69 lines
3.5 KiB
Markdown
69 lines
3.5 KiB
Markdown
tags:: [[#zotero]]
|
||
title:: @LowcoBot: Towards Chatting With Low-Code Platforms
|
||
item-type:: [[journalArticle]]
|
||
original-title:: LowcoBot: Towards Chatting With Low-Code Platforms
|
||
language:: en
|
||
authors:: [[Francisco Martínez-Lasaca]], [[Pablo Díez]], [[Esther Guerra]], [[Juan de Lara]]
|
||
library-catalog:: Zotero
|
||
links:: [Local library](zotero://select/library/items/E92ZL76F), [Web library](https://www.zotero.org/users/1039502/items/E92ZL76F)
|
||
|
||
- [[Abstract]]
|
||
- Low-code platforms are gaining momentum, allowing the creation of complex applications directly from the browser. This allows their use by individuals with a wide range of backgrounds, but they pose some problems. On the one hand, newcomers may want to grasp the platform capabilities or pinpoint where can they access some functionality, which may prove difficult without guidance. On the other hand, their navigability can be complex: their functionality can be distributed across many webpages and user interfaces, each managing different concepts. Additionally, users may deem more convenient addressing some tasks using natural language instead of navigating visual interfaces. For these reasons, we introduce LowcoBot, a model-driven solution to generate LLM-based chatbots out of low-code platform design models. We demonstrate its capabilities by generating a chatbot for Dandelion+, a low-code platform built within an industrial context, and showing the range of tasks it supports out-of-the-box.
|
||
- ### Attachments
|
||
- [STAF_2024_paper_66.pdf](zotero://select/library/items/EGACKK83) {{zotero-imported-file EGACKK83, "STAF_2024_paper_66.pdf"}}
|
||
- ### Notes
|
||
- # Annotazioni
|
||
(10/6/2024, 12:25:34)
|
||
|
||
- “their functionality can be distributed across many webpages and user interfaces, each managing different concepts.” (Martínez-Lasaca et al., p. 1) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “integrating conversational assistants – or chatbots – into low-code platforms can improve their navigability by providing users with more ways to interact with them –” (Martínez-Lasaca et al., p. 1) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “odel-driven engineering (MDE) approach [3] that allows generating chatbots automatically” (Martínez-Lasaca et al., p. 2) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “contents of the LLM agent vary between platforms.” (Martínez-Lasaca et al., p. 3) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “o automatically populate tools and the initial prompt from a low-code platform model specification” (Martínez-Lasaca et al., p. 3) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “visual metaphors (e.g., tables, diagrams, or forms)” (Martínez-Lasaca et al., p. 4) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “capturing the relationships of the entities between the three technological spaces” (Martínez-Lasaca et al., p. 5) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “initial prompt” (Martínez-Lasaca et al., p. 5) #5fb236
|
||
* *
|
||
|
||
|
||
|
||
- “shallow way” (Martínez-Lasaca et al., p. 5) #ffd400
|
||
*I wold define such a concept. *
|
||
|
||
|
||
|
||
- “igure 4:” (Martínez-Lasaca et al., p. 6) #ffd400
|
||
*Who create this graph and when? Can we explicitly link this graph with the explanatory example presented in Fig. 1? *
|
||
|
||
|
||
|
||
- “Conclusion” (Martínez-Lasaca et al., p. 10) #ffd400
|
||
*You are assuming that the LLM knows the lowcode platform you are considering. in case you are developing a new one or you are targeting a lowcode platform the LLM is not aware of, you should support also the training phase, isn't it? I think you should discuss this side situation somewhere in the paper. * |