Filter
Exclude
Time range
-
Near
You can do some pretty cool things with this 4th step. And it goes beyond just a verification step with your coding agent because it’s gonna miss most of its errors anyway. Something I’ve been doing is creating test suites to give to ChatGPT agent. First, I give the following prompt to Claude or whatever is building the app to get me tests. Here’s the prompt ———————- { "role": "Front End User Test Generator", "task": "Generate a structured testing plan that ONLY covers what a single end user can manually test through the front end UI. Do not include automated tests, backend checks, or code-level validation. Focus entirely on what a real person can see, click, enter, or experience in the browser or app interface.", "projectFeatures": "{{INSERT_FEATURE_LIST_OR_PROJECT_DESCRIPTION_HERE}}", "outputFormat": [ { "testCaseID": "TS-###", "testType": "UI | Interaction | Flow", "feature": "{{Feature Name}}", "scenario": "{{Brief description of what the user is doing in the UI}}", "steps": ["Step 1", "Step 2", "Step 3", "..."], "expectedResult": "{{What the user should see or experience if the test passes}}" } ], "rules": [ "Each testCaseID must be unique and sequential (e.g., TS-001, TS-002...).", "All tests must be written from the perspective of a single user interacting with the front end only.", "No backend, API, or automation steps are allowed.", "Prioritize real-world user flows, edge cases, and visible outcomes.", "Use plain, non-technical language so that anyone could follow and execute the tests." ] } —————————— Then I copy paste the output I get back to ChatGPT agent along with a url and tell it to get started. Here is the prompt I send along with the test suite and url. —————- You are in Ultra-Thorough Implementation Mode. Begin now. You have already received a structured test suite output. Begin executing the test cases one-by-one with zero omissions or summarization. For each test case, follow this exact format: Step [#]: Execute Test Case TS-### – [Short Test Title] Tools needed: [List tools or utilities used for this specific test] Preconditions: [All setup states or conditions required before execution] Configuration Required: [Describe any necessary configuration, environment, or state] Output: [Describe the result of executing the test] Success criteria: [Define the condition for a passing result] Always process sequentially by testCaseID (e.g., TS-001, TS-002, etc.). Do not skip, merge, or summarize any step. Explicitly log expected vs. actual result comparisons. For any deviation or failure, capture exact repro steps and environment state. Continue until every test case in the suite is executed and validated. Begin executing the test suite now. Do not stop. Do not simplify. Do not summarize.
2
3
632
Have assistant write you a front end test suite. Give it this prompt and then give assistants response to ChatGPT agent. Bam saved you 5 bucks and 45 minutes { "role": "Frontend Test Suite Generator", "task": "Generate a structured testing plan focused only on front-end features. The plan must include simple user-facing test cases (clicking buttons, filling forms, navigating screens, checking visuals).", "projectFeatures": "{{INSERT_FEATURE_LIST_OR_PROJECT_DESCRIPTION_HERE}}", "outputFormat": [ { "testCaseID": "FT-###", "testType": "UI | Interaction | Visual", "feature": "{{Feature Name}}", "scenario": "{{Brief description of what the user does or sees}}", "expectedResult": "{{What the user should experience if the test passes}}" } ], "rules": [ "Each testCaseID must be unique and sequential (e.g., FT-001, FT-002...)", "Cover clicking, typing, scrolling, and visual layout checks", "Use plain, non-technical language so anyone can follow", "Focus only on what the user sees and does, not backend logic" ] }
3
69
WHO KNEW THIS COULD BE A 'STARTUP' Here's a prompt that you can use. Give this prompt to your app agent and then hand the response you get back to chatgpt agent. when its done, youll get a report with screenshots attached. { "role": "Test Suite Generator", "task": "Generate a structured testing plan based on the provided project or feature descriptions. The plan must include unit, integration, and end-to-end test cases where applicable.", "projectFeatures": "{{INSERT_FEATURE_LIST_OR_PROJECT_DESCRIPTION_HERE}}", "outputFormat": [ { "testCaseID": "TS-###", "testLevel": "Unit | Integration | E2E", "feature": "{{Feature Name}}", "scenario": "{{Brief description of the test situation}}", "expectedResult": "{{What should happen if the test passes}}" } ], "rules": [ "Each testCaseID must be unique and sequential (e.g., TS-001, TS-002...)", "Distribute tests across Unit, Integration, and E2E levels", "Prioritize functional and edge case coverage", "Use plain, non-technical language where possible" ] }
Synthetic Society tests your product with AI-powered user simulations. Their agents mimic real users to catch bugs, bad UX, and edge cases. Ship faster, kill manual testing, and build with confidence. ycombinator.com/launches/O7g… Congrats on the launch, @aaronchewbani and @kavandoc!
1
2
285
😇 SunSpace JUMP (t.me/SunSpaceJump_bot/play?s…) – Cosmic Tournament ⚠️ Note: During this tournament, updates may be released and its parameters may change. 👍 Prize Pool: 4,000,000 $SPC (~$770) Shared among players in the TOP 700🗓 Ends Thursday at 18:00 (UTC) 🏆 Get into the TOP and earn $SPC – the native token of the SunSpace projectFeatures: 💲 Staking – lock your tokens and earn more 🎰 Games using $SPC with up to x20 returns 💎 Instant withdrawal to TON and TRX ⭐️ Exchange for Stars, Premium, and VPN 🕹 See you in the game, astronaut!
1
6
96
Have you tried using a Bento Board for your projects? 📝✨ --Here’s a glimpse of a board I created for one of my projects—showcasing key features and functionality in a clean, organized way. #BentoBoard #ProjectFeatures #UXDesign #PresentationTips #figma #casestudy #frototype
1
59
27 Jun 2022
Don't forget to get your copy today! Available at selected CNA & Exclusive book stores nationwide. #SABuildingReview #MediaXpose #Advertising #Marketing #Architecture #Handbook #Guide #ProjectFeatures
2
We love how @lucasmurnaghan immerses himself in his artwork - literally! We were thrilled to design the framing for this underwater photo, setting it in a shadowbox with a white gallery frame. Sign up for our newsletter for more #projectfeatures!
4
9
Inspired by Swedish artist Harriet Sundstrom, this greyhound lithograph was a pleasure for us #doglovers to frame! More live updates of #projectfeatures on our FB and IG pages😃
1