Automate knowledge bases
with an agentic RAG
Connect to database, process information, and deliver results,
all powered by AI agents and RAG
Trusted by users worldwide
connect to
datasource
process
information
with AI
deliver
results
Give it a go!
INPUT
Knowledge Base
OpenAI's Movement in AI Agent Products
OpenAI, a frontrunner in large language model, has also been pioneering the implementation of agent-based products. Throughout the past year, OpenAI has unveiled multiple agent products. I will examine the progression of OpenAI's agent products and their influence in this article.
Plugin Store
The earliest commercial application of agents originated from OpenAI's Plugin store launched in April 2023. Users could specifying up to three plugins an agent could access and assist in chatting with users.
Initially released in early April 2023, it was regard as the next-generation app store. However, following user numbers did not meet expectations. Finally it was shut down in November 2023 and replaced by GPTs and All-tools.
GPTs
GPTs was launched as the agent store on Dev Day in November 2023. It focused on the ability to quickly develop and deploy one's own agent through natural language dialogue, targeting ToC scenarios. Initially, it met with high expectations.
However, it was later proven that GPTs cannot meet the needs of in-depth development and cannot handle complex scenarios, whereas simple scenarios can be completely solved using all-tools agent.
Finally, GPTs became more like a tool for startups to attract users to their products, rather than a cornerstone for a thriving ecosystem.
All-tools Agent
All-tools agent was launched on Dev Day in November 2023. It integrated three tools: web searching, code interpreting, and DALLE-3. Additionally, it implicitly included web browsing and local RAG.
These tools integrations, by transferring the cost of configuring and selecting tools onto the model, removes the need for users to manually set up their own tools, objectively decrease user's effort.
However, OpenAI secretly removed the web searching tool from All-tools agent in mid-2024 for selected users. This AB test was so subtle that many people did not notice it.
This change was possibly because using search in scenarios where it was not intended could lower the quality of responses. Moreover, recognizing users' intent on whether to use search for answering questions proved challenging. Therefore,OpenAI's product approach to this issue remains ambiguous.
This may suggest that there is differentiation between two kinds of products: AI search engine and ChatBot.
Code interpreter (Data analysis)
Code interpreter was launched in early July 2023, featuring the ability for ChatGPT to run code automatically after finishing it. If the code results in an error, it automatically generates new code based on the error and attempts to run it again. If there are three or more consecutive errors, a response of 'Unable to complete the task' will be given. Code interpreter can automatically debug to some extent, making it quite practical.
Subsequently, Code interpreter was renamed to Data analysis. Many user experience enhancements were made around data analysis scenarios. For example, images generated during data processing can be enlarged and centered, and the chat bar has been moved to the sidebar, allowing users to chat with the figure.
OpenAI-o1
OpenAI-o1 is not a product, but a model. This model was released in September 2024, aiming to solve complex problems by increasing inference costs and using Chain of Thought (CoT). It requires thinking before providing an answer, so it can be considered a form of agent, deciding what to think about next based on its earlier thoughts. This step-by-step thinking helps the model solve more difficult problems. This methodical approach enables the model to tackle complex problems that were previously challenging to solve.
Summary
OpenAI has tried many agent scenarios. Plugin store and GPTs have mixed results, not quite a success. In contrast, the Code Interpreter and All-tools Agent have shown considerable practical utility.
