AI Project Assistant (code: LAB25001)

Executive Summary

The AI Project Assistant is designed to support project management at M31 by providing tools for advanced project data analysis and assistance in creating technical and operational documentation. It doesn’t just monitor and interpret information from various sources—it also guides teams in drafting documents, generating ready-to-use templates, and creating outlines that comply with standards like ISO9001, ensuring all technical and operational requirements are met.

This project aims to develop an intuitive web application with analysis and suggestion functionalities, as well as automated documentation models to enhance efficiency and accuracy. It will integrate with tools already in use, such as Confluence and Jira.
Here’s what you can expect:

Data analysis dashboards to visualize key metrics.
Automated notifications to keep teams informed.
Template generators to streamline project documentation.

The estimated budget for this project is €500–€1000, which will cover server expenses and software licenses.
The main risks involve the accuracy of data analysis models and the compliance of generated documents with standards, requiring thorough testing to ensure quality.

Problem Description

Managing multidisciplinary and long-term projects at M31 comes with its challenges. These projects require us to balance multiple tools for tracking activities, managing resources, and analyzing data. The challenge is that each tool stores information in different formats, often resulting in scattered data. This makes it difficult to get a clear overview of the project or quickly locate the information we need. As a result, project management can become less efficient and take more time than it really should.
Another critical aspect is creating accurate and consistent documentation. Internally, we need detailed records of decisions, tests, analyses, and system architectures to keep the team on track and make future updates easier. On the other hand, external documentation has to meet industry standards, like ISO 9001, to comply with regulations. Unfortunately, writing documentation is often seen as dull, so it’s either rushed or postponed. This can leave gaps in critical information, which risks hurting both the quality of the project and its compliance with standards. That’s where the Intelligent Project Assistant comes in. This tool is designed to simplify the documentation process by providing ready-made templates and models for internal and external needs. It doesn’t stop there—it also helps analyze project data, giving managers a clear view of progress, highlighting potential risks, and helping them act quickly to solve issues. By taking on these tasks, the assistant not only saves time but also improves efficiency and ensures better project quality, making complex projects much easier to manage.

In short, the Intelligent Project Assistant takes the pressure off and helps us focus on what really matters: delivering high-quality results.

Specific Objectives and KPIs

Specific Objectives:

The Intelligent Project Assistant is designed to provide a straightforward mechanism for creating accurate and compliant project documentation. This saves time and reduces errors while creating official and technical documents, ensuring that everything is done correctly the first time.
It will also concentrate all of the critical project information, improving traceability and making it easier for team members to get the data they require without additional delays or confusion.
The assistant will have real-time dashboards that show project progress, indicate potential concerns, and anticipate new hazards. These changes will enable project managers to make better-informed and more efficient decisions.
Finally, the assistant will seamlessly integrate with the tools we already use at M31, such as Bytes, Jira, Confluence, Bitbucket, Teams, and SharePoint, creating a unified workflow that enhances productivity and collaboration.

Key Performance Indicators (KPIs):

Documentation completion time: Reduce the time required for drafting and reviewing project documentation by 30%, measured in man-hours compared to current timelines.
Documentation compliance rate: Achieve at least 95% compliance for documentation required by ISO9001 procedures and quality audits.
Project information coverage: Ensure that at least 80% of key project decisions and tests are documented and traceable within the first three months.
Team satisfaction: Target a team satisfaction rating of ≥4 out of 5, monitored through quarterly surveys to assess the assistant’s usefulness and usability in document and decision-making support.

High-Level Architecture and Proposed Technologies

A cