Burnishing the UI
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 refining Burnish’s landing page so it clearly explains GEO and its value to Shopify merchants, while turning the page into an acquisition funnel that offers a free scan rather than demanding an immediate subscription. Reviews cover the hero, pricing, product explanation, calls to action, and mobile experience, alongside unfinished visual experiments involving WebGL, GSAP, an interactive logo, and a light-reactive grid; several results remained short of the intended design. The speaker argues that clear messaging, a provisional V1 focus on GEO, and one ideal customer profile matter more than endless polish, while acknowledging that scope, pricing, and willingness-to-pay assumptions still require validation. The discussion also addresses Shopify review risks and the need to begin marketing and market validation before approval, since building alone does not ensure merchant acquisition. His Codex and Claude comparisons are explicitly personal: reusable skills and critique sessions may improve the starting point, but they do not replace a clear vision, repeated review, or early checks of repository, branch, and implementation plans. In audience discussions, he advises beginners to build a small personal project with Codex and also covers WebGL, GSAP, usage limits, agents and automation, and the economics of software and dropshipping, presenting tool comparisons and market forecasts as tentative opinions rather than proven findings.
71 moments from the stream
- 1:31:46
Conflicting Edits Between AI Coding Tools
The speaker expresses confusion that Claude appeared to remove changes made by Codex, despite saying that he had not requested any change to be executed.
- 1:36:44
Planning a Scroll-Driven Pricing and Feature Comparison
Hero-section changes were deferred while a concept was explored for combining pricing tiers with the full feature comparison and revealing tier progression during scrolling. A similar effect on an external site whose name is unclear was to be studied before producing an implementation plan; these captions do not establish that it was implemented.
- 1:41:08
Planning a Refactor and Inspecting Web Interfaces with Codex
The discussion began with a proposed full refactor that needed planning, then considered using Codex to inspect a reference website and analyze how a particular interaction was built. This was compared with using Playwright MCP with Claude, while noting that the speaker had not tried that setup with Codex and that the tools may serve somewhat different purposes.
- 1:43:14
Reviewing a UI Refactor Plan Before Implementation
An AI-assisted critique workflow for rereading a plan to refactor an entire UI section, finding gaps before implementation, having a sub-agent review the revised plan, and recording the final version in Markdown. The speaker said critique sessions can help, but their value still depends on having a clear underlying idea, and expressed the opinion that some stronger tools consume tokens too quickly to remain practical for heavy workloads.
- 1:50:27
Visually Communicating Answer Absence
A design exploration focused on making visitors understand within three seconds that the problem is an absent answer, shown from the shopper’s point of view. Proposed visual refinements included improving a 3D logo, adding a drop-down effect, and thinning a green circle; the closing question about the answer’s physical form is unclear in the captions.
- 1:54:58
Iterative UI Refinement Through Design Feedback
A practical review of header spacing, clickability of the bar and CTA, and the logo treatment. The direction evolved from adjusting a logically angled shadow to replacing it with a subtle green glow, followed by verification that some requested changes were still absent.
- 1:57:13
Anticipated Growth of Answer and Generative Engine Optimization
An explanation compares AEO and GEO with the older SEO field and expresses the speaker's belief that interest and demand for GEO could grow strongly over the following two years. Shopify is presented as the application context rather than a new independent platform.
- 2:01:56
Balancing Text and Visuals on a Capabilities Page
Guidance to revisit prior documents, earlier brainstorming, and the current page before reshaping it, with the goal of balancing text and visuals while communicating at least five strong capabilities the product can offer Shopify stores.
- 2:03:25
Assessing Competition and Market Gaps in Shopify Apps
The speaker contrasts basic Shopify tools with enterprise platforms and sees room for more capable AI-assisted catalog and merchandising solutions. He stresses that competition is healthy but demands deep technical understanding and market research, while presenting accelerated demand ahead of Q4 2026 as his forecast rather than a certainty.
- 2:09:30
Rethinking the Pricing Page Design
The discussion shifts from plan review to examining the desired pricing-page design and available design capacity. The proposed layout keeps a feature comparison at the top and the plans below, while noting that plan cards do not need to be interactive; some surrounding details are unclear in the captions.
- 2:11:33
Shopify App Launch Risks and Go-to-Market Strategy
The speaker explains that building an app alone does not ensure success: teams must account for engineering risk, possible rejection and review cycles lasting weeks, and a strong go-to-market strategy. He identifies inbound and outbound sales, funnels, and marketing as necessary merchant-acquisition work rather than assuming users will discover the app on their own.
- 2:13:33
Don’t Wait for App Approval to Start Marketing
The speaker revisited a plan to build other apps while waiting for Shopify review and described it as a potential trap. Even with checklists and pre-validation, rejection remains possible, while a strong product still needs marketing expertise and effort before traction can make growth more self-sustaining.
- 2:16:31
Designing a Coming-Soon App Page
The speaker explained that the app would not yet be installable during the first two phases. He asked for the page to communicate “coming soon” at first glance and for the pricing call to action to match that pre-launch state.
- 2:17:44
Marketing Investment and Burn-Rate Risk
The speaker discussed burn rate as a way to plan how capital is spent on marketing in pursuit of future recurring returns. He stressed that spending requires a calculated plan and does not guarantee success; the practical bottleneck is often investment and customer reach, not merely building the product.
- 2:19:34
Vibe Coding Does Not Solve Go-to-Market
The speaker criticized producing many vibe-coded apps without shipping or marketing them, arguing that reaching customers can be harder than making the product. He added that truly uncontested ideas are difficult to find, but entering an existing market is valid and competition can be healthy.
- 2:24:28
Reading Coding-Model Benchmarks Carefully
The speaker compared GPT, Claude, and Codex using a benchmark page and his own experience. He preferred Claude for planning, specifications, and code quality while believing GPT might be stronger overall, but explicitly said he did not fully understand some metrics, making this a personal and inconclusive reading of the results.
- 2:27:05
Cost Versus Quality in AI Coding Tools
The speaker preferred Claude for coding work but said its higher cost limits practical use and leads him to rely more on Codex. This is his personal quality-and-affordability tradeoff, with account and plan details omitted.
- 2:34:51
Shopify App Review Feedback Workflow Changes
The discussion says app-review feedback moved from email to the Partner Dashboard and mentions requirements involving theme app extensions and the app-store listing. The speaker worries that a rejection may send a submission back into the queue, while explicitly acknowledging that this interpretation could be wrong.
- 2:39:43
Aligning Marketing and Pricing With Product Margins
The speaker explains that marketing needs differ between B2C and B2B products and that gross margins are an important input. He also prefers a strong first release followed by narrower improvements instead of sweeping redesigns, and responds positively to early-access pricing.
- 2:43:58
Reducing Hero Copy and Improving the CTA Banner
In a landing-page review, the hero headline and subheadline are considered sound, but the supporting copy is judged too long. The “scan now, install later” banner should become more visually appealing, with an appropriate background effect also considered.
Got a question about something in this stream?
Ask in the group