Chunks
[
{
"content": "OpenAI's Movement in AI Agent Products\n\n",
"metadata": {
"id": 0
}
},
{
"content": "OpenAI, a frontrunner in large language model, has also been pioneering the implementation of agent-based products. Throughout the past year, OpenAI has unveiled multiple agent products. I will examine the progression of OpenAI's agent products and their influence in this article.\n\n",
"metadata": {
"id": 1
}
},
{
"content": "Plugin Store\nThe earliest commercial application of agents originated from OpenAI's Plugin store launched in April 2023. Users could specifying up to three plugins an agent could access and assist in chatting with users.\n\n",
"metadata": {
"id": 2
}
},
{
"content": "Initially released in early April 2023, it was regard as the next-generation app store. However, following user numbers did not meet expectations. Finally it was shut down in November 2023 and replaced by GPTs and All-tools.\n\n",
"metadata": {
"id": 3
}
},
{
"content": "GPTs\nGPTs was launched as the agent store on Dev Day in November 2023. It focused on the ability to quickly develop and deploy one's own agent through natural language dialogue, targeting ToC scenarios. Initially, it met with high expectations.\n\n",
"metadata": {
"id": 4
}
},
{
"content": "However, it was later proven that GPTs cannot meet the needs of in-depth development and cannot handle complex scenarios, whereas simple scenarios can be completely solved using all-tools agent.\n\n",
"metadata": {
"id": 5
}
},
{
"content": "Finally, GPTs became more like a tool for startups to attract users to their products, rather than a cornerstone for a thriving ecosystem.\n\n",
"metadata": {
"id": 6
}
},
{
"content": "All-tools Agent\nAll-tools agent was launched on Dev Day in November 2023. It integrated three tools: web searching, code interpreting, and DALLE-3. Additionally, it implicitly included web browsing and local RAG.\n\n",
"metadata": {
"id": 7
}
},
{
"content": "These tools integrations, by transferring the cost of configuring and selecting tools onto the model, removes the need for users to manually set up their own tools, objectively decrease user's effort.\n\n",
"metadata": {
"id": 8
}
},
{
"content": "However, OpenAI secretly removed the web searching tool from All-tools agent in mid-2024 for selected users. This AB test was so subtle that many people did not notice it.\n\n",
"metadata": {
"id": 9
}
},
{
"content": "This change was possibly because using search in scenarios where it was not intended could lower the quality of responses. Moreover, recognizing users' intent on whether to use search for answering questions proved challenging. Therefore,OpenAI's product approach to this issue remains ambiguous.\n\n",
"metadata": {
"id": 10
}
},
{
"content": "This may suggest that there is differentiation between two kinds of products: AI search engine and ChatBot.\n\n",
"metadata": {
"id": 11
}
},
{
"content": "Code interpreter (Data analysis)\nCode interpreter was launched in early July 2023, featuring the ability for ChatGPT to run code automatically after finishing it. If the code results in an error, it automatically generates new code based on the error and attempts to run it again. If there are three or more consecutive errors, a response of 'Unable to complete the task' will be given. Code interpreter can automatically debug to some extent, making it quite practical.\n\n",
"metadata": {
"id": 12
}
},
{
"content": "Subsequently, Code interpreter was renamed to Data analysis. Many user experience enhancements were made around data analysis scenarios. For example, images generated during data processing can be enlarged and centered, and the chat bar has been moved to the sidebar, allowing users to chat with the figure.\n\n",
"metadata": {
"id": 13
}
},
{
"content": "OpenAI-o1\nOpenAI-o1 is not a product, but a model. This model was released in September 2024, aiming to solve complex problems by increasing inference costs and using Chain of Thought (CoT). It requires thinking before providing an answer, so it can be considered a form of agent, deciding what to think about next based on its earlier thoughts. This step-by-step thinking helps the model solve more difficult problems. This methodical approach enables the model to tackle complex problems that were previously challenging to solve.\n\n",
"metadata": {
"id": 14
}
},
{
"content": "Summary\nOpenAI has tried many agent scenarios. Plugin store and GPTs have mixed results, not quite a success. In contrast, the Code Interpreter and All-tools Agent have shown considerable practical utility.\n\n",
"metadata": {
"id": 15
}
},
{
