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
- 4:14:26
Start with a Small Mobile App and Learn with AI
The beginner-oriented advice is to start with the Codex app while considering one’s experience and goal, and to use AI dialogue to learn mobile-development steps. It recommends first building a small personal app, gaining a practical grasp, and only then building for others, with help from experienced mobile developers when needed.
- 4:34:58
Improving the App Layout and Fixing Popup Movement
A design review says the interface looks like a box embedded in a web page rather than a complete application and proposes making the workspace full screen. It also identifies a bug where the popup shifts up and down during navigation and recommends keeping it fixed.
- 4:45:23
Reviewing Manifesto Milestones and Infrastructure
After confirming that a fix was working better, the session called for a recap of completed milestones and the next direction, with finishing Manifesto’s infrastructure identified as the work goal.
- 4:55:21
A User Manifesto as an Intelligent Application Input
The application can work without a manifesto, but answering six questions produces one containing system guidance that improves inputs across articles, visibility, and the storefront. A preliminary draft could be derived from Shopify scopes when users drop off, while direct answers are expected to yield a better result; multi-lens research is described as an additional information layer.
- 4:58:07
Section-by-Section Implementation After Storefront Complexity
At the time of the recording, work was proceeding section by section; the storefront had taken longer because it contained more behavior, while articles, visibility, and intelligence were expected to progress faster.
- 4:59:12
Defining a Purpose That Sustains Community Engagement
After building the initial skeleton, the discussion calls for a purpose deeper than a merely gamified 2D application: users need a reason to remain engaged with the community instead of trying it briefly and leaving.
- 5:04:06
Tracking Project Progress While Respecting Privacy
The concept would let community members track projects and see who has shipped, potentially through GitHub integration. Execution remains unresolved because many people work on private projects.
- 5:06:15
Tracing a Broken Manifesto-Generation Interface
The manifesto-generation interface became broken after previously working, both for review-and-generate and direct drafting. The proposed next step is to trace the change that caused the regression and fix it; the captions do not confirm a completed repair.
- 5:08:17
Celebrating Small Milestones Instead of Waiting for Launch
Because shipping moments are rare, the discussion suggests using celebratory effects for smaller self-reported milestones, achievements, and progress, while letting people showcase work and request feedback. The execution and broader direction remain open.
- 5:11:41
Using a Reactable MVP for Product Discovery
The proposal is to build a usable MVP first and react to it to generate further ideas, while exploring whether the character can move between desks within the experience.
- 5:13:07
Unverified Impressions of Claude in Cursor
The speaker relays a claim they had heard that using Claude within Cursor may be powerful. This is presented as hearsay rather than a direct comparative test, alongside a general observation that the option is expensive and that its usage requirements are not fully clear in the captions.
- 5:15:58
AI Model Overload and Distraction
A brief reflection that the rapid proliferation of AI models has become distracting, alongside anticipation of an upcoming model whose details are uncertain in the captions.
- 5:16:54
Designing a Scalable Interactive Virtual Office
A concept for a virtual space where members move between desks, share project updates and files, and signal when they need help. The discussion considers cost and interaction, starting with a small space and expanding in response to usage, plus zones, a meeting room, or discipline-based floors. It also uses Gather as a visual reference and considers buying higher-quality assets or designing custom ones for a cleaner, more colorful result.
- 5:31:57
Merging and Deploying Changes Incrementally
After completing a set of pull requests, the speaker plans to merge and deploy the changes one at a time so that any problem arising during the process is easier to isolate.
- 5:45:02
Isometric Tiny-House Prototype
A request to build a quick isometric prototype of a one-room tiny house that lets the speaker walk around it.
- 5:52:53
Two UI and PDF Download Bugs
Testing found that the content did not render immediately and required a refresh or hard refresh. Selecting Download PDF also opened a new window that returned to the dashboard instead of performing the expected download; both behaviors were identified as bugs to fix.
- 5:57:50
Adding Proper Collisions to the Cat Scene
The scene representation looked better, but the couch and desk did not behave as physical obstacles, allowing the cat to pass through them. The discussion called for correcting the collision physics before committing and rebuilding, while acknowledging uncertainty about whether the current behavior was intentional.
- 6:05:44
Supporting Diagonal Cat Movement
The cat was observed to be unable to walk diagonally, and diagonal movement was identified as an important capability to add to the movement controls.
- 6:08:03
Code Review, Merge, and Deployment Workflow
A live coding workflow covering review, approval, merge, and deployment of code changes, followed by checking whether the expected behavior works and deciding what to do next. Fragmentary captions also suggest that a fresh generation may be needed, but the technical details are too unclear to state more definitively.
- 6:20:05
Reviewing Design Through a Full-App Mockup
A suggestion to render the entire application as a visual mockup for approval or rejection instead of generating an isolated element that does not show the intended whole.
Got a question about something in this stream?
Ask in the group