Days From Shopify
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 developing a Shopify app for improving merchants’ visibility in AI answers, including reviews of the reputation and discovery sections, presence-score design, intent-based query ranking, and clearer presentation of answers and research. Luqman argues that measurement should use web-grounded research across multiple engines, while provider quality, cost, and policy-compliant access must be verified; the scoring formula, engine selection, parts of the product architecture, and pricing remain unresolved. The work also covers Market Scout planning, an activity log and dashboard, onboarding, quality checks, and Shopify submission preparation, alongside inconclusive troubleshooting of Shopify and Claude outages and YouTube chat auto-translation. Audience discussions include GEO versus SEO, AI coding-tool limits and pricing, livestreams as shared workspaces, professional networking, and cybersecurity careers, while distinguishing responsible vulnerability disclosure from harmful or unlawful suggestions.
59 moments from the stream
- 0:00:57
Balancing Transparency with Product Confidentiality
Luqman explains why he avoided publishing a detailed breakdown of the app’s engineering and competitor comparisons: in his view, it could make the work easier to copy. He leaves open the possibility of sharing a limited private summary and being more transparent on future projects.
- 0:03:16
Orchestrating Overnight Claude Work Across Dependent Phases
He describes giving Claude rules to run multiple sessions across dependent phases, with later work starting only after an earlier phase produced a pull request and proceeded through merge and deployment. The deployment destination is unclear in the captions.
- 0:05:07
Reviewing Shopify App Sections and Completion Priorities
Luqman reviews the app’s sections and remaining priorities: the merchant catalog storefront, a visibility area divided into reputation and discovery, articles, intelligence features connected to other components, analytics or revenue, settings, and a dashboard redesign that surfaces key parts of the app. His comments on quality and progress are his own review, not documented test results.
- 0:10:02
Scoring Merchant Reputation from AI Answers
An explanation of a system that repeatedly asks a fixed set of questions about a merchant, including legitimacy and refund policies, then derives a score from AI-platform answers. An agent compares each answer with the brand manifesto and identifies signals such as sentiment, sources, and competitors; the speaker said the results had generally been accurate, with minor changes still needed.
- 0:14:10
Reviewing the Visibility and Articles Sections
A brief work update noting that the visibility section still needed some changes and that completing discovery might finish that work. The speaker expected to complete the section that day but remained unsure about finishing the articles section.
- 0:15:56
Clarifying Plan Benefits in the Product UI
A plan-interface review arguing that, because users must choose a plan, the UI should clearly explain what each plan provides. The speaker objected to a “no plan” state and its associated response cap because they did not match the intended product experience.
- 0:16:45
YouTube Live Chat Auto-Translation Problem
A discussion of YouTube automatically translating Arabic live-chat text into English, making it difficult to read and concentrate. The captions show an attempt to inspect live-chat settings and disable native auto-translation, but they do not confirm that the issue was solved.
- 0:24:28
Moving from the Reputation Section to Discovery Improvements
The speaker considers the reputation section provisionally ready for V1, while leaving some details for the final review before submitting the application to Shopify. The next step is to revisit the purpose of discovery from first principles, review the merged work for context, and bring the unfinished section to a comparable level of polish.
- 0:31:49
Designing the Research Presentation Before Backend Wiring
The discussion proposes defining the UI skeleton and the end-to-end research presentation before addressing backend logic and operational cadence. Some decisions and phase seven remain deferred until discovery is complete, with plans to verify details and cadence over time before exploring visual directions and a combined recommendation.
- 0:39:43
Aligning Scout Research with the Reputation Section
The Market Scout section is viewed as a useful compact summary of recent activity. The proposed direction is to study how queries are presented in the reputation section, reuse that presentation style for scout research ordered newest first, and keep the Market Scout report at the top.
- 0:43:40
Displaying a Presence Score and Explaining Its Components
A product-design discussion about improving the discovery section by showing presence-score details beneath each query, similar to the representation-score treatment in reputation. The work also considers card-click behavior, a lane-based experience, and adding a third bar, but the excerpt does not contain the final scoring formula or a complete explanation of the lanes.
- 0:51:32
Ranking Discovery Questions by Value and User Intent
A discussion of how discovery questions vary in value and user intent, with purchase-related intent treated as the most important bottom-of-funnel signal. It also considers letting users add their own queries and refining the overall direction.
- 0:53:45
Observing a Prediction Shift on Polymarket
A brief observation about a sudden weekend shift in a Polymarket market that the speaker associated with expectations around GPT-5.6. The speaker noted movement in a chart but could not find the specific chart and offered no confirmed explanation for the change.
- 0:55:39
Designing the Discovery Score Interface
A proposal to design the frontend before wiring the backend: three indicators would compute a discovery score, while an existing reputation view—with 12 questions, a score, and pill-style labels—serves as the presentation reference.
- 0:59:37
Checking a Shopify Outage During Work
Live troubleshooting of a Shopify access problem: the internet connection appeared healthy while the service was unavailable in multiple places, even though the status page reported normal operation. The speaker tentatively suspected a server outage and planned another check.
- 1:01:47
Checking a Possible Widespread Shopify Outage
After noticing that Shopify was unavailable, he asked an attendee to check independently so he could distinguish a local problem from a broader outage. Seeing the main site, App Store, development stores, and domain affected, he suspected—but did not confirm—a major outage and chose to continue working with limited visibility until service was restored.
- 1:05:56
Reassessing Product Lanes Around Validated Elements
He reconsidered five proposed product lanes, stressing that neither their number nor their definitions were final and that each element needed validation. He viewed topics, blog topics, and possibly discovery as relatively supported, while questioning the value of contribution in a reputation section whose questions remain fixed.
- 1:13:39
Dynamic Discovery vs. Static Reputation
The speaker distinguishes a dynamic discovery area—with changing, archivable, or rotating queries—from a more static reputation area, arguing that the same page structure may not suit both.
- 1:17:53
An AI Visibility Audit Lane
The speaker explores a lane combining brand truth with a detailed audit of factors affecting AI visibility, including flagging concerns and offering recommendations. He also notes overlap between this lane and discovery or content capabilities across product tiers.
- 1:20:54
Showing an AI Answer in a Modal
The speaker proposes letting users open a question and inspect the AI answer in a modal rather than navigating to a separate page.
Got a question about something in this stream?
Ask in the group