AI case study

Personalized coding support

by
University of California, Berkeley
Context

UC Berkeley developed 61A-Bot, an AI chatbot using GPT-4 via Azure OpenAI Service, to assist students in their Intro to Computer Science class. The bot provides personalized hints and feedback to help students solve complex coding challenges independently, integrated within their coding environment.

Results

Reduced homework completion times by over 30 minutes per assignment, increased availability of support options, and enhanced learning experiences for over 2,000 students.

Results not reported in the source
Industry
Education
Published
September 25, 2024
Agent type
Employee Agents
AI provider
Microsoft
Models/tools
Not disclosed
ICE score
448
The ICE framework in this database provides a quick way to assess the feasibility and potential impact of AI use cases, with higher scores signaling more actionable opportunities.

Impact: Potential benefits to the business.

Confidence: Likelihood of achieving expected results.

Ease: Simplicity of implementation in terms of resources and time.

ICE Score: Calculated by multiplying the component scores.

Note:
Each score is AI-generated based on available data and should be viewed merely as a general guideline for deeper exploration of the use cases.
Impact
8
Confidence
8
Ease
7

46

AI use cases in

Education

See All

Rising Academies

Education
Use case
Accessible mobile tutoring
Context

Rising Academies integrated Claude-powered chatbots into mobile educational tools via WhatsApp to provide both a virtual math tutor (Rori) and a teacher support system (Tari). Rori delivers personalized math lessons through a mix of pre-written lesson plans and dynamic conversations, while Tari offers on-demand curriculum and lesson planning support for teachers. These solutions enhanced personalized learning and professional development in regions with limited access to traditional edtech.

Models/tools
...
1

Pensieve

Education
Use case
Personalized student support
Context

Pensieve integrated Anthropic's Claude models (Claude 3.5 Sonnet and Claude 3.7 Sonnet) to build AI teaching assistants that automate grading and provide 24/7 personalized tutoring. The system clusters student submissions to calibrate grading rubrics and transforms static PDFs into interactive worksheets while enforcing instructor-controlled policies. This integration streamlines course management workflows and enhances real‐time classroom analytics.

Super Teacher

Education
Use case
Building learning tools and making content
Context

Super Teacher integrated Anthropic's Claude to generate initial code for interactive educational tools and draft lesson plans for subjects ranging from pre-K to 5th grade. They embedded the AI into both software development and content creation workflows with mandatory human review to ensure safety and quality standards. This integration streamlined operational processes, enabling engineering and content teams to focus on higher-level development and creative enhancements.

Models/tools
...
1
Explore industries

321

companies using

Employee Agents

See All
Use case
Fast content creation
Context

Cox Automotive integrated Claude via Amazon Bedrock into its portfolio by first creating a sandbox environment to evaluate performance metrics and then selecting Claude 3.5 Sonnet for complex tasks and Claude 3.5 Haiku for high-volume content generation. They automated personalized dealer-consumer communications, generated engaging vehicle listing descriptions, and produced SEO-optimized blog posts, while also streamlining internal data governance through automated metadata generation. This integration optimized operational efficiency across marketing and internal data processes.

Models/tools
...
2
Use case
Reduce report writing burden
Context

Quillit integrated Anthropic’s Claude to automate qualitative research tasks by summarizing interview transcripts, generating contextual citations, and threading conversation data into comprehensive reports. They implemented the AI tool into their existing research workflow within three months, streamlining report writing, transcription, and analysis while ensuring data security and high precision.

Models/tools
...
2
Use case
Faster retail transformation
Context

TCS partnered with Google Cloud to integrate advanced AI and generative AI capabilities into retail service offerings. They launched the Google Cloud Gemini Experience Center at their Retail Innovation Lab in Chennai, enabling retail clients to ideate, prototype, and co-develop tailored AI solutions that optimize supply chain, warehouse receiving, customer insights, and content creation. This approach automated processes using tools like Vertex AI Vision for warehouse receiving and leveraged Vertex AI with Gemini 1.5 Pro and speech-to-text to transform service centers.

Models/tools
...
4
Explore agents

251

solutions powered by

Microsoft

See All
Use case
High-volume student queries
Context

Physics Wallah developed 'Gyan Guru', a hyperpersonalized conversational study companion to address the unique academic and support needs of its 2 million daily users. The system was implemented by indexing over one million Q&As and ten million solved doubts in a vector database, then leveraging a Retrieval-Augmented Generation (RAG) approach integrated with Azure OpenAI to deliver individualized, context-aware responses. This integration streamlined various student interactions including academic queries, product-related issues, and general support, reducing reliance on human subject matter experts.

Models/tools
...
1
Use case
Streamlined executive operations
Context

Brandix adopted the Microsoft 365 Copilot suite via the Early Access Program to integrate AI into key executive workflows, automating meeting transcript-based action tracking in Teams, accelerating pitch deck creation in PowerPoint, and streamlining document generation in Word while leveraging AI-enhanced querying in Power BI and efficient information retrieval via Copilot Chat. This implementation transformed internal communications, reporting, and presentation preparation processes by significantly reducing manual effort.

Models/tools
...
2
Use case
Future-proof IT operations
Context

University of Oxford’s IT Services department deployed Microsoft 365 Copilot across its 400+ staff as part of a pilot program aimed at embedding generative AI into research, teaching, and administrative workflows. They implemented extensive onboarding sessions, community engagement via Microsoft Teams, and established an acceleration team to integrate Copilot with other business applications. This deployment streamlined routine tasks such as document generation, summarization, and meeting support, fostering innovation within the department.

Models/tools
...
1
Explore AI providers

284

AI use cases in

North America

See All
Use case
Fast content creation
Context

Cox Automotive integrated Claude via Amazon Bedrock into its portfolio by first creating a sandbox environment to evaluate performance metrics and then selecting Claude 3.5 Sonnet for complex tasks and Claude 3.5 Haiku for high-volume content generation. They automated personalized dealer-consumer communications, generated engaging vehicle listing descriptions, and produced SEO-optimized blog posts, while also streamlining internal data governance through automated metadata generation. This integration optimized operational efficiency across marketing and internal data processes.

Models/tools
...
2
Use case
Faster tax form processing
Context

Intuit integrated Google Cloud’s Document AI and Gemini models into its GenOS platform to automate the autofill of ten common U.S. tax forms, including complex 1099 and 1040 forms. The solution extracts and categorizes data from uploaded documents, drastically reducing manual data entry for TurboTax customers. This integration streamlines tax preparation workflows and improves speed and accuracy.

Models/tools
...
2
Use case
Democratized data access
Context

Block implemented Anthropic’s Claude models (Claude 3.5 Sonnet and Claude 3.7 Sonnet) on its Databricks platform to power its internal AI agent, codename goose. They integrated the LLM using secure OAuth-enabled connections and a custom MCP server to connect internal databases and tools, enabling employees across all roles to auto-generate SQL queries, analyze complex data, and automate workflows. This agentic integration streamlined software development, design prototyping, and data analysis by translating user intents into actionable insights.

Models/tools
...
2
Explore regions
Thoughts & ideas