Shopify App Submission
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 July 7, 2026 session follows preparation of a Shopify app focused on improving merchant visibility through AI. The speaker walks through brand-context onboarding, discovery queries, product-data optimization, article and image generation, attribution, integrations, and a concept for progressively enabling automated publishing as merchant trust develops. Practical work centers on reinstalling and checking post-install behavior, clearly presenting pricing, trials, and usage limits, and preparing an English screencast and app listing. The discussion concludes that critical failures and broken workflows—not every remaining polish item—are the immediate review priority: issues appeared around generated-output persistence and smart posting, while some scheduled automation, export functionality, and product areas remained unfinished or untested. The stream also covers technical debt, isolating and verifying one task at a time, managing coding-agent context, and delegating implementation to fresh sessions, alongside qualified opinions about Codex and Claude rather than a definitive comparison. Audience questions address learning to build software with AI and an unclear VS Code run problem; the speaker stresses that diagnosis requires enough concrete context. On the business side, he sees growing competition in Shopify’s AEO category and expects marketing, service quality, and premium positioning to matter, while leaving room to adjust pricing or product positioning in response to market metrics. His historical expectation at the time was a Shopify review response in roughly two to four weeks, possibly five, not a guaranteed timeline.
49 moments from the stream
- 0:01:05
Bug Risks During Shopify App Review
The speaker explains that submission readiness is not only about Shopify policy compliance: a reviewer may test the app and find bugs that lead to rejection, especially when critical, while smaller issues may be returned for correction.
- 0:04:51
Growing Competition in Shopify’s AEO App Market
In the July 7, 2026 session, the speaker describes Shopify’s AEO app category as a young market attracting new competitors frequently. He believes his app covers a broad portion of the category and expects marketing to become the main differentiator after launch.
- 0:06:37
Balancing Premium Pricing with Marketing Metrics
The speaker discusses pricing a costly service as a premium offering relative to competitors, expecting effects on customer acquisition cost and other marketing metrics, with possible repositioning based on marketing results.
- 0:08:53
Preparing a Screencast for Shopify App Reviewers
The speaker explains that the submission requires a short recorded app presentation, proposing Loom to demonstrate the core functionality and explain complex parts so reviewers can evaluate the app.
- 0:10:29
Using a Work Log to Measure Progress
The speaker explains that revisiting recorded work from earlier periods helps him see what happened and roughly measure progress.
- 0:13:18
Reviews and Acceptance on the Shopify Platform
The speaker views reviews as a highly important success metric for a Shopify app, while treating platform acceptance and the removal of obvious bugs as the more immediate priorities.
- 0:15:56
Balancing a Submission Deadline with Technical Debt
The speaker explains that rushing software under a deadline accumulates technical debt whose effects return later. In the current submission push, he prioritizes obvious and critical bugs that could cause Shopify to reject the app, while deferring less urgent polish.
- 0:17:24
Operational Readiness and Service Positioning After Launch
The speaker outlines work remaining after the core features: refining design and UX, preparing marketing and email, building support, maintaining a changelog and help center, and offering customer meetings. He presents these as part of a premium service position based on capabilities and service quality, in his view.
- 0:21:27
Why Planning Can Use More Tokens Than Implementation
The speaker explains that producing specifications or an implementation plan can sometimes consume more tokens than the build itself because the agent must first explore the codebase and inspect many files, while an implementation agent may start from a bounded specification. The result still depends on the task.
- 0:22:46
Pricing an AI-Automated Application
The speaker ties pricing to the cost of automated work that begins after sign-up, including creating a merchant profile, generating queries, and periodically requesting answers from several AI platforms. He also explains that trial periods let users assess the value before continuing, with availability varying by tier.
- 0:26:06
Testing Installation and Manifesto Generation Before Shopify Review
The speaker reinstalls the app and follows an onboarding stage that inspects the catalog, products, and brand name to generate a manifesto. He describes this as essential to rendering the application, then opens the broader feature set for verification and debugging ahead of a Shopify reviewer going through the flow.
- 0:28:58
When Coding Agents Cannot Resolve a Seemingly Simple Issue
The speaker expresses frustration that an issue persists despite clear instructions, multiple coding agents, and several ways of framing the request. The example shows that switching tools or prompting angles does not guarantee a solution when an agent cannot understand or deliver the requested fix.
- 0:30:24
Executing and Verifying One Task at a Time
The speaker proposes narrowing the work to one task at a time, applying the change, restarting the app, and verifying whether the requested change actually landed.
- 0:32:30
How Technical Debt Complicates Simple Tasks
The speaker discusses simple, clearly described changes still failing and attributes the difficulty to accumulated technical debt and increasingly tangled code after repeated edits and merges.
- 0:33:48
Compacting an AI Coding Session's Context
The discussion describes compacting or clearing an AI coding session instead of always replacing it, favoring compaction because it can reduce accumulated context while retaining important instructions and information.
- 0:35:53
Delegating Work to Fresh-Context Sessions
The speaker describes using a primary orchestrating session to discuss bugs and root causes, then spawning fresh-context sessions to perform the work instead of asking the long, context-heavy session to implement it directly.
- 0:38:38
Testing Automated Content Generation and Smart Posting
The speaker tests generating an article or blog post with images, explaining that the feature is intended to scale content production for search visibility and that usage limits vary by tier. A “smart posting” option is meant to schedule and publish posts automatically, but a bug is noticed during the test, so successful operation is not established.
- 0:40:28
Functional Bugs and Shopify App Rejection Risk
According to the speaker, the main Shopify review risk is broken functionality, such as generated output disappearing after a refresh or page change, and whether a feature works matters more to review than the polish of its generated copy.
- 0:41:32
Merchant Content Generation and Search Optimization Workflow
A workflow derives topics from discovery queries and the merchant catalog, supports content and image generation, and includes SEO settings and an FAQ section, with preview and regeneration controls. Automatic generation and publishing in “Smart Pilot” were explicitly described as not yet tested.
- 0:46:56
Shopify Review for Critical Bugs
According to the speaker, Shopify reviewers inspect the app for bugs, and a critical failure can lead to rejection; submission readiness therefore centers on clearing blocking defects.
Got a question about something in this stream?
Ask in the group