Building AEO Scan Funnel System
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
A practical build session centered on preparing Burnish and its AEO scan funnel for Shopify merchants ahead of launch. Luqman reviewed the landing page, product demo, and scan-results interface; reviewed UI issues and requested fixes and alignment changes; and prepared a clearer video-editor handoff, while design polish, scan testing and delivery, email, and ad creatives remained unfinished. He explored offering an instant preview followed by a fuller report, balancing low signup friction against lead qualification because scans have an operating cost, and judging marketing through conversion and acquisition economics rather than assuming success. Technical work included examining crawlers, sitemaps, llms.txt, and robots.txt, alongside inconclusive discussions of privacy, application security, and reliance on Shopify; no comprehensive security test was documented. He also considered Graph Engineering and RAG as possible approaches to managing AI systems, while arguing that adoption should wait for a clear operational need. He examined role-sharing between Codex and Claude, context and usage-limit management, and task decomposition; his changing comparisons of speed and quality remained early impressions, not controlled tests. Audience discussions covered learning by building, freelancing, marketing and sales, e-commerce platform choice, and market validation, with emphasis on fundamentals and honest product claims and reviews. The supported conclusion is that the system was approaching launch and ready for further review—not complete or proven successful—while AEO remained an emerging, uncertain market requiring real-world testing and learning during the first weeks.
147 moments from the stream
- 0:01:53
Organizing the Codex–Claude Workflow and Finishing the Website
He says the website is nearly complete and describes bringing Codex into the implementation workflow while using Claude to help organize the work. He also stresses setting a limit on endless polishing so the project can move forward.
- 0:02:45
Designing a Landing Page for an AEO Scan Funnel
He explains a concise landing page with one purpose: collect a store URL and business email, run an AEO scan, and provide a useful result. He contrasts sending Facebook ad traffic directly to a Shopify listing with routing cold traffic through a lead funnel, then following up by email to encourage an eventual app install.
- 0:05:13
Moving from Funnel Setup to Scan Improvement
He identifies the current stage of the work: the funnel page is live with some revisions remaining, and the next step is improving the scan itself. He frames the scan as the core value deliverable that should give visitors a compelling reason to try the app.
- 0:06:55
Brand Search Visibility and Programmatic SEO Constraints
Responding to a question about analyzing the landing page, he discusses early brand visibility in search results and AI overviews, without presenting it as a completed test. He then explains that Claude can assist with large-scale programmatic SEO content, while cautioning that new sites may face an initial delay or verification period before gaining stable visibility.
- 0:10:51
Writing Clearer Directions for a Product Demo
He works on giving the video editor precise directions so the product-demo steps and intended result are clear, aiming to finish this handoff before returning to the scan implementation.
- 0:13:22
Using an Early Install to Expose a Scanning Bug
He explains that an early app install exposed a bug in the scanning system after recent UX or code changes. The installation exposed a first-use failure, while the reason the user removed the app shortly afterward remains uncertain.
- 0:15:16
Assessing the App’s Price-Market Fit
He questions whether the app’s price point fits merchants serving the Egyptian market and suggests that businesses operating in the United States may evaluate it differently.
- 0:17:48
Exploring AI-Assisted Coding Tools
He opens Codex as part of the workflow and briefly tries another coding interface for the first time, encountering confusion when it responds in an unexpected language. The segment is exploratory and does not establish a final evaluation or a successfully completed task.
- 0:22:08
Assigning AI Agent Roles and Monitoring Usage
A discussion of using one AI agent as a manager and another as an executor, starting aggressively while monitoring token consumption before deciding whether to switch approaches. Some tool names are unclear in the captions.
- 0:24:26
Advice for a Developer New to a Software Company
An audience response first asks what help is actually needed, then suggests that a programming background may make Claude useful in a new software-company role. The advice is qualified by noting that the speaker's own professional experience differs.
- 0:27:26
Delegating Background Music Setup for a Video
An AI agent is asked to use the video's purpose and content, navigate a music tool's settings, and choose a suitable way to generate background music for later review. The tool's identity is uncertain from the captions.
- 0:29:12
Planning the Post-Scan AEO Results
With the landing page considered complete, attention shifts to brainstorming what users should receive after the scan. The proposed approach is to review the previously built end-to-end scan, evaluate content before design, and delegate the task to Codex for parallel work.
- 0:30:31
Preparing a Cohesive Product Demo Package
Organizing materials for a video editor producing a product demo for a Shopify listing, including a prepared voice-over, brand kit, and design system to support a cohesive production workflow.
- 0:31:33
Graph Engineering for Managing AI Systems
The speaker discusses Graph Engineering, which he believes is a relatively new area within computer science and software engineering. In his view, it can help structure AI control across multiple parts of a company, but doing so requires a well-designed graph; he also notes that he has not started implementing it yet.
- 0:35:28
Turning a Bug Diagnosis into an Implementation Handoff for Codex
After identifying three separate issues—most importantly, a copy step that cannot recover from partial completion—the speaker asks for a complete implementation plan and a handoff prompt for Codex, with a separate review step afterward.
- 0:43:05
Testing a Voiceover with Background Music
A practical request to combine a voiceover with a quieter background track so the resulting sound could be reviewed.
- 0:45:29
When Graph Engineering Becomes Worthwhile
A discussion of RAG and graph engineering, with the speaker arguing that adoption should wait for a clear operational need and that hands-on work remains suitable for the current stage.
- 0:47:06
Draft Explainer for Measuring Brand Visibility in AI Answers
A draft marketing voiceover presents Burnish as analyzing AI-engine answers to buyer questions, turning them into a visibility index, suggesting content improvements with approval or automation, and attributing AI visits to orders. It is a marketing draft under review, not evidence of a completed test.
- 0:48:20
Ad Creative Importance and the Limits of AI Video
The speaker argues that creative quality may be decisive for Facebook ad performance, expresses uncertainty about AI-generated video, and considers recording a video personally after further research and script development.
- 0:50:20
Designing a Scan Offer Around Quality, Speed, and Value
Planning for an AEO scan funnel that balances quality, speed, and value, asking for a Shopify store URL and email in exchange for a strong scan. The detailed implementation remains unresolved in this segment.
Got a question about something in this stream?
Ask in the group