-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
89cb460
commit a9b8e3d
Showing
30 changed files
with
460 additions
and
15 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,46 @@ | ||
# GenAI Case Study - Careers360 | ||
|
||
Case Study: Enhancing Productivity at Careers360 with GenAI and Amazon Bedrock | ||
|
||
## Client Overview | ||
|
||
Careers360 is a prominent educational platform offering insights, reviews, and guidance to millions of students and professionals across India. The platform relies heavily on content creation, research, and updates to maintain its relevance in the rapidly changing educational landscape. | ||
|
||
## Challenge | ||
|
||
Careers360’s content team faced significant challenges in conducting extensive research for various articles, reviews, and guides. With a large repository of internal documents, public blogs, and an ever-increasing volume of content, the team often found themselves overwhelmed, spending hours manually searching through documents to gather information. | ||
|
||
## Solution by Opstree | ||
|
||
To address this challenge, Opstree leveraged **Amazon Bedrock** to implement a **Retrieval-Augmented Generation (RAG)** model. The core idea was to streamline the research process for Careers360’s content creators by building an advanced AI-driven knowledgebase capable of retrieving accurate and targeted information in real-time. | ||
|
||
## Steps Involved | ||
|
||
### 1. Knowledge Base Creation | ||
|
||
- All internal documents, including public blogs and internal guides, were collated to form the foundation of the knowledge base. | ||
- A real-time update mechanism was implemented to ensure the knowledgebase was always current with the latest information. | ||
|
||
### 2. Integration with GenAI | ||
|
||
- Using Amazon Bedrock, a GenAI model was built on top of the knowledgebase. | ||
- The RAG model enabled content creators to perform targeted research by querying the AI tool, which would retrieve specific, relevant information from the knowledgebase, vastly improving response time. | ||
|
||
### 3. Customized for Careers360 | ||
|
||
- The model was fine-tuned to understand Careers360’s tone, style, and specific needs, making it more relevant for their content creation process. | ||
- The system provided curated information that met the nuanced requirements of the content team, ensuring higher accuracy and relevance. | ||
|
||
## Results | ||
|
||
- **Increased Productivity:** The content team at Careers360 saw a dramatic reduction in research time. Tasks that previously took hours could now be completed in minutes, resulting in a **300% increase in productivity**. | ||
- **Efficient Knowledge Management:** By keeping the knowledge base updated in real-time, Careers360's team always had access to the most current information, eliminating the risk of outdated content. | ||
- **Streamlined Research Process:** The GenAI tool offered highly targeted results, saving the content creators time and effort in sifting through large volumes of information. | ||
|
||
## Impact | ||
|
||
Opstree’s solution empowered Careers360’s content team to focus on higher-level content creation, free from the burden of manual research. The implementation of the RAG model not only boosted productivity but also improved content quality, as the team could now base their articles and reports on more precise, up-to-date information. | ||
|
||
## Conclusion | ||
|
||
With Opstree’s GenAI-driven solution using Amazon Bedrock, Careers360 was able to transform its content operations, achieving greater efficiency and saving significant research time for its large team of content creators. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,39 @@ | ||
# Code Generators | ||
|
||
## Github Copilot | ||
|
||
### Commands | ||
|
||
- `@workspace` | ||
- `/doc` | ||
- `/explain` | ||
- `/fix` | ||
- `/generate` | ||
- `/optimize` | ||
- `/tests` | ||
|
||
### Links | ||
|
||
- [Get to know GitHub Copilot in VS Code and be productive IMMEDIATELY - YouTube](https://www.youtube.com/watch?v=jXp5D5ZnxGM&ab_channel=VisualStudioCode) | ||
- [Essential AI prompts for developers - YouTube](https://www.youtube.com/watch?v=H3M95i4iS5c&ab_channel=VisualStudioCode) | ||
- [Copilot Best Practices (What Not To Do) - YouTube](https://www.youtube.com/watch?v=2q0BoioYSxQ&ab_channel=VisualStudioCode) | ||
- Ghost Text | ||
- Inline Chat | ||
- Chat Panel | ||
- Comments | ||
- [Tips & Tricks for GitHub Copilot Chat in Visual Studio - Visual Studio (Windows) | Microsoft Learn](https://learn.microsoft.com/en-us/visualstudio/ide/copilot-chat-context) | ||
|
||
## Others | ||
|
||
- Tabnine | ||
- [Amazon Q Developer](https://aws.amazon.com/q/developer/) | ||
- [AI Code Reviews | CodeRabbit | Try for Free](https://coderabbit.ai/) | ||
- [AI Code Generation | Google Cloud](https://cloud.google.com/use-cases/ai-code-generation?hl=en) | ||
- [Galileo AI · Copilot for interface design](https://www.usegalileo.ai/) | ||
|
||
## Links | ||
|
||
- [15 Best AI Coding Assistant Tools in 2024 | CodiumAI](https://www.codium.ai/blog/best-ai-coding-assistant-tools/) | ||
- [Aider LLM Leaderboards | aider](https://aider.chat/docs/leaderboards/) | ||
- [BigCodeBench: The Next Generation of HumanEval](https://huggingface.co/blog/leaderboard-bigcodebench) | ||
- [BigCodeBench Leaderboard](https://bigcode-bench.github.io/) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.