"content": "Plugin store VS All-tools agent\nAn agent relies on tools for work must have enough model-layer data about these tools. Simply using prompts to call tools, as done in the plugin store, is currently ineffective with the model's capabilities.\n\n",
"metadata": {
"id": 16
}
},
{
"content": "All-tools agent (with web search) VS All-tools agent (without web search)\nEven a pioneer like OpenAI struggles with deciding when to use a search engine for support in general scenarios. Currently, OpenAI has simply handed this issue over to users partly (deciding to use ChatGPT or SearchGPT), which may also mean opportunities for some AI searching startups.\n\n",
"metadata": {
"id": 17
}
},
{
"content": "Code interpreter VS GPTs\nA practical agent requires more than just prompt-level programming. It necessitates numerous decision-making mechanisms, which are often achieved by code rather than natural language prompt. Ironically, OpenAI's own assistant platform can't create an agent as advanced as the code interpreter.",
"metadata": {
"id": 18
}
}
]Retrieved Contexts
[
{
"id": "9361f805-eddb-4bdc-b59f-3ec04e90a8f2",
"content": "However, OpenAI secretly removed the web searching tool from All-tools agent in mid-2024 for selected users. This AB test was so subtle that many people did not notice it.\n\n",
"metadata": {
"id": "9",
"info": [
{
"content": "OpenAI's Movement in AI Agent Products\n\n",
"metadata": {
"id": 0
}
},
{
"content": "OpenAI, a frontrunner in large language model, has also been pioneering the implementation of agent-based products. Throughout the past year, OpenAI has unveiled multiple agent products. I will examine the progression of OpenAI's agent products and their influence in this article.\n\n",
"metadata": {
"id": 1
}
},
{
"content": "Plugin Store\nThe earliest commercial application of agents originated from OpenAI's Plugin store launched in April 2023. Users could specifying up to three plugins an agent could access and assist in chatting with users.\n\n",
"metadata": {
"id": 2
}
},
{
"content": "Initially released in early April 2023, it was regard as the next-generation app store. However, following user numbers did not meet expectations. Finally it was shut down in November 2023 and replaced by GPTs and All-tools.\n\n",
"metadata": {
"id": 3
}
},
{
"content": "GPTs\nGPTs was launched as the agent store on Dev Day in November 2023. It focused on the ability to quickly develop and deploy one's own agent through natural language dialogue, targeting ToC scenarios. Initially, it met with high expectations.\n\n",
"metadata": {
"id": 4
}
},
{
"content": "However, it was later proven that GPTs cannot meet the needs of in-depth development and cannot handle complex scenarios, whereas simple scenarios can be completely solved using all-tools agent.\n\n",
"metadata": {
"id": 5
}
},
{
"content": "Finally, GPTs became more like a tool for startups to attract users to their products, rather than a cornerstone for a thriving ecosystem.\n\n",
"metadata": {
"id": 6
}
},
{
"content": "All-tools Agent\nAll-tools agent was launched on Dev Day in November 2023. It integrated three tools: web searching, code interpreting, and DALLE-3. Additionally, it implicitly included web browsing and local RAG.\n\n",
"metadata": {
"id": 7
}
},
{
"content": "These tools integrations, by transferring the cost of configuring and selecting tools onto the model, removes the need for users to manually set up their own tools, objectively decrease user's effort.\n\n",
"metadata": {
"id": 8
}
},
{
"metadata": {
"id": 9
}
},
{
"content": "This change was possibly because using search in scenarios where it was not intended could lower the quality of responses. Moreover, recognizing users' intent on whether to use search for answering questions proved challenging. Therefore,OpenAI's product approach to this issue remains ambiguous.\n\n",
"metadata": {
"id": 10
}
},
{
"content": "This may suggest that there is differentiation between two kinds of products: AI search engine and ChatBot.\n\n",
"metadata": {
"id": 11
}
},
{
"content": "Code interpreter (Data analysis)\nCode interpreter was launched in early July 2023, featuring the ability for ChatGPT to run code automatically after finishing it. If the code results in an error, it automatically generates new code based on the error and attempts to run it again. If there are three or more consecutive errors, a response of 'Unable to complete the task' will be given. Code interpreter can automatically debug to some extent, making it quite practical.\n\n",
"metadata": {
"id": 12
}
},
{
