Planned
Fix Magic Wand placement of Trigger Node
At 71:00 [email protected] hit the magic wand and our x-coordinate placement for the trigger node is wrong. Let’s correct this. Also, notice that the connecting lines disappeared for some reason at 71:25-71:45 (not sure what caused this or how to replicate).
Marc 16 days ago
🐛 Report Bug
Planned
Fix Magic Wand placement of Trigger Node
At 71:00 [email protected] hit the magic wand and our x-coordinate placement for the trigger node is wrong. Let’s correct this. Also, notice that the connecting lines disappeared for some reason at 71:25-71:45 (not sure what caused this or how to replicate).
Marc 16 days ago
🐛 Report Bug
Planned
Deactivate individual widgets?
It might be helpful if there was a way to deactivate individual widgets, but leave them staged in the workflow, but turn them off while I’m experimenting with other configurations. For instance and the moment I have a code widget “Flatten array”, which is not connected in the workflow, but it seems to be breaking the API call even though it isn’t connected. My widget here with a bit of code is probably just rubbish and I will probably delete it in the end, But it would be nice if I could just deactivate it while I troubleshoot the other parts of the workflow, so I don’t need to delete it to test the other widgets. My apologies, maybe there is a way to do this already that I’m not aware.
celso.wilkinson 23 days ago
💡 Feature Requests
Planned
Deactivate individual widgets?
It might be helpful if there was a way to deactivate individual widgets, but leave them staged in the workflow, but turn them off while I’m experimenting with other configurations. For instance and the moment I have a code widget “Flatten array”, which is not connected in the workflow, but it seems to be breaking the API call even though it isn’t connected. My widget here with a bit of code is probably just rubbish and I will probably delete it in the end, But it would be nice if I could just deactivate it while I troubleshoot the other parts of the workflow, so I don’t need to delete it to test the other widgets. My apologies, maybe there is a way to do this already that I’m not aware.
celso.wilkinson 23 days ago
💡 Feature Requests
Planned
Test Case Expected Results
When creating Test Cases, capture expected results (in addition to capturing the name and test conditions as Lamatic does currently). Consider also, Using code checks and AI to find deviation and grade result quality. Use this quality score as an input for deciding whether to deploy an update. Assist in recommending the best option when A|B testing prompts, agents, workflows, models and other settings such as temperature. Using these results to create benchmarks. Measuring and alerting about “model drift” over time. Integrating “human-in-the-loop” strategies to expand Test Cases and quality checking. Added Later (based on feedback from another user): Make it easier to see the history of Test Case executions (without leaving Experiments). Marc Greenberg didn’t realize he could find the results in Logs, but also didn’t like having to dig through logs to find the execution details for a given test.
cwhiteman About 1 month ago
💡 Feature Requests
Planned
Test Case Expected Results
When creating Test Cases, capture expected results (in addition to capturing the name and test conditions as Lamatic does currently). Consider also, Using code checks and AI to find deviation and grade result quality. Use this quality score as an input for deciding whether to deploy an update. Assist in recommending the best option when A|B testing prompts, agents, workflows, models and other settings such as temperature. Using these results to create benchmarks. Measuring and alerting about “model drift” over time. Integrating “human-in-the-loop” strategies to expand Test Cases and quality checking. Added Later (based on feedback from another user): Make it easier to see the history of Test Case executions (without leaving Experiments). Marc Greenberg didn’t realize he could find the results in Logs, but also didn’t like having to dig through logs to find the execution details for a given test.
cwhiteman About 1 month ago
💡 Feature Requests
Planned
Model Preference & Fallback
A dedicated UI to choose model preferences on project level. There will be different categories of models ( Tabs ) for Text | Embedding| Chat | Image | Audio | Transcript For Each category customer can create 5 Settings and reorder them. In each settings can choose 4 tabs ( Basic | Fallback | Best | A/B Test ) When using model selection in a workflow node, choose a preferred setting options which will populate the UI with credentials and model selection. ( By Default the first preference will be chosen or create a new preferences
Aman Sharma About 1 month ago
💡 Feature Requests
Planned
Model Preference & Fallback
A dedicated UI to choose model preferences on project level. There will be different categories of models ( Tabs ) for Text | Embedding| Chat | Image | Audio | Transcript For Each category customer can create 5 Settings and reorder them. In each settings can choose 4 tabs ( Basic | Fallback | Best | A/B Test ) When using model selection in a workflow node, choose a preferred setting options which will populate the UI with credentials and model selection. ( By Default the first preference will be chosen or create a new preferences
Aman Sharma About 1 month ago
💡 Feature Requests
Improvement to Model Benchmark Screen
Take this Prototype for inspiration - https://cristi5833.softr.app/new Keep the Column Header Fixed Add Sort by in the headers itself for all columns Add Context Length Column Add Shortcut to model API screen ( Open Porta )
Aman Sharma About 1 month ago
👏🏻 Feedback
Improvement to Model Benchmark Screen
Take this Prototype for inspiration - https://cristi5833.softr.app/new Keep the Column Header Fixed Add Sort by in the headers itself for all columns Add Context Length Column Add Shortcut to model API screen ( Open Porta )
Aman Sharma About 1 month ago
👏🏻 Feedback
Planned
Web Crawl Node
Create a Web Crawl Node to allow Lamatic to ingest and store data from a website to be accessed downstream. Specific requirements: 1) Accept a URL, multiple URLs, a sitemap.xml, or a URL pattern regex as a parameter to direct the crawl. Consider what would be needed to accept login credentials as a param to enable ingesting content behind a login (future). 2) Support the ability to store important metadata along with the visible content (for instance, the hreflang tag that will indicate the language & geography of the target audience). Consider a default metadata capture config that can be optionally reduced or expanded (future). 3) Generate status and error messaging: Accept parameters that configure status notifications (what notifications to send & to whom?). Thoughts/Questions: How to tell the Node where to store the crawled content? How should the visibility of this store be determined (in other words, is this store available only to this workflow, others within the Project, or others within the Organization)? Should the Node support an option to simultaneously vectorize the content as part of the crawl (to reduce storage needs)? Can/should we use the attribute on the Sitemap.xml to trigger this Node? Can/should the Node capture Image, Audio, and/or Video content? How should notifications & error handling work (regarding the status of the crawl)?
cwhiteman About 1 month ago
💡 Feature Requests
Planned
Web Crawl Node
Create a Web Crawl Node to allow Lamatic to ingest and store data from a website to be accessed downstream. Specific requirements: 1) Accept a URL, multiple URLs, a sitemap.xml, or a URL pattern regex as a parameter to direct the crawl. Consider what would be needed to accept login credentials as a param to enable ingesting content behind a login (future). 2) Support the ability to store important metadata along with the visible content (for instance, the hreflang tag that will indicate the language & geography of the target audience). Consider a default metadata capture config that can be optionally reduced or expanded (future). 3) Generate status and error messaging: Accept parameters that configure status notifications (what notifications to send & to whom?). Thoughts/Questions: How to tell the Node where to store the crawled content? How should the visibility of this store be determined (in other words, is this store available only to this workflow, others within the Project, or others within the Organization)? Should the Node support an option to simultaneously vectorize the content as part of the crawl (to reduce storage needs)? Can/should we use the attribute on the Sitemap.xml to trigger this Node? Can/should the Node capture Image, Audio, and/or Video content? How should notifications & error handling work (regarding the status of the crawl)?
cwhiteman About 1 month ago
💡 Feature Requests
Trigger Node: prompt with list of valid triggers on double-click
User was having difficulty dragging nodes and tried to dbl-click the Trigger Node to pop a list of valid triggers.
cwhiteman 3 days ago
UI/UX
👏🏻 Feedback
Trigger Node: prompt with list of valid triggers on double-click
User was having difficulty dragging nodes and tried to dbl-click the Trigger Node to pop a list of valid triggers.
cwhiteman 3 days ago
UI/UX
👏🏻 Feedback
LLM Credential Naming in the Index to DB node is confusing to users
The way we present the name of the model is confusing here (and perhaps elsewhere).
cwhiteman 4 days ago
UI/UX
👏🏻 Feedback
LLM Credential Naming in the Index to DB node is confusing to users
The way we present the name of the model is confusing here (and perhaps elsewhere).
cwhiteman 4 days ago
UI/UX
👏🏻 Feedback
Allow user to see node detail & config simultaneously
Users occasionally want to see where in the config they are as they edit the node params. Suggest making it possible to pin both the Node Parameter side panel and the Config side panel (so both are visible) and defaulting the Config side panel to the place in the config where the current node appears (maybe even highlighting the node to make it even more clear).
cwhiteman 4 days ago
UI/UX
👏🏻 Feedback
Allow user to see node detail & config simultaneously
Users occasionally want to see where in the config they are as they edit the node params. Suggest making it possible to pin both the Node Parameter side panel and the Config side panel (so both are visible) and defaulting the Config side panel to the place in the config where the current node appears (maybe even highlighting the node to make it even more clear).
cwhiteman 4 days ago
UI/UX
👏🏻 Feedback
Expand "clickable area" within nodes & workflows (in the visual editor)
Users often click in the box that represents a node or workflow and expect that to open it. They don’t realize they have to click on the text. If possible, expand the clickable area to include the entire box. For an example, look at 32:00 in this onboarding video.
cwhiteman 4 days ago
👏🏻 Feedback
Expand "clickable area" within nodes & workflows (in the visual editor)
Users often click in the box that represents a node or workflow and expect that to open it. They don’t realize they have to click on the text. If possible, expand the clickable area to include the entire box. For an example, look at 32:00 in this onboarding video.
