No description
Find a file
2026-02-08 19:13:38 +00:00
.vscode Added vscode suggestions 2026-01-17 20:40:09 +00:00
apps Added mcp rag, onboarding app, frontend for learning and agent inference 2026-02-08 15:34:26 +00:00
compose Added tls to compose 2026-02-08 19:13:38 +00:00
config Added mcp rag, onboarding app, frontend for learning and agent inference 2026-02-08 15:34:26 +00:00
data Added dummy data for testing 2026-01-20 02:59:52 +00:00
mcp_agent Added mcp rag, onboarding app, frontend for learning and agent inference 2026-02-08 15:34:26 +00:00
notebooks Added preparation notebook 2026-01-28 09:55:43 +00:00
requirements Added pgvector, docx and pdf parsing requirements 2026-02-08 15:33:07 +00:00
src Added mcp rag, onboarding app, frontend for learning and agent inference 2026-02-08 15:34:26 +00:00
.dockerignore Added docker ignore 2026-01-17 21:13:14 +00:00
.editorconfig Modified scripts, prettier, editor confs and env 2026-01-18 14:27:58 +00:00
.env.template Removed replicas 2026-01-30 00:10:33 +00:00
.gitattributes Added node ignore and attributes 2026-01-17 20:40:34 +00:00
.gitignore Added more ignores 2026-02-07 10:02:07 +00:00
.gitlab-ci.yml Added node syntax check, remove tag condition 2026-01-28 10:31:50 +00:00
.prettierignore Modified scripts, prettier, editor confs and env 2026-01-18 14:27:58 +00:00
.prettierrc.json Added vite, ts, lint and package files 2026-01-17 21:03:12 +00:00
env.d.ts Added ant, fixed types issues 2026-01-17 21:23:30 +00:00
eslint.config.ts Added ant, fixed types issues 2026-01-17 21:23:30 +00:00
index.html Added vite, ts, lint and package files 2026-01-17 21:03:12 +00:00
manage.py Added project level settings, api, celery and view 2026-01-17 14:11:24 +00:00
package-lock.json Modified scripts, prettier, editor confs and env 2026-01-18 14:27:58 +00:00
package.json Modified scripts, prettier, editor confs and env 2026-01-18 14:27:58 +00:00
README.md Updated path 2026-01-17 20:36:04 +00:00
tsconfig.json Tweaked configuration settings 2026-01-18 14:27:15 +00:00
vite.config.ts Tweaked configuration settings 2026-01-18 14:27:15 +00:00

An Agentic Approach to Role-Specific Trainers - Dynavera

A proof-of-concept platform for automating the induction and support of new hires or team members into a role using AI agents. This project demonstrates a reusable workflow that combines a modern full-stack application with AI-driven guidance and assessment.


Table of Contents


Project Goals

The main objectives of this project are:

  1. Reusable Workflow Create a pipeline that can automatically onboard and guide new hires or team members in a specific role.
  2. AI Agent Integration Use intelligent agents to provide guidance, monitor progress, and adapt learning to individual users.
  3. Real-World Testing Evaluate the suitability and effectiveness of the tool in realistic onboarding scenarios.
  4. Role Specific Trainers Support the creation of trainers specialized for different roles, fields, or industries.

Tech Stack


Features

  • Automated onboarding workflow for new hires.
  • Role-specific AI training modules.
  • Adaptive guidance and personalized learning paths.
  • Dashboard for tracking user progress and feedback.
  • Modular AI agent integration (Python/JS).

Usage

  1. Navigate to the frontend URL (hosted at https://fyp.viswamedha.com).
  2. Register a new user or login.
  3. Select the role to train in.
  4. Follow the guided AI-assisted onboarding workflow.
  5. Track progress and view recommendations on the dashboard.