NANO 🍌 BUILT THIS
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 follows development of TalkStore, a proposed AI assistant for Shopify merchants, from shaping a pre-launch waitlist page to testing access to product, order, and theme data and building GraphQL wrappers with personal-data safeguards. Luqman discusses specialized research, build, review, security, and compliance agents; usage limits that constrain parallel work; store-context caching; and conversation persistence. Practical work covers deploying an Astro frontend through Cloudflare, connecting the domain, Supabase, and the waitlist form, and improving social metadata and lightweight analytics. Deployment and DNS pass through repeated errors and pending states before later progress is reported. A code audit surfaces significant authorization, Prisma connection, expired API-version, and GDPR-webhook issues; some fixes are reported, while follow-up remains. Audience discussions also cover video performance, model routing, OpenClaw, code security, freelancing, Shopify basics, and distribution. Final Shopify approval and compliance remain uncertain, as does the measured benefit of some caching work, while the broader discussion argues for beginning marketing and waitlist building before launch without treating the overall build or review as fully finished.
119 moments from the stream
- 3:43:40
Configuring the TalkStore Domain Through Cloudflare
The domain setup was started by pointing it to Cloudflare and reviewing DNS records and proxy status. Activation remained pending, while the root and www domains were added as custom domains, with propagation expected to take some time.
- 3:45:03
Persisting Clarification Turns and Conversation Identity
The discussion covered saving ambiguous requests and clarification questions in conversation history as separate user and assistant rows. It also proposed creating a conversation ID on page load and sending it with every message, because the client was sending the full message array without giving the server a reliable conversation identity.
- 3:50:17
Launch Planning and the Pre-launch Campaign
A discussion of launch sequencing: prioritizing the landing page, teaser video, and distribution campaign while using a possible review period for marketing and waitlist building.
- 3:54:42
Section Generation and Security Reviews
A brief preview of the next section-generation phase, followed by a decision to pause and review completed work through security and compliance sweeps before continuing.
- 3:56:26
Connecting a Waitlist to an Email Platform
A comparison of storing waitlist data in Supabase and forwarding it to an email-publishing platform, with options ranging from manual CSV export to programmatic API or trigger-based synchronization.
- 3:58:09
Why Collect Shopify Store URLs on a Waitlist?
The discussion suggests that a Shopify store URL can help qualify real merchants, inform pre-launch research, select beta users, segment leads, and personalize onboarding. It concludes with a proposal to store both email addresses and store URLs in Supabase.
- 4:02:01
Persisting Chat Messages and Associating Them with Merchants
A review of a persisted message and its metadata, followed by a question about associating records with each merchant as the dataset grows. According to the response shown in the captions, the Shopify store domain is already stored on the shop model from the session value and is not itself presented as a compliance violation.
- 4:06:06
Configuring Supabase Without Exposing Keys
A practical discussion of hiding the screen while handling API credentials, distinguishing public from secret keys, and locating the Supabase project URL needed for a connection. No actual credential values are included.
- 4:10:16
Designing a Supabase Table for a Merchant List
A proposal to create a Supabase table for a merchant list, treating the email address and Shopify store URL as important fields. The captions describe planning, not confirmed creation or testing.
- 4:10:44
Connecting Supabase MCP for a Shopify Liquid Validation Task
The speaker requested installing or updating the Supabase MCP connection for a larger task involving validation of several installable Shopify Liquid files, with four post-build agents to run sequentially. Verification was still in progress, so no completed result is established.
- 4:14:08
Troubleshooting Supabase MCP and Handing Off the Task
Supabase was authenticated through MCP, but the server tools did not immediately appear despite the connection succeeding. Restarting the Claude Code session was suggested, followed by a concise handoff prompt so another agent with MCP access could continue creating the tables.
- 4:19:04
Creating a Supabase Waitlist Table
An MCP-connected agent was used to create a Supabase waitlist table intended to receive email addresses and Shopify store URLs, after which the table appeared in the interface.
- 4:23:06
Connecting and Testing the Waitlist Form
After the table was created, the join-the-waitlist form was updated and connected to it. A sample submission was then entered, followed by a check in Supabase.
- 4:24:17
Improving Waitlist Fields and Validating Shopify URLs
The email-field placeholder was to be simplified, while the store URL should be checked as far as possible for validity; if full verification was impractical, requiring a myshopify.com ending was proposed as a minimum constraint.
- 4:26:02
Reviewing the Shopify Section Templates and Their Purpose
The build review reported fixes involving tag and attribute injection and countdown-timer data attributes. The ten templates were explained as reference recipes that help the model generate more consistent Liquid and reduce theme-editor breakage. They currently live as source files in the app and could later be installed in a development store for visual review.
- 4:27:56
Templates as Reference Blueprints, Not Model Training
The templates were clarified as reference blueprints read by the generation flow, not training in the machine-learning sense. The initial sections were framed as an MVP floor based on commonly requested needs, prompting a discussion about missing lower-funnel surfaces such as product, collection, and cart pages. The response began by noting that Shopify Online Store 2.0 treats these as templates rather than sections, with the fuller explanation continuing beyond these pages.
- 4:31:05
Enhancing Product Pages While Protecting Core Components
Sections such as testimonials can be added alongside a product page’s core sections rather than replacing them. Heavy modification of the main product template is treated as a separate risk category because it could disrupt a critical commerce page, so it is deferred to a stage with appropriate safety rails.
- 4:32:27
Deferring Deep Review to a Structured Code Sweep
Each task is not reviewed exhaustively at this stage because a later pass is planned to sweep security and validate the entire codebase in detail.
- 4:33:03
Limits of Client-Side Shopify Store Verification
Confirming whether a store is real cannot be done fully on the client side without calling Shopify’s API, while existing enforcement mechanisms filter out most junk input.
- 4:34:21
Flagging innerHTML in a Recently Viewed Template
A security check flagged the use of innerHTML in a recently viewed template, identifying it as an item that needed fixing.
Got a question about something in this stream?
Ask in the group