cwhiteman 4 days ago
👏🏻 Feedback
Google Drive: set expectations, verify app, and narrow permissions
When adding Google Drive as a data source, Jason Reichle at 15:28 encounters a warning “Google hasn’t verified this app”, but proceeds only with my encouragement. He then explains how he would like to limit granted access to a specific folder (Al Serize on 9/4 had same request). Recommended action Items to increase trust & reduce abandons: Set the user’s expectations before they get the warning. Update the email address referenced in the warning from [email protected] to [email protected] (more trusted). Get Lamatic verified by Google. Limit permissions to something less than the entire Google Drive. #1 - Set Expectations: A simple way to boost trust is to explain the permissions they’ll be asked to grant in advance of the Google prompt (see highlighted area in the screenshot below). Suggested message text (for the highlighted area in the screenshot above): Add Credentials Add a unique name to reference this Credential within the workflow builder. Note: Google will ask you to grant lamatic.ai access to your Google Drive. This access is used strictly by the Lamatic application to allow you to create workflows using the information found on the authorized Google Drive. #2 - Update Lamatic app author Reference a more trusted email address than [email protected] on the warning below (e.g., [email protected]). #3 - Get Lamatic verified by Google: Not sure what is required to do this, but getting verified would increase trust a lot. #4 - Narrow the permissions: Not sure if this is even possible, but the screen below is scary. Multiple users have requested that permissions be limited here to a specific folder (they have sensitive stuff in other folders and don’t want to grant access to this data).
cwhiteman 4 days ago
🔌 Integration
Google Drive: set expectations, verify app, and narrow permissions
When adding Google Drive as a data source, Jason Reichle at 15:28 encounters a warning “Google hasn’t verified this app”, but proceeds only with my encouragement. He then explains how he would like to limit granted access to a specific folder (Al Serize on 9/4 had same request). Recommended action Items to increase trust & reduce abandons: Set the user’s expectations before they get the warning. Update the email address referenced in the warning from [email protected] to [email protected] (more trusted). Get Lamatic verified by Google. Limit permissions to something less than the entire Google Drive. #1 - Set Expectations: A simple way to boost trust is to explain the permissions they’ll be asked to grant in advance of the Google prompt (see highlighted area in the screenshot below). Suggested message text (for the highlighted area in the screenshot above): Add Credentials Add a unique name to reference this Credential within the workflow builder. Note: Google will ask you to grant lamatic.ai access to your Google Drive. This access is used strictly by the Lamatic application to allow you to create workflows using the information found on the authorized Google Drive. #2 - Update Lamatic app author Reference a more trusted email address than [email protected] on the warning below (e.g., [email protected]). #3 - Get Lamatic verified by Google: Not sure what is required to do this, but getting verified would increase trust a lot. #4 - Narrow the permissions: Not sure if this is even possible, but the screen below is scary. Multiple users have requested that permissions be limited here to a specific folder (they have sensitive stuff in other folders and don’t want to grant access to this data).
cwhiteman 4 days ago
🔌 Integration
Cost forecasting
Users frequently wish that Lamatic could help them forecast and manage the cost of running AI workflows (3rd party LLM & API costs). Is there some way to accomplish this? Doing so has the potential to create a lot of goodwill & word-of-mouth virality. Consider a module that estimates cost per thousand runs based on a published rate (which the user could adjust if they have special pricing with the vendor). Consider a module that makes LLM and/or workflow suggestions to save money.
cwhiteman 5 days ago
High Priority
💡 Feature Requests
Cost forecasting
Users frequently wish that Lamatic could help them forecast and manage the cost of running AI workflows (3rd party LLM & API costs). Is there some way to accomplish this? Doing so has the potential to create a lot of goodwill & word-of-mouth virality. Consider a module that estimates cost per thousand runs based on a published rate (which the user could adjust if they have special pricing with the vendor). Consider a module that makes LLM and/or workflow suggestions to save money.
cwhiteman 5 days ago
High Priority
💡 Feature Requests
Node category order in the left nav of the workflow builder isn't clearly logical
Users typically don’t understand why these nodes are organized as they are: It should be clear why they are ordered this way to users (e.g., alphabetical or the order in which they are typically used). Maybe there’s a better order than this, but it seems more logical to order them as follows: Triggers Data GenAI or Generate (rather than “AI” to capture the idea that these nodes create something) Flow (consider moving “API” here as it seems more similar to a “Code” node than the nodes that appear under Data) Response (eliminate “Apps” as it’s odd to see Slack in Trigger and Apps, but not in Response - feels like we’re mixing paradigms)
cwhiteman 5 days ago
UI/UX
👏🏻 Feedback
Node category order in the left nav of the workflow builder isn't clearly logical
Users typically don’t understand why these nodes are organized as they are: It should be clear why they are ordered this way to users (e.g., alphabetical or the order in which they are typically used). Maybe there’s a better order than this, but it seems more logical to order them as follows: Triggers Data GenAI or Generate (rather than “AI” to capture the idea that these nodes create something) Flow (consider moving “API” here as it seems more similar to a “Code” node than the nodes that appear under Data) Response (eliminate “Apps” as it’s odd to see Slack in Trigger and Apps, but not in Response - feels like we’re mixing paradigms)
cwhiteman 5 days ago
UI/UX
👏🏻 Feedback