Debugging Core Product Engine
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 moving Burnish toward a Shopify-ready V1: reviewing its product engine and value proposition, auditing what is actually wired between the frontend and backend, and refining onboarding plus the Pulse, Mentions, and settings sections around Polaris and Built for Shopify expectations. Luqman discusses making background-agent work visible through a continuous activity feed and connecting research, action, and measurement in a closed loop, alongside demo-state and free-audit funnel ideas; whether these ideas are sufficient, and how attribution and measurement should work, remain unresolved. Practical work includes tracing intermittent HTTP 500 errors and missing CSS registration on the Pulse route, noting an initial Supabase connection problem and caution around resetting onboarding state in the database without establishing a diagnosis, and auditing branches, Git worktrees, and pull requests after mismatched development environments made preserved changes appear lost. Audience questions and side discussions cover context-dependent Shopify app selection, SEO/GEO and product metadata, browser agents and Codex/Claude workflows, broader Git and agent-orchestration guidance, evaluating agent skills, AI-assisted study, and the tradeoff between livestream latency and quality. Other exploratory discussions address Product Hunt’s suitability for Shopify apps, traffic measurement, advertising, and possible discrimination around product launches, as well as practical comparisons of AI-generated storefronts; some model names and versions are inconsistent in the captions, and perceived speed was not formally measured. The stated direction is to finish Burnish’s core, simplify onboarding, and conduct a thorough Shopify compliance review before expanding marketing, while acknowledging that limited development-store testing, expected V1 bugs, migration and performance issues, and several measurement questions still require verification and concrete resolution.
121 moments from the stream
- 0:04:30
Starting the Burnish Core-Engine Review
The session was dedicated to the application itself: understanding its core engine, automation, and value proposition. An initial Supabase connection problem was noted, but no cause or resolution was established here.
- 0:04:52
Designing a Shopify-Native App
The discussion covers using Shopify design resources and Polaris Web Components to reduce guesswork and align the interface with Shopify requirements, followed by plans to review the design and links before examining the app’s behavior more deeply.
- 0:09:42
Showing Daily Progress to Support Retention
The speaker argues that merchants should see ongoing work and measurements while longer-term domain results develop. AI-generated articles are examined as one way to make activity visible and potentially reduce churn, while whether Burnish should add a similar feature remains undecided.
- 0:11:42
Different Roles for Articles and FAQs in SEO and GEO
In the speaker’s analysis, articles tend to benefit SEO more, while FAQs may be more useful for GEO. He also cautions that visible content-generation activity does not necessarily translate into strong GEO scoring or AI visibility.
- 0:12:59
Preserving Project Context in Shared State
The speaker notes that milestone organization became messier as the work expanded, but a shared-state JSON file is used to preserve project context for the AI assistant.
- 0:14:14
Diagnosing a 500 Error Through an MCP Browser Session
The captions describe an MCP session that lets Claude control the browser and inspect developer tools, network activity, design, and screenshots, while the application was still returning a 500 error at that point.
- 0:15:05
Reviewing Application Readiness Before a Shopify Audit
Luqman discusses reviewing the application end to end, assessing what remains, considering features that may help reduce churn, and preparing for a major Shopify compliance-checklist audit. He also mentions worktree overlap during preparation.
- 0:20:41
Diagnosing Broken Copy and Paste in Logitech G Hub
The captions describe a problem appearing after a Logitech G Hub update: the mouse side buttons were mapped to copy and paste, but paste appeared to send Shift+V. The mapping and a screenshot were reviewed and a reset was attempted, followed by an indication that copy and paste worked, though the root cause was not clearly established.
- 0:26:42
Requiring a Debugging Agent to Verify the 500 Error Is Gone
Luqman sets a clear completion criterion for the agent: apply the change, inspect the logs, and verify that the response is no longer 500 before reporting the job complete, continuing diagnosis until then.
- 0:30:20
Reviewing the Application’s Value Proposition and Customer Segments
The captions describe asking an assistant to review market documents and examine the Burnish application inside Shopify from a value-proposition perspective rather than focusing only on its code, then revisit customer segments, differentiating wedges, and how the current features work. Competitor names and private strategic details are omitted.
- 0:32:13
Keeping the Browser Session Inside the Correct MCP Group
When Chrome was opened outside the designated MCP group, Luqman asks that the orchestrator be told the browser session must remain inside that group, illustrating the importance of isolating agent-session context.
- 0:33:18
Correcting Claude Mid-Session
Luqman explains that a Claude command can alert a standing sub-agent to a mistake while work continues, allowing it to notify the orchestrator and prompt an immediate correction without ending the session.
- 0:33:59
Auditing Burnish’s Value Beyond Bug Fixes
The discussion proposes auditing Burnish against its documents, competitive wedge, and value proposition to find omissions or needed additions. The goal is for merchants to perceive ongoing background work, while whether the current implementation is sufficient still needs evaluation.
- 0:37:04
Shopify-Native Settings Design
The work covers settings pages using a Shopify-native design approach, viewed as practical and aligned with the platform’s expectations, while fixing bugs encountered during interface refinement when possible.
- 0:38:04
Intermittent 500 Error After Refresh
A 500 error appeared after the first hard refresh, reload did not resolve it, and a second hard refresh worked while other pages remained available. The logs were to be checked for a cause and a tangible fix, with no diagnosis yet established.
- 0:39:14
Limits of Testing on a Small Development Store
Luqman discusses the difficulty of inferring app behavior for stores with much larger catalogs from a limited development store. Although safeguards were considered, not every scenario can be observed directly, so he expects V1 bugs and sees customer support as necessary.
- 0:42:00
Making Background Work Visible to Merchants
The discussion argues that showing only a score or completed progress may make a merchant think the app’s value is exhausted and remove it. The proposed direction is to surface background-agent activity so ongoing value is visible, while acknowledging that the idea still needs analysis.
- 0:43:55
Recovering and Ordering Design Requirements
Luqman asks to revisit the earlier app-design requirements, including the self-score system and the section order beginning with Settings and Pulse, and to incorporate the newly added Shopify design MCP information to identify where it could help.
- 0:45:38
Reviewing Pulse with Shopify and Polaris Skills
Luqman asks for the Pulse section to be evaluated with Shopify and Polaris skills plus Shopify Dev MCP, with potential improvements explained before implementation. He also asks whether direct access to Shopify documentation and APIs could reduce guesswork and support the review.
- 0:48:55
Finishing the Product Before Shopify Compliance Review
Luqman describes a temporary decision to focus on completing Burnish first, then audit the app against a Shopify compliance checklist before expanding attention to other activities.
Got a question about something in this stream?
Ask in the group