, some UI content still failed to render as expected. He also discusses structuring debugging as its own milestone with specialized agents, using Command Center plus parallel sessions and agents to accelerate work, and exploring a multi-model strategy for AI-tool usage limits, while deferring UI/UX refinement until core logic is validated. Project planning includes reviewing task dependencies, blockers, and priorities, as well as weighing early submission against further polish amid uncertain Shopify review and opportunity cost. Audience discussions cover livestreaming as a focus and progress log, cautiously building a side project, validating demand before development through landing pages and early-commitment signals, and the speaker’s view that clear vision, strong goals, and self-confidence support commitment. A future commerce-intelligence milestone could answer merchant questions about sales metrics, while product scope, the post-launch workflow, and workable paths around Shopify’s constraints remain open.
47 moments from the stream
- 0:51:57
Creating a Hero Banner Entry with Shopify Metaobjects
A practical walkthrough of locating the metaobject definitions, opening the hero banner, filling a seasonal collection entry, saving it, and checking the generated handle. He also notes that some fields cannot be changed and that the workflow is still being understood during implementation.
- 0:53:21
Market Validation Before Building
He points to a future idea centered on validating the market before starting to build, without enough detail on the method in this page.
- 0:54:11
Speeding Up Work with Parallel Sessions and Agents
He describes a fast workflow that runs multiple terminal sessions and agents in parallel to complete many tasks quickly, without exposing private usage figures.
- 0:57:47
Exploring the Section and Handle Flow
He traces the workflow from copying a handle to adding a section and selecting a hero banner, while making clear that he is still learning how the pieces connect before settling on the flow.
- 0:59:02
Defining TalkStore Beyond Page-Builder Competition
He questions whether the current direction turns TalkStore into a page-builder competitor, rejects that positioning as outside the app’s intended goal, and notes that competing only on price is not the desired path. He closes with an open question about the workflow after the product is completed and launched.
- 1:00:41
Architecture of an AI Agent for Shopify Storefront Editing
A proposed flow accepts a request such as creating a Summer 2026 collection banner, classifies it as a storefront change, requests confirmation, and executes it. Visual templates, metaobjects, content fields, and deep links guide the task while keeping it away from settings.
- 1:02:47
Prebuilt Blocks as an Alternative to Free-Form Theme Editing
While testing an FAQ section about shipping, returns, and sizing, Luqman explains that his original vision was a conversational agent enabling merchants to make simple theme changes. After that approach was rejected, he considers predefined primitive blocks as a possible replacement, while stressing that implementation is difficult and the alternative is imperfect.
- 1:08:38
Debugging a Storefront Banner’s Metaobject Binding
The test shows that the agent created and populated a metaobject with a title and CTA, but its link opened an empty hero-banner block in the theme editor. The debugging checks block settings, fixes a required path, and makes the tool’s returned handle more prominent so the agent does not miss it; repeated tests show the binding still failing.
- 1:23:39
Diagnosing a Shopify Block That Does Not Render
Luqman revisits a deep-link task and identifies the current issue: the handle is not being added automatically to the block, so it does not render as intended in Shopify. He proposes reviewing the task and codebase again and using research, exploration, and builder agents, while noting that debugging demands more patience than the initial build.
- 1:26:19
Shipping Before Polishing Under Review Uncertainty
Luqman discusses submitting the app before spending weeks polishing it, because Shopify approval is uncertain and he estimates that review may take several weeks. He considers the idea promising but time-intensive, so he favors shipping first and polishing further if the app is accepted, while accounting for opportunity cost.
- 1:30:54
Architectural Limits of Linking a Shopify Block to a Metaobject Entry
The discussion concluded that the problem was architectural rather than something prompt refinement could solve: the deep link could not prefill block settings, there was no clear API for setting them without theme changes, and the metaobject picker required a hard-coded numeric app ID. Testing the proposed flow then showed the block reporting no entry even though an entry with a handle existed, so the option was judged non-viable in its current form.
- 1:32:23
The Case for a Dedicated Debugging Agent
The discussion noted that a multi-agent build process can still miss small issues, motivating a future dedicated debugging agent to review defects that slip past the other agents after the application is completed.
- 1:39:47
Reviewing Task Dependencies, Blockers, and Priorities
A milestone review began after its tasks appeared to have no dependencies or blockers. The requested work was to move tasks into the blocked section where appropriate, add dependencies, and double-check task priorities.
- 1:51:06
Testing a UI Content-Rendering Issue After Deployment
Luqman returns to a debugging issue, deploys the app to test it, and observes that the banner content should appear while other elements still do not render as expected, suggesting the problem is deeper than the initial fix.
- 1:57:47
Commerce Intelligence for Sales Questions Inside Shopify
Luqman explains a milestone that gives the app access to Shopify orders and analytics so merchants can ask about sales, conversion rate, average order value, and other store metrics. He describes it as a distinct milestone with a relatively contained scope.
- 2:00:14
Turning Debugging into a Structured Workflow
Luqman says a clear, organized command center greatly improves execution speed, but his debugging process has not yet been designed well. He considers making debugging its own milestone so work can proceed more consistently.
- 2:07:36
An Action-Taking Agent Inside Shopify
The speaker describes TalkStore as a Shopify app where merchants converse with an agent that can control the store and take actions, rather than only return text. The claimed lack of such action-taking agents is presented as his own market observation.
- 2:08:40
Using Command Center to Accelerate Workflows
The speaker describes Command Center as a central part of his workflow and credits it with helping him move faster and more efficiently. He also considers making a standalone reference video for recurring questions about it.
- 2:10:17
Testing Demand Before Building the App
The speaker proposes pre-build market validation: generate several ideas, create a landing page for each, measure early reservations or commitments through ads, and compare conversion and demand. The weaker ideas are then dropped in favor of the one showing the strongest signal, without treating the expected outcome as guaranteed.
- 2:13:20
Why Build in Public Through Livestreams
The speaker says the channel is not primarily aimed at views or direct monetization. Livestreaming helps him stay focused while building, while organic viewers may learn from observing real work rather than only hearing theoretical tool comparisons.
Got a question about something in this stream?
Ask in the group