metadata

title: Talk to your Multi-Agentic Architect System
emoji: 👁
colorFrom: purple
colorTo: green
sdk: docker
pinned: false
license: mit

Title

Empower people with ability to harness the value of Enterprise Architecture through Generative AI to positively impact individuals and organisations.\n

Overview

Trigger: How disruptive may Generative AI be for Enterprise Architecture Capability (People, Process and Tools)? \n Motivation: Master GenAI while disrupting Enterprise Architecture to empower individuals and organisations with ability to harness EA value and make people lives better, safer and more efficient. \n Ability: Exploit my carrer background and skillset across system development, business accumen, innovation and architecture to accelerate GenAI exploration. \n\n

That's how the EA4ALL-Agentic system was born and ever since continuously evolving.

Benefits

Empower individuals with Knowledge: understand and talk about Business and Technology strategy, IT landscape, Architectue Artefacts in a single click of button. \n Increase efficiency and productivity: generate a documented architecture with diagram, model and descriptions. Accelerate Business Requirement identification and translation to Target Reference Architecture. Automated steps and reduced times for task execution.\n Improve agility: plan, execute, review and iterate over EA inputs and outputs. Increase the ability to adapt, transform and execute at pace and scale in response to changes in strategy, threats and opportunities. \n Increase collaboration: democratise architecture work and knowledge with anyone using natural language.\n Cost optimisation: intelligent allocation of architects time for valuable business tasks. \n Business Growth: create / re-use of (new) products and services, and people experience enhancements. \n Resilience: assess solution are secured by design, poses any risk and how to mitigate, apply best-practices. \n

Knowledge context

Synthetic dataset is used to exemplify the Agentic System capabilities.

IT Landscape Question and Answering

- Application name
    - Business fit: appropriate, inadequate, perfect
    - Technical fit: adequate, insufficient, perfect
    - Business_criticality: operational, medium, high, critical
    - Roadmap: maintain, invest, divers
    - Architect responsible
    - Hosting: user device, on-premise, IaaS, SaaS
    - Business capability
    - Business domain
    - Description

Architecture Diagram Visual Question and Answering

- Architecture Visual Artefacts
    - jpeg, png

    **Disclaimer**
            - Your data & image are not accessible or shared with anyone else nor used for training purpose.
            - EA4ALL-VQA Agent should be used ONLY FOR Architecture Diagram images.
            - This feature should NOT BE USED to process inappropriate content.

Reference Architecture Generation

- Clock in/out Use-case

Log / Traceability

For purpose of continuous improvement, agentic workflows are logged in.

Architecture

Core architecture built upon python, langchain, meta-faiss, gradio and Openai.

- Python
    - Pandas
    - Langchain
    - Langsmith
    - Langgraph
    - Huggingface

- RAG (Retrieval Augmented Generation)
    - Vectorstore

- Prompt Engineering
    - Strategy & tactics: Task / Sub-tasks
    - Agentic Workflow

- Models: 
    - OpenAI
    - Llama

- Hierarchical-Agent-Teams: 
    - Tabular-question-and-answering
    - Supervisor
    - Visual Questions Answering 
    - Diagram Component Analysis
    - Risk & Vulnerability and Mitigation options
    - Well-Architected Design Assessment
    - Vision and Target Reference Architecture

- User Interface
    - Gradio

- Hosting: Huggingface Space

Agentic System Architecture

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference