Missing Disconnecting Whatsapp from Superagents feature
It does sound like the ability to disconnect WhatsApp from a Superagent isn't available in the UI yet. I linked my Superagent to Whatsapp using the Activation code as requested but when I searched to disconnect it, I could not find any option to do so. Could you please investigate this ? Do not hesitate to reach me if you want me to show you live if it is unclear 😎 Thank you very much for your time and help, I wish you a wonderful afternoon. Kind regards.
Pierre Moras About 2 hours ago
Feature Request
Missing Disconnecting Whatsapp from Superagents feature
It does sound like the ability to disconnect WhatsApp from a Superagent isn't available in the UI yet. I linked my Superagent to Whatsapp using the Activation code as requested but when I searched to disconnect it, I could not find any option to do so. Could you please investigate this ? Do not hesitate to reach me if you want me to show you live if it is unclear 😎 Thank you very much for your time and help, I wish you a wonderful afternoon. Kind regards.
Pierre Moras About 2 hours ago
Feature Request
Allow the purchase of batch credits when plan is used up.
I just ran out of credits under my plan. In order to get more credits, I have to upgrade to the next level (on top of what I currently pay) or wait for the month to end. We should be able to buy separate batches of credits without having to upgrade the plan. 50 credits = $30 extra 250 credits = $50 extra 500 credits = $75 extra or something like this, so we’re not stuck having to upgrade or wait 2 weeks, which is not an option for some people when under time lines.
Jason Myers About 2 hours ago
Feature Request
Allow the purchase of batch credits when plan is used up.
I just ran out of credits under my plan. In order to get more credits, I have to upgrade to the next level (on top of what I currently pay) or wait for the month to end. We should be able to buy separate batches of credits without having to upgrade the plan. 50 credits = $30 extra 250 credits = $50 extra 500 credits = $75 extra or something like this, so we’re not stuck having to upgrade or wait 2 weeks, which is not an option for some people when under time lines.
Jason Myers About 2 hours ago
Feature Request
server accept typescript, but editor he doesn't accept it
If there is a syntax error in the editor the file is not deployed to the server
Francesco About 5 hours ago
Feature Request
server accept typescript, but editor he doesn't accept it
If there is a syntax error in the editor the file is not deployed to the server
Francesco About 5 hours ago
Feature Request
Feature Request: Cross-App Write Access for Superagents
The SuperAgents are great. Really a step forward. Great work. A Superagent can currently read data from other apps owned by the same user via read_user_app_data, but cannot write to them (create, update, or delete entity records). This means that tasks which could otherwise be fully automated still require manual intervention for the final step. Proposed solution Add a section in each app's Settings called something like "Connected Superagents", where the app owner can select which Superagent(s) are allowed to write to that app. The connected agent would then receive admin-level access to that app's entities — the same way it already works for the agent's own app. Why not a custom endpoint? A custom endpoint (e.g. via a Function) only partially solves the problem: You'd need to build a separate endpoint for every action → high maintenance The agent doesn't learn the app's data structure or logic Internal automations and business logic in the app wouldn't be triggered Direct entity access is cleaner, more powerful, and consistent with how the platform already works. Concrete use case My Superagent receives an email with an attachment → retrieves and uploads the file → needs to add it as a document to the correct grant application in my GrantWise app → and mark the related task as done. Right now, 90% of this is automated but it breaks at the write step. Suggested implementation Add a connected_agents field to app configuration When an agent request comes in with a matching agent ID → grant admin-level entity access Expose a write_user_app_data tool alongside the existing read_user_app_data This seems relatively straightforward to implement and would unlock true end-to-end automation across apps — which I think is a compelling use case for any power user on the platform. Thanks for considering it!
ET4ever About 7 hours ago
Feature Request
Feature Request: Cross-App Write Access for Superagents
The SuperAgents are great. Really a step forward. Great work. A Superagent can currently read data from other apps owned by the same user via read_user_app_data, but cannot write to them (create, update, or delete entity records). This means that tasks which could otherwise be fully automated still require manual intervention for the final step. Proposed solution Add a section in each app's Settings called something like "Connected Superagents", where the app owner can select which Superagent(s) are allowed to write to that app. The connected agent would then receive admin-level access to that app's entities — the same way it already works for the agent's own app. Why not a custom endpoint? A custom endpoint (e.g. via a Function) only partially solves the problem: You'd need to build a separate endpoint for every action → high maintenance The agent doesn't learn the app's data structure or logic Internal automations and business logic in the app wouldn't be triggered Direct entity access is cleaner, more powerful, and consistent with how the platform already works. Concrete use case My Superagent receives an email with an attachment → retrieves and uploads the file → needs to add it as a document to the correct grant application in my GrantWise app → and mark the related task as done. Right now, 90% of this is automated but it breaks at the write step. Suggested implementation Add a connected_agents field to app configuration When an agent request comes in with a matching agent ID → grant admin-level entity access Expose a write_user_app_data tool alongside the existing read_user_app_data This seems relatively straightforward to implement and would unlock true end-to-end automation across apps — which I think is a compelling use case for any power user on the platform. Thanks for considering it!
ET4ever About 7 hours ago
Feature Request
Image output changed to 1024x1024 on march 10th. Destroyed my website
This is unbelievable. Base44 changed the system of rendering the image base44.integrations.Core.GenerateImage to have only squared images! If it is not reverted this change totally destroy 3 months of work, my website and the monthly fee I take from customers. If this change to the core is keep I only have to refund the customers and loose 3 month of 3 people works. Now only choice is start again with a stable platform and loose 5 month to rebuild it. Advise: cannot base a project on an instable platform that change the core without back-compatibility
disarci About 8 hours ago
Feature Request
Image output changed to 1024x1024 on march 10th. Destroyed my website
This is unbelievable. Base44 changed the system of rendering the image base44.integrations.Core.GenerateImage to have only squared images! If it is not reverted this change totally destroy 3 months of work, my website and the monthly fee I take from customers. If this change to the core is keep I only have to refund the customers and loose 3 month of 3 people works. Now only choice is start again with a stable platform and loose 5 month to rebuild it. Advise: cannot base a project on an instable platform that change the core without back-compatibility
disarci About 8 hours ago
Feature Request
Multi sites & each have their own domain
It would be nice if one of your premium plan would have a feature supporting Multi sites custom front end & each have their own domain on the same backend. Everything hosted by you of course 😉 Ex: a soccer league with many teams
Francois Cloutier About 13 hours ago
Feature Request
Multi sites & each have their own domain
It would be nice if one of your premium plan would have a feature supporting Multi sites custom front end & each have their own domain on the same backend. Everything hosted by you of course 😉 Ex: a soccer league with many teams
Francois Cloutier About 13 hours ago
Feature Request
if i enter a chat and its not what i want and i click on the revert button, the company should change their terms to allow users to gain their credit points back, not money but credit points. that would help user so much in creating their apps
Eunice Grace About 15 hours ago
Feature Request
if i enter a chat and its not what i want and i click on the revert button, the company should change their terms to allow users to gain their credit points back, not money but credit points. that would help user so much in creating their apps
Eunice Grace About 15 hours ago
Feature Request
StoreKit/IAP Integration for Apple and Google to sell digital and have subscriptions. You don’t need it. Use stripe!!!! This is HUGE.
payment + review flow Legal background (Epic v. Apple) Case: Epic Games, Inc. v. Apple Inc., Case No. 4:20‑cv‑05640‑YGR (N.D. Cal.). Result: Apple cannot block or punish apps for sending users to an external website (like Stripe) to pay instead of using Apple’s in‑app purchase system, for US App Store users. Apps are allowed to: • Show prices and “subscription” language inside the app. • Redirect users to a web page for payment (e.g., Stripe Checkout). • Return users to the app afterwards. How this works with Base44 + Stripe The app itself is built in Base44 (web app wrapped for iOS/Android). Inside the app you: • Show subscription options and pricing. • When the user taps “Subscribe,” show a clear message like: “You are leaving the app to complete payment on our secure website (Stripe).” • Then redirect them to a Stripe Checkout URL in the browser / in‑app web view. • After payment, Stripe redirects back to a URL or deep link that re‑opens the app with the user marked as subscribed. Because the payment is processed on the web via Stripe, Apple and Google do NOT take the 15–30% cut; you just pay normal Stripe fees. What we do in practice Build everything in Base44 (RealShield AI app). Integrate Stripe for subscriptions. Implement a “leaving the app to pay on the web via Stripe” confirmation box before redirect. Submit the wrapped app to: • Google Play (AAB file). • Apple App Store (IPA file). If Apple rejects the app Sometimes reviewers still apply old rules and say you “must use in‑app purchases.” In that case, we DO NOT change the payment flow. Instead, we appeal. In the appeal, we: • Cite Epic Games, Inc. v. Apple Inc., Case No. 4:20‑cv‑05640‑YGR. • Explain that: – The app uses a clearly disclosed external web payment (Stripe). – Users see a neutral notice that they are leaving the app to pay on the web. – No Apple IAP is being used or hidden; the flow is consistent with the court decision and Apple’s updated US rules. Typical pattern: Submit with Stripe + external redirect notice. If Apple approves: done. If Apple rejects on payments: file an appeal referencing the Epic case and clarify that this is an allowed external payment flow. Short version: Epic v. Apple opened the door for external web payments (Stripe) in US apps. A Base44 app can show prices and subscriptions, then send users to Stripe on the web and back. If Apple says “no,” you appeal and point to the Epic ruling instead of rebuilding the app or ripping Stripe out. I have also consulted with my lawyer and he confirms this. Im working out a few bugs on my app and turning into Apple and Google today. I’ll post on here what happens, if it gets approved or rejected.
Israel Mudder About 18 hours ago
Feature Request
StoreKit/IAP Integration for Apple and Google to sell digital and have subscriptions. You don’t need it. Use stripe!!!! This is HUGE.
payment + review flow Legal background (Epic v. Apple) Case: Epic Games, Inc. v. Apple Inc., Case No. 4:20‑cv‑05640‑YGR (N.D. Cal.). Result: Apple cannot block or punish apps for sending users to an external website (like Stripe) to pay instead of using Apple’s in‑app purchase system, for US App Store users. Apps are allowed to: • Show prices and “subscription” language inside the app. • Redirect users to a web page for payment (e.g., Stripe Checkout). • Return users to the app afterwards. How this works with Base44 + Stripe The app itself is built in Base44 (web app wrapped for iOS/Android). Inside the app you: • Show subscription options and pricing. • When the user taps “Subscribe,” show a clear message like: “You are leaving the app to complete payment on our secure website (Stripe).” • Then redirect them to a Stripe Checkout URL in the browser / in‑app web view. • After payment, Stripe redirects back to a URL or deep link that re‑opens the app with the user marked as subscribed. Because the payment is processed on the web via Stripe, Apple and Google do NOT take the 15–30% cut; you just pay normal Stripe fees. What we do in practice Build everything in Base44 (RealShield AI app). Integrate Stripe for subscriptions. Implement a “leaving the app to pay on the web via Stripe” confirmation box before redirect. Submit the wrapped app to: • Google Play (AAB file). • Apple App Store (IPA file). If Apple rejects the app Sometimes reviewers still apply old rules and say you “must use in‑app purchases.” In that case, we DO NOT change the payment flow. Instead, we appeal. In the appeal, we: • Cite Epic Games, Inc. v. Apple Inc., Case No. 4:20‑cv‑05640‑YGR. • Explain that: – The app uses a clearly disclosed external web payment (Stripe). – Users see a neutral notice that they are leaving the app to pay on the web. – No Apple IAP is being used or hidden; the flow is consistent with the court decision and Apple’s updated US rules. Typical pattern: Submit with Stripe + external redirect notice. If Apple approves: done. If Apple rejects on payments: file an appeal referencing the Epic case and clarify that this is an allowed external payment flow. Short version: Epic v. Apple opened the door for external web payments (Stripe) in US apps. A Base44 app can show prices and subscriptions, then send users to Stripe on the web and back. If Apple says “no,” you appeal and point to the Epic ruling instead of rebuilding the app or ripping Stripe out. I have also consulted with my lawyer and he confirms this. Im working out a few bugs on my app and turning into Apple and Google today. I’ll post on here what happens, if it gets approved or rejected.
Israel Mudder About 18 hours ago
Feature Request
Allow deferring /User/me auth check on public pages
"Allow deferring /User/me auth check on public pages so it doesn't appear in the critical rendering chain and affect LCP scores"
healthiermindforlife About 20 hours ago
Feature Request
Allow deferring /User/me auth check on public pages
"Allow deferring /User/me auth check on public pages so it doesn't appear in the critical rendering chain and affect LCP scores"
healthiermindforlife About 20 hours ago
Feature Request
Hello, There should be a way to add **partial additional credits**, regardless of the current plan, without needing to upgrade or change the plan. This limitation makes it harder to manage projects. Sometimes we only need to add a small amount of credits to continue working. Thank you for your attention.
Ronaldo Franco About 21 hours ago
Feature Request
Hello, There should be a way to add **partial additional credits**, regardless of the current plan, without needing to upgrade or change the plan. This limitation makes it harder to manage projects. Sometimes we only need to add a small amount of credits to continue working. Thank you for your attention.
Ronaldo Franco About 21 hours ago
Feature Request
I want my users to be able to see their password. I asked your help for it, got this response:In the AI chat, type something like: "Add a show/hide password toggle (eye icon) to the login and sign-up password fields so users can reveal their password while typing." The AI will update the password input fields to include a visibility toggle button. This is a standard UX feature and won't affect how passwords are stored or secured — it just lets users see what they're typing.
but that doesn’t work because it’s a feature from base 44 that the ai can’t manage.
Richard Stockwell About 23 hours ago
Feature Request
I want my users to be able to see their password. I asked your help for it, got this response:In the AI chat, type something like: "Add a show/hide password toggle (eye icon) to the login and sign-up password fields so users can reveal their password while typing." The AI will update the password input fields to include a visibility toggle button. This is a standard UX feature and won't affect how passwords are stored or secured — it just lets users see what they're typing.
but that doesn’t work because it’s a feature from base 44 that the ai can’t manage.
Richard Stockwell About 23 hours ago
Feature Request
New Features
The new superagent is truly incredible. Could we: add the possibility of changing the whatsapp name (and maybe even the profile picture)? what you currently see is “base44’s ai agent” but id love to be able to see my superagent’s name as i named her could you integrate superagent to phone alarms? im a heavy sleeper and having the superagent keep my phone alarm going until i’ve sent it a pic on whatsapp would be a life saver (i know there are similar clocks out there but they still have some sort of off button if you dont’ wanna get out of bed, which is exactly what i click everytime)
Yasmyna Feraru About 24 hours ago
Feature Request
New Features
The new superagent is truly incredible. Could we: add the possibility of changing the whatsapp name (and maybe even the profile picture)? what you currently see is “base44’s ai agent” but id love to be able to see my superagent’s name as i named her could you integrate superagent to phone alarms? im a heavy sleeper and having the superagent keep my phone alarm going until i’ve sent it a pic on whatsapp would be a life saver (i know there are similar clocks out there but they still have some sort of off button if you dont’ wanna get out of bed, which is exactly what i click everytime)
Yasmyna Feraru About 24 hours ago
Feature Request
I don't think it's right to deduct credits when the AI is correcting code errors. The right thing to do is that if you tell the AI to build something, it should do so correctly and functionally. I purchased the plan yesterday, and today I no longer have credits to continue working because the AI used them up trying to correct a code error, and the issue wasn't even resolved. Now I have to wait a month to be able to resolve it. It's unfair.
HACIENDA EFICIENTE About 24 hours ago
Feature Request
I don't think it's right to deduct credits when the AI is correcting code errors. The right thing to do is that if you tell the AI to build something, it should do so correctly and functionally. I purchased the plan yesterday, and today I no longer have credits to continue working because the AI used them up trying to correct a code error, and the issue wasn't even resolved. Now I have to wait a month to be able to resolve it. It's unfair.
HACIENDA EFICIENTE About 24 hours ago
Feature Request
'Enter' send request by default instead of just new line
There is a bug: Pressing 'Enter' perform "send request" by default instead of just move to next line. it can be adjust on settings, however, I think that the DEFAULT state should be that ‘Enter’ move to new line (like in Whatsapp chat) Verified on mobile app, maybe occur also on web env. Observed behavior: Pressing 'Enter' send request Expected behavior: Pressing 'Enter' move to next line Please try it yourself, install base44 on new phone, and write app instruction, after 1 line the instructions will be sent before you finished to write the instructions, it looks bad and unprofessional, please consult with your manager, I strongly advise to fix it.
Ronen 1 day ago
Feature Request
'Enter' send request by default instead of just new line
There is a bug: Pressing 'Enter' perform "send request" by default instead of just move to next line. it can be adjust on settings, however, I think that the DEFAULT state should be that ‘Enter’ move to new line (like in Whatsapp chat) Verified on mobile app, maybe occur also on web env. Observed behavior: Pressing 'Enter' send request Expected behavior: Pressing 'Enter' move to next line Please try it yourself, install base44 on new phone, and write app instruction, after 1 line the instructions will be sent before you finished to write the instructions, it looks bad and unprofessional, please consult with your manager, I strongly advise to fix it.
