ALMOST 70% BUILT
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 documents the practical development of Burnish, a product beginning on Shopify and exploring how stores can improve their visibility in AI answers and platforms through GEO. Much of the work centers on the website and product message: clarifying the problem, solution, and customer outcome; structuring the homepage and pricing page; routing “Scan My Store” calls to action consistently; and refining cards, contrast, mobile layouts, scroll interactions, and a floating 3D logo. Visual reviews repeatedly led to revisions or removal of immersive effects when they distracted from the product, alongside recognition that excessive polish could delay shipping. The pricing experience advanced, but the homepage and especially the scan flow still required substantial frontend and backend work. The proposed scan collects a native Shopify store address and business email, then leads toward a deeper AI-visibility report. Important questions remained unresolved, including audit cost, the instant result or teaser, brand-name detection, usage limits, protection of shared public infrastructure, report-email delivery, and the terms of a refundable reservation. The discussion emphasized honest scarcity indicators and responsible marketing claims. Lighthouse and browser inspection provided preliminary performance signals, but measurements from an older site were not treated as final evidence for the heavier new version; screenshot and animation problems also remained under investigation. For implementation, Luqman compares Claude and Codex and assigns design, backend, migration, and audit work according to their perceived strengths. The workflow uses separated specifications, milestones, dependencies, a Command Center, coding agents, audits, and human visual review. His practical conclusion is that specific instructions, clean context handoffs, and deliberate sequential work are often more manageable than too many simultaneous sessions. The stream does not establish that every migration, audit, or automated workflow was completed successfully. The broader discussion turns to go-to-market work: validating demand before launch, building a list and organic distribution, warming an email domain, and testing advertising or direct sales in phases. Luqman argues that market response—not personal enthusiasm—is the real test of an idea, and that a strong product still needs marketing and distribution. He presents GEO and AEO as emerging relatives of SEO; based on his reading of trends, he observed growing interest during 2025 and predicted further growth by September 2026, explicitly as an opinion rather than confirmed market evidence. Audience questions also cover whether non-developers can build with AI, learning by doing, Micro-SaaS and B2B opportunities, model and hosting choices, and choosing Telegram or Discord for an Arabic-speaking community. Overall, this is an unfinished build-and-validation journey rather than a completed launch, with product viability and growth channels still awaiting real market evidence.
163 moments from the stream
- 1:41:02
Snapping a Logo into a Circle on Scroll
Defines a scroll interaction where the logo moves beyond an earlier section into a later one, is sized and perfectly centered inside a circle, and receives a snap effect matching an existing interaction. Some section names are unclear in the captions.
- 1:43:01
Consulting Product Documents to Clarify Backend Requirements
Suggests returning to the manifesto and other documents about the Scan Store section to clarify what the backend is meant to do, emphasizing that the question extends beyond the UI.
- 1:52:23
Reviewing Card Effects and Scroll Speed
He reviews the implementation direction and specifies card fixes: reveal effects in sequence, slow the overly sensitive scrolling behavior, and add another effect. He also explains that precise requirements are easier for him to formulate in writing than by voice.
- 1:56:59
A Scroll-Reactive Graph for the Measure-and-Improve Cycle
He proposes adding a graph to the e-commerce index card and making it react to scrolling, while enlarging the header and removing the subheader. The graph should advance through measure, fix, prove, and remeasure, with each connecting line responding to one scroll step.
- 1:59:17
Reviewing Homepage Progress and Snap Effects
He reviews the remaining homepage work, including an exit transition and further refinements. He considers the pricing page complete and professional, then checks another snap effect and finds it promising but still in need of minor adjustment.
- 2:00:34
Keeping the Logo Fixed After It Snaps to Center
He specifies that once the logo snaps to the center of the section, it should remain fixed and stop reacting to scrolling, changing behavior only after the viewer scrolls beyond the section under the current setup.
- 2:01:10
Building a Landing Page Without a Web Development Background
A practical discussion of refining a landing page by fixing logo movement during scrolling, section sizing, and visual effects. The speaker says directing an agent is harder without web-development knowledge, but argues these tools can still help non-developers ship a good product, while acknowledging that technical experience enables better results and more precise guidance.
