Update README.md #310
Update README.md #310
Conversation
Maxim's edited and updated ReadMe
|
Note: CircleCI check fails as I am not a registered user. |
| @@ -5,13 +5,13 @@ | |||
|
|
|||
| # DevChat Visual Studio Code Extension | |||
|
|
|||
| **An effective, down-to-earth AI coding assistant that blends AI power and manual control.** | |||
| **The Truly Collaboartive AI Coding Assistant. The Best of AI. The Best of You. Integrated Seamlessly.** | |||
|
|
|||
There was a problem hiding this comment.
Can we somehow point "collaborative" to collaboration between humans and AI? Now most readers may take it as a regular meaning which is not our unique feature.
"The Best of AI. The Best of You. Integrated Seamlessly." I don't think most readers can really understand what this is about. If not, pretty wording itself wouldn't be strong. Can we emphasize our pragmatic approach to AI? That means we should manually control the context and other processes when necessary so that the AI power can be made really effective. Most other tools go too far in leveraging AI or automation that actually harms its effectiveness. We are not building an imaginary or experimental tool. We are building a truly productive assistant, but the precondition is that we humans do our job.
|
|
||
| 🛠️ No excessive automation, just right AI where it works. | ||
| 🛠️ AI integrated where you want it, when you need it, with no disruption to your flow. | ||
|
|
There was a problem hiding this comment.
The emphasis is not about "disruption". Actually, the opposite. Humans must be involved. Some steps should not be automated or AI'ed at all. That's why I wrote No excessive automation.
Also, the problem now is most users are not sure where or when AI is needed. But if you use our tool, our design will frame your way to use AI and only use it where it really works.
| @@ -30,30 +30,30 @@ | |||
|
|
|||
| ## What is DevChat? | |||
|
|
|||
| DevChat is an open-source platform that empowers developers to leverage AI for code generation and documentation. We aim to go beyond simple code auto-completion and limited operations on code snippets. DevChat offers a highly *practical* and *effective* way for developers to interact and collaborate with large language models (LLMs). | |||
| DevChat is an open-source platform that empowers developers to more naturally and effectively integrate AI into code generation and documentation. DevChat aims to go beyond simple auto-completion and limited operations on code snippets. DevChat offers a highly *practical* and *effective* way for developers to interact and collaborate with large language models (LLMs), DevChat is the tool that works for you, no need to change your workflow. | |||
|
|
|||
There was a problem hiding this comment.
I guess "naturally" and "no need to change your workflow" come from your understanding of "no disruption". As aforementioned, it is not like that. Let's tune these.
There was a problem hiding this comment.
Hi @MaximDub and @basicthinker I was thinking of a two liner introduction as shown below.
DevChat, a tool that brings prompt-centric developer workflow to life using AI for writing code, docs, and much more through an innovative concept of "DevPromptOps".
|
|
||
| ## Why DevChat? | ||
|
|
||
| While there are many AI coding tools available, we developed DevChat based on our practical insights from generating tens of thousands of lines of code. DevChat makes the following distinctive design choices: | ||
| We spent years on code analysis, static-analysis, and DevOps improvements, working with hundreds of companies around the world. The insights we have picked up in this process are all incorporated into DevChat. The techniques, approaches, and decisions that drive success for companies large and small inform every detail of DevChat. You'll find some distinctive design choices: | ||
|
|
There was a problem hiding this comment.
Hmm... Code analysis makes sense. Most others are not that relevant so it may sound over selling. Maybe we can position us as dev tool builders like creators of Apache DevLake? In addition, the amount of code we generate is anyway better evidence of our experience as this is much more closely related. Tens of thousands lines of code is not a small number -- most developers should know this.
|
|
||
| - **Precise manual control over the context embedded in a prompt**. Precise control over context is the key to effective AI use. We find that most other "intelligent" or "automatic" tools tend to over-guess what a user needs to put into a prompt. That typically introduces more noise than LLMs can effectively manage. | ||
| - **A simple, extensible prompt directory**. This enables developers or teams to easily integrate their own prompt templates into DevChat, avoiding significant engineering effort or a steep learning curve. You don't need a complex framework to make AI work for you. All it takes is a standard editor operating on your filesystem. | ||
| - **Precise manual control over the context embedded in a prompt**. DevChat won't create new work for you, because it ensures that context drives everything. Precise control over context is the key to effective AI use. We find that most other "intelligent" or "automatic" tools tend to over-guess what a user needs to put into a prompt. That typically introduces more noise than LLMs can effectively manage. |
There was a problem hiding this comment.
The point is not that the context drives everything. We actually require humans do a little bit more work in specifying the right context but makes AI much more effective as return.
basicthinker
added
documentation
Maxim's edited and updated ReadMe. Improved the descriptions, made changes for readability and clarity.