"content": "Subsequently, Code interpreter was renamed to Data analysis. Many user experience enhancements were made around data analysis scenarios. For example, images generated during data processing can be enlarged and centered, and the chat bar has been moved to the sidebar, allowing users to chat with the figure.\n\n",
"metadata": {
"id": 13
}
},
{
"content": "OpenAI-o1\nOpenAI-o1 is not a product, but a model. This model was released in September 2024, aiming to solve complex problems by increasing inference costs and using Chain of Thought (CoT). It requires thinking before providing an answer, so it can be considered a form of agent, deciding what to think about next based on its earlier thoughts. This step-by-step thinking helps the model solve more difficult problems. This methodical approach enables the model to tackle complex problems that were previously challenging to solve.\n\n",
"metadata": {
"id": 14
}
},
{
"content": "Summary\nOpenAI has tried many agent scenarios. Plugin store and GPTs have mixed results, not quite a success. In contrast, the Code Interpreter and All-tools Agent have shown considerable practical utility.\n\n",
"metadata": {
"id": 15
}
},
{
"content": "Plugin store VS All-tools agent\nAn agent relies on tools for work must have enough model-layer data about these tools. Simply using prompts to call tools, as done in the plugin store, is currently ineffective with the model's capabilities.\n\n",
"metadata": {
"id": 16
}
},
{
"content": "All-tools agent (with web search) VS All-tools agent (without web search)\nEven a pioneer like OpenAI struggles with deciding when to use a search engine for support in general scenarios. Currently, OpenAI has simply handed this issue over to users partly (deciding to use ChatGPT or SearchGPT), which may also mean opportunities for some AI searching startups.\n\n",
"metadata": {
"id": 17
}
},
{
"content": "Code interpreter VS GPTs\nA practical agent requires more than just prompt-level programming. It necessitates numerous decision-making mechanisms, which are often achieved by code rather than natural language prompt. Ironically, OpenAI's own assistant platform can't create an agent as advanced as the code interpreter.",
"metadata": {
"id": 18
}
}
],
"path": [
9,
"content"
],
"key_1": "content",
"list_0": 9
},
"score": 0.159702689700836
},
{
"id": "3d76699c-b224-4076-bed7-8de84ba5f1de",
"content": "However, OpenAI secretly removed the web searching tool from All-tools agent in mid-2024 for selected users. This AB test was so subtle that many people did not notice it.\n\n",
"metadata": {
"id": "9",
"info": [
{
"content": "OpenAI's Movement in AI Agent Products\n\n",
"metadata": {
"id": 0
}
}
]
}
}
]INPUT
Query
Which OpenAI product went offline shortly after its launch?
OUTPUT
Answer
The OpenAI product that went offline shortly after its launch is the Plugin Store. It was launched in April 2023 but was shut down in November 2023 due to user numbers not meeting expectations.
Chunking
Retrieve
Generate
Press enter or space to select a node.You can then use the arrow keys to move the node around. Press delete to remove it and escape to cancel.
Press enter or space to select an edge. You can then press delete to remove it or escape to cancel.
Click to activate
Self-Evolving
RAG Engine
Upload data, score the result,
improve retrieving pipeline better and better
Build Your Own
Retrieving Pipeline
on-going,
fast, easy, and integrate it into your enterprise
Ask Puppy
Questions
What is PuppyAgent?
PuppyAgent is an automated AI knowledge builder that creates RAG pipelines based on your enterprise's own knowledge base, empowering businesses to automate workflows using their proprietary expertise.
Is PuppyAgent free to use?
PuppyAgent provides a free plan for individual users. For teams or enterprises requiring enhanced functionality, we offer Professional plans tailored to meet more advanced needs.
What can PuppyAgent do?
PuppyAgent enables you to construct Retrieval-Augmented Generation (RAG) systems for your enterprise knowledge base. It can be applied to various use cases, including supports chatbots community chatbots, AI-powered search engine optimization strategies, spreadsheet automation, and various other applications.
What is the mission of PuppyAgent?
PuppyAgent's mission is to reshape the world with AI agents. We are initiating this vision by focusing on knowledge base and Retrieval-Augmented Generation (RAG) technologies.
How can I contact the PuppyAgent team?
You can reach out to our team by emailing to the founder: guantum@puppyagent.com,
and follow PuppyAgent on Twitter and DM us: https://x.com/PuppyAgentTech
Automate Different ?