Building Intelligence + Manifesto
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 hands-on review of Burnish before V1: auditing the first-time-user experience, documenting bugs in product-readiness states, publishing, links, and image alt text, and testing autopilot batches, timing, loading, and pause behavior. It also traces failures in manifesto generation and PDF downloading and a missing FAQ presentation, using a workflow of visual verification, issue logging, root-cause research, separate implementation handoffs, and incremental merging and deployment. The work remained unfinished: autopilot, the Intelligence page, and downstream manifesto integration still required testing and polish, while several bug causes were unresolved. The discussion also develops an exploratory Telegram-based virtual office for collaboration and project progress, including prototypes, character movement, and collisions, although its lasting purpose, implementation scope, and privacy model remained open questions. Audience exchanges cover launching mobile apps, choosing B2B or B2C and web or mobile, competitor research, unit economics, and marketing, alongside qualified opinions about agentic coding tools, AI models, infrastructure, and token pricing. The speaker’s recurring view is that workflow fit matters more than broad model claims and that building a product is only the start of market testing, marketing, and sustained execution.
82 moments from the stream
- 0:03:15
Shopify App Development Preview Constraints
The speaker explains that his Shopify workflow did not allow multiple environments or app areas to be active and previewed in parallel. Trying additional development stores did not solve it, so he had to work on one part at a time.
- 0:04:39
An Idea for Mutual Community Collaboration
The speaker briefly outlines an early idea for a shared activity among an engaged community whose members learn from one another, potentially extending both within and beyond Telegram, without defining its final form.
- 0:06:44
A Visual QA Workflow for Documenting Bugs Before Fixing Them
The speaker proposes exploring an app as a first-time user, checking its flows and possible variations, and recording each issue in a separate file. An orchestrator agent then researches likely causes and suggests solution directions without changing code, leaving implementation to a later session.
- 0:08:21
Delegating Long Tasks to AI and Evaluating Models Carefully
The speaker discusses giving a well-scoped, substantial task to an AI agent for an extended run, such as research or deep preparation. Regarding MiniMax, he explicitly says he has not used it himself and that his reservation comes from another developer’s reported experience, while emphasizing that what matters is whether the model works well for the user’s workflow.
- 0:16:03
Questions for Launching a First Mobile App
A discussion with a developer about a first Google Play app, including questions about what the app does and whether it has a market-entry plan rather than simply being released and abandoned for the next project. Luqman expressed the opinion that B2C and B2B software models can offer strong margins while also facing intense competition.
- 0:17:44
Iterative Debugging and Manifesto Integration
An iterative pass reviewing changes and fixing unspecified elements, including a decision to remove one section and place the manifesto there. The process involved regeneration, trying modifications, checking results, and deferring nonessential features to focus on the immediate issue; the page ends as a broader debugging explanation begins.
- 0:20:45
Finding Bugs Before Users Do
A reminder to review an application's different flows and states so problems are found early, while acknowledging that testing cannot catch every bug.
- 0:22:29
Positioning a Construction-Work Management App
A discussion of a product intended to simplify work for managers and workers in the Gulf construction sector, including the personal view that a business-focused starting point may be stronger and a question about choosing mobile over a web app.
- 0:25:23
Image Alt Text Fails to Publish
During a QA review, publishing product changes was observed to apply the other fields but not the image alt text, followed by a request to verify title and description publishing as well.
- 0:27:11
Correcting the Product-Title Link Target
A UI issue was identified where a product title in the AI Ready tab opens change review, while it should lead to the Shopify product page consistently with the Products tab.
- 0:28:57
Competition and Platform Choice for Construction Software
A discussion of construction tools aimed mainly at enterprises and a possible opportunity to serve smaller companies and workers through mobile. A web or desktop competitor was requested to clarify the concept and market; claims about competition and profitability remained preliminary, unverified opinions.
- 0:32:12
Why Competitor Teardowns Are Useful
A recommendation to examine competitors and conduct product teardowns as a useful exercise for the project owner.
- 0:38:37
Fixing Misleading Post-Publish Status
A bug causes a product to appear optimized immediately after publishing even when not all fields were selected, before the status changes on refresh. The discussion proposes basing the displayed state on the total score and representing live and pending items more accurately.
- 0:42:01
Evaluating Phone-Based Construction-Site Capture
An exploratory discussion about construction-project software asks whether a phone camera could replace specialized hardware, whether it would provide sufficient quality, and whether AI image processing would be needed for additional capabilities.
- 0:44:33
Building in Public from Development to Marketing
The channel is described as a public record of the full journey, extending beyond AI-assisted coding to building, shipping, and marketing a product while discussing vibe coding and the models involved.
- 0:45:48
An Arabic Community for Vibe Coding and AI
Viewers are invited to join a Telegram community for Arabic discussions about vibe coding and AI.
- 0:46:33
Editing Published Fields and Recomputing Readiness
The product-details design shows the previous field beside the version published by Burnish and would allow the published version to be edited. How edits affect readiness remains a design question: ordinary edits would leave the score unchanged by default, while drastic changes—such as deleting the description or reverting it—may require recomputation without overcomplicating the backend.
- 0:53:00
Reviewing Optimization States and Change Comparisons
A review of the optimization interface: showing what is live or pending and ensuring that Review Changes clearly distinguishes the previous value from the optimized or published version. The observed issues were treated as small bugs ahead of larger autopilot work.
- 0:57:59
A Telegram App Idea for Better Community Collaboration
An early exploration of deploying a Telegram app that could help community members communicate, work, and support one another more effectively. The proposed approach was to begin with a simple version and expand it only if the idea proved useful.
- 1:03:30
Inconsistent Product-Readiness Indicators
A mismatch was noticed between the product-readiness states shown in the table and the summary indicator at the top of the dashboard, prompting a check of how those states are calculated and displayed.
Got a question about something in this stream?
Ask in the group