Ronen 1 day ago
Feature Request
My First weeks experiences of using Base44 as a no-code user
Executive Summary I began using the platform on a Builder subscription, but within the first day I needed to upgrade to Pro, and shortly afterwards to the Elite plan, in order to continue developing my application. Within my first week, I have now exhausted approximately 95% of my monthly message credits. This has not been due to building new functionality, but primarily due to repeatedly fixing regressions introduced by the platform’s AI development agent. As a result, I now have no option but to stop development for the next three weeks until the subscription renews, because there is currently no way to purchase additional credits. The core issue appears to be a lack of safeguards in how the AI development agent operates. It can make changes without assessing the impact on existing functionality, without preventing previously working features from breaking, and without providing a reliable way to roll back to a stable version. This has created a development cycle where previously resolved issues reappear and must be corrected again, consuming credits each time. Based on my experience, this appears to be a structural limitation in the current development workflow rather than a one-off issue. Key Issues Encountered 1. AI Development Agent Creating Regression Loops During development, the in-app AI development agent repeatedly introduced bugs into parts of the application that had previously been working correctly. Even when the agent acknowledged the mistake and corrected it, similar issues would often reappear in later changes. At present there appears to be no mechanism to: Evaluate the impact of a change before it is applied Protect existing working functionality Reliably restore a known working version Without these safeguards, development can easily fall into a regression loop, where the same problems repeatedly return and require additional prompts to resolve. Each iteration consumes credits and slows development progress. 2. Credit Consumption Caused by Platform Behavior Because these regressions required repeated investigation and correction, the majority of my credits were consumed debugging issues introduced by the agent itself, rather than building new features. Currently there appears to be no way for users to: Stop an agent caught in a regression cycle Recover credits spent resolving platform-introduced problems Purchase additional credits during the current billing cycle The platform interface also displays a “Purchase more credits →” prompt when credits are exhausted, even though purchasing additional credits is not currently available. This creates a confusing user experience and suggests functionality that does not actually exist. 3. Reliability of Basic Data Operations Interestingly, some of the more advanced AI enrichment features worked extremely well and delivered fast, useful results. However, the most basic data operations proved unreliable. In particular: File imports sometimes required multiple attempts to complete successfully Database updates were inconsistent Long-running background tasks did not appear to complete or fail cleanly The job queue system did not appear to provide clear retry, timeout, or failure behavior These types of operations are generally well understood in software engineering, so their instability creates a significant reliability concern for anyone trying to build a production-quality application. 4. Absence of a Structured Change Management Approach From my perspective, many of these issues stem from the absence of a structured framework governing how the AI agent performs changes to an application. I believe both the AI agents and the Base44 organisation would benefit from implementing a recognized service management framework such as ITIL (other frameworks are available). Even a lightweight approach covering Incident Management, Problem Management, and Change Management could significantly reduce the types of issues described here. For example, the current process appears to lack: Impact assessment before applying changes Safeguards to prevent modifications during active incidents Reliable rollback capability Clear change tracking showing what was modified and when Without these controls, the AI agent effectively has unrestricted ability to modify application behavior without the safeguards typically present in modern development environments. 5. Expectations Placed on Non-Technical Users Another difficulty I encountered is that, although the platform is presented as a no-code solution, I have repeatedly been asked to perform tasks that are typically the responsibility of technical specialists. This has included being asked to: Investigate code-level issues Diagnose system behavior Identify technical faults Provide detailed explanations of what may be happening internally In practice, this places the user in the role of developer, systems analyst, and technical investigator, which is very different from the expectation created by the platform’s messaging that coding knowledge is not required. Overall Impact Area Impact Credits Approximately 95% consumed within the first week Development Work on the application has effectively halted Time Significant time spent repeatedly fixing the same issues Progress Development must pause until the next subscription cycle What I Am Not Asking For Sympathy or reassurance Temporary workarounds General assurances that the issue will not happen again What I Am Asking For Credit restoration Credits that were consumed fixing agent-introduced regressions should be restored. Migration support Assistance moving the project to a clean environment without consuming additional credits. Platform acknowledgement Confirmation that the regression loop and reliability issues described above are recognized and being addressed. User interface correction The “Purchase credits” prompt should not be shown if additional credits cannot actually be purchased. Closing Note I have invested a considerable amount of time working through these issues and reporting them constructively. My intention in posting this is not simply to complain, but to highlight platform-level reliability concerns that may affect other users building applications on the platform. The platform clearly has significant potential. However, improving reliability safeguards, development controls, and support structures would greatly improve the experience for users trying to build real applications.
Chip 1 day ago
Feature Request
My First weeks experiences of using Base44 as a no-code user
Executive Summary I began using the platform on a Builder subscription, but within the first day I needed to upgrade to Pro, and shortly afterwards to the Elite plan, in order to continue developing my application. Within my first week, I have now exhausted approximately 95% of my monthly message credits. This has not been due to building new functionality, but primarily due to repeatedly fixing regressions introduced by the platform’s AI development agent. As a result, I now have no option but to stop development for the next three weeks until the subscription renews, because there is currently no way to purchase additional credits. The core issue appears to be a lack of safeguards in how the AI development agent operates. It can make changes without assessing the impact on existing functionality, without preventing previously working features from breaking, and without providing a reliable way to roll back to a stable version. This has created a development cycle where previously resolved issues reappear and must be corrected again, consuming credits each time. Based on my experience, this appears to be a structural limitation in the current development workflow rather than a one-off issue. Key Issues Encountered 1. AI Development Agent Creating Regression Loops During development, the in-app AI development agent repeatedly introduced bugs into parts of the application that had previously been working correctly. Even when the agent acknowledged the mistake and corrected it, similar issues would often reappear in later changes. At present there appears to be no mechanism to: Evaluate the impact of a change before it is applied Protect existing working functionality Reliably restore a known working version Without these safeguards, development can easily fall into a regression loop, where the same problems repeatedly return and require additional prompts to resolve. Each iteration consumes credits and slows development progress. 2. Credit Consumption Caused by Platform Behavior Because these regressions required repeated investigation and correction, the majority of my credits were consumed debugging issues introduced by the agent itself, rather than building new features. Currently there appears to be no way for users to: Stop an agent caught in a regression cycle Recover credits spent resolving platform-introduced problems Purchase additional credits during the current billing cycle The platform interface also displays a “Purchase more credits →” prompt when credits are exhausted, even though purchasing additional credits is not currently available. This creates a confusing user experience and suggests functionality that does not actually exist. 3. Reliability of Basic Data Operations Interestingly, some of the more advanced AI enrichment features worked extremely well and delivered fast, useful results. However, the most basic data operations proved unreliable. In particular: File imports sometimes required multiple attempts to complete successfully Database updates were inconsistent Long-running background tasks did not appear to complete or fail cleanly The job queue system did not appear to provide clear retry, timeout, or failure behavior These types of operations are generally well understood in software engineering, so their instability creates a significant reliability concern for anyone trying to build a production-quality application. 4. Absence of a Structured Change Management Approach From my perspective, many of these issues stem from the absence of a structured framework governing how the AI agent performs changes to an application. I believe both the AI agents and the Base44 organisation would benefit from implementing a recognized service management framework such as ITIL (other frameworks are available). Even a lightweight approach covering Incident Management, Problem Management, and Change Management could significantly reduce the types of issues described here. For example, the current process appears to lack: Impact assessment before applying changes Safeguards to prevent modifications during active incidents Reliable rollback capability Clear change tracking showing what was modified and when Without these controls, the AI agent effectively has unrestricted ability to modify application behavior without the safeguards typically present in modern development environments. 5. Expectations Placed on Non-Technical Users Another difficulty I encountered is that, although the platform is presented as a no-code solution, I have repeatedly been asked to perform tasks that are typically the responsibility of technical specialists. This has included being asked to: Investigate code-level issues Diagnose system behavior Identify technical faults Provide detailed explanations of what may be happening internally In practice, this places the user in the role of developer, systems analyst, and technical investigator, which is very different from the expectation created by the platform’s messaging that coding knowledge is not required. Overall Impact Area Impact Credits Approximately 95% consumed within the first week Development Work on the application has effectively halted Time Significant time spent repeatedly fixing the same issues Progress Development must pause until the next subscription cycle What I Am Not Asking For Sympathy or reassurance Temporary workarounds General assurances that the issue will not happen again What I Am Asking For Credit restoration Credits that were consumed fixing agent-introduced regressions should be restored. Migration support Assistance moving the project to a clean environment without consuming additional credits. Platform acknowledgement Confirmation that the regression loop and reliability issues described above are recognized and being addressed. User interface correction The “Purchase credits” prompt should not be shown if additional credits cannot actually be purchased. Closing Note I have invested a considerable amount of time working through these issues and reporting them constructively. My intention in posting this is not simply to complain, but to highlight platform-level reliability concerns that may affect other users building applications on the platform. The platform clearly has significant potential. However, improving reliability safeguards, development controls, and support structures would greatly improve the experience for users trying to build real applications.
Chip 1 day ago
Feature Request
