Build a Research Review App With Codex
Give your saved research a useful home: review an idea, choose the right reference images, and finish with a report you can use to create original designs.
Narrated by TEE-BOT, an AI voice. Every result gets a human review.
Start with the previous research video: Paste This Codex Prompt. Let It Do Your T-Shirt Research. Keep its saved research files in your project. Get the prerequisite research prompts.
Watch the full app build on YouTube ↗ · Episode notes and transcript
Jump to the starter prompt ↓ · Read the Markdown version
Build one stage. Open it. Test it.
- Watch the prerequisite research video and save its research files in your Codex project. This app reads that research; it does not replace the research step.
- Paste the starter prompt into Codex in that project. Ask for the simple research viewer first, then open the app link and test search, sorting and saved decisions.
- Add the later stages one at a time: relevant Amazon captures, image review, design analysis and one automatic final report per idea. Explain missing behavior in plain English and ask Codex to fix it.
- Review the artwork itself before approving a reference. When the final report is ready, copy its AI generation brief into ChatGPT and ask for five distinct T-shirt design concepts. Check the outputs before production.
You do not need a coding background to start. Describe what you need in plain English. If a button, capture or report does not give you the result you want, explain the gap and ask Codex to improve it. That is the benefit of owning the app.
Keep the decisions yours
Starter · not independently tested as one combined prompt. It consolidates the staged build shown in the video; your research format and local environment may need changes.
Saved counts and ranks are dated snapshots, not proof of demand, sales or profit. Keyword approval and image approval are separate decisions.
The personal local app uses the official Codex CLI with ChatGPT sign-in for analysis. Eligible subscription allowances and usage limits apply. This is not general API access or unlimited usage; the prompt asks Codex to verify current support and avoid a silent separately billed fallback.
Amazon access can be limited. Keep conservative pacing, preserve progress and stop on access challenges. Do not bypass them. References support original exploration; they are not artwork to copy.
Copy the app starter prompt
Starter · not tested as one combined prompt. Build and test each stage. Free to adapt under the MIT license.
Build a small standalone local app to review the Amazon T-shirt research already saved in this project. Inspect the existing research format first and preserve source files. Do not connect to another app or a production service.
Start with one simple review screen: keyword/idea, Amazon link, saved page-3 total result count, checked date, and Pending / Approved / Rejected decisions. Add search, sort, undo and persisted decisions. Counts are historical snapshots, not demand or sales estimates. Test decision changes in isolated storage before touching actual user records.
After that works, add these stages one at a time and demonstrate each:
1. Approval-triggered collection of organic, non-sponsored Page 1 products. Save only verified matching products with a MAIN Clothing, Shoes & Jewelry BSR strictly below 4,000,000. Skip uncertain matches, unreadable ranks and subcategory-only evidence. Follow website constraints, use conservative pacing, save progress and exclusions, support cancellation, and stop on access challenges. Never purchase anything.
2. An app-owned background capture worker triggered by approval, with app progress and actionable errors instead of recurring no-work messages in the build chat. Make startup/shutdown and browser ownership explicit. Crop to the shirt/design image; preserve originals, BSR/category, checked date and product link.
3. Individual image approval/rejection, separate from keyword approval. Enlarge the actual artwork so a person can read its printed phrase. Listing titles are not evidence of artwork wording. Allow corrections and show review progress.
4. For this trusted personal local app, investigate the OFFICIAL local Codex CLI using the existing ChatGPT subscription sign-in for analysis. Verify current official support and usage limits. Never extract/copy/expose OAuth tokens or silently fall back to separately billed API-key usage. If the route is unavailable, explain before choosing a different provider or billing setup. Do not add credentials or paid services without direction.
5. Analyze approved artwork only: exact visible phrases, depicted characters, motifs, text-only / graphic-only / mixed classification, styles, printed ink colors excluding fabric/background, typography, composition, overall concept and uncertainties. Never reconstruct missing text from a listing title. Preserve existing analysis and allow human edits.
6. My ideas: Research → Review captures → Final report. Generate one current report per idea automatically only after collection, all image decisions, and analysis of approved images finish. Include only approved references. If everything is rejected, say no designs were selected. Update the current report when relevant decisions change instead of mixing ideas.
7. Final report with Markdown, structured JSON, a ZIP of approved reference images and Copy AI generation brief. Preserve report/image provenance. Encourage original exploration, exact spelling and one coherent direction rather than copying all references.
Keep the interface simple. Preserve original files and saved decisions during migrations. Run checks appropriate to each stage and show the real workflow before calling it complete. Do not publish, upload, buy, schedule recurring tasks or mutate real decisions for testing without explicit authorization.
After human review, the design handoff can be: paste the final brief into ChatGPT and ask, “Create five distinct T-shirt design concepts using this research brief.” Review wording and artwork, then verify export requirements. Concepts are not proof of sales or automatically cleared print-ready files.
Your next small win
Sign up for the free newsletter for niche ideas and bonus prompts. You can also choose Newsletter in the website menu.
Keep building your AI POD future.