- 2:07:32
Creating a Project Marketing Video with Remotion and Codex
An explanation of experimenting with Remotion inside Codex for editing and generating a marketing video after an agent reads and understands a project manifesto. The speaker mentions organizing work with compositions and sequences, notes a small learning curve, and qualifies that he has not explored the tool deeply yet.
- 2:11:35
From Proving the App on Shopify to an Independent Platform
Shopify is presented as an initial proof stage; if the product later evolves into an independent platform, the website will need a command-center interface and broader frontend development. The current website is described not as the final product, but as a small step where a merchant scans a store and provides an email. Future expansion remains conditional on the Shopify app’s results and marketing, with explicit uncertainty about whether the app will perform well or progress slowly.
- 2:14:12
Debugging UI Animations Through Precise Feedback
The session iterates on cards and scroll-driven animations. Some attempts improve centering while introducing regressions, such as an icon moving with the page or a section disappearing before its content is populated. Since frontend work is outside the speaker’s specialty, the workflow relies on describing visible behavior precisely to the coding agent and reviewing each result iteratively.
- 2:16:14
Handing Off Context When a Coding Session Slows Down
The speaker observes that typing and responses seem slower as the coding session grows, then proposes starting fresh and requesting a handoff file that carries the working context forward. This is a practical session observation, not a controlled performance test.
- 2:17:01
Planning Ahead for an AI-Assisted Portfolio Build
In an audience discussion, the portfolio is clarified as taking two days after advance preparation of what to build. The exchange also notes that thinking through animations and designing them mentally can consume substantial time. The coding tool’s name is unclear in the captions, so it is not asserted as a project identity.
- 2:21:51
Reviewing a Website Interface for Conversion
He asks Claude to restate its understanding first and reviews the findings; he initially considers screenshots for unclear points, then sets them aside because they can cause problems, before requesting a handoff prompt for a new session. The review covers logo sizing, the header background, typing-animation speed, cards, and counters, while emphasizing that visual polish should help inbound traffic convert rather than merely showcase the site.
- 2:28:21
Planning an Architectural Migration and Review Workflow
He discusses an important UI migration from React to another shop-related technology whose identity is unclear in the captions, noting that it has architectural consequences across multiple areas. After weighing which coding tools fit the work, he decides to use Codex for implementation and Claude for the audit.
- 2:31:40
Splitting Implementation and Auditing Between Coding Agents
Luqman proposes having Codex complete the milestone, then using an audit command in the command center with Claude to inspect the whole milestone and address any issues it finds. This is a workflow preference, not evidence of a completed successful audit.
- 2:32:56
Visually Verifying Interface Adjustments
While adjusting an element to fit an inner circle, he notes that the exact numerical changes are unknown and asks whether the agent can take screenshots to verify its own work, providing a screenshot of the current result.
- 2:34:39
Preparing Tasks by Size Before Running Agents
He describes a workflow that prepares separate prompts for large and medium tasks before distributing them across agents to complete a milestone. He avoids fully automating the current migration because it requires additional research and investigation, and also considers routing work by task intensity without resolving the unclear model or tool names in the captions.
- 2:38:40
Focus and Marketing in Micro-SaaS
He argues that a Micro-SaaS product can focus on one simple problem that the market needs solved, but a strong product alone is insufficient: marketing and customer outreach remain central challenges for both small and larger SaaS products.
- 2:39:53
Designing a 3D Element Transition
He explores a visual change that would require careful additional coding: as the page scrolls into the working-loop section, he wants to isolate the inner square of a 3D element and dim its outer green circle. The idea is still being formulated, with no claim that it was completed.
- 2:41:41
Refining an Animated Logo with AI Assistance
The speaker iteratively centers a logo inside an animated loop, fades the outer circle during the transition, then adjusts the logo’s scale and components. He notes that the idea is simple in principle but precise visual implementation is difficult because the assistant sometimes guesses from screenshots. He also discusses, with explicit uncertainty, whether the reconstructed asset involves SVG, a 3D file, or WebGL.
Got a question about something in this stream?
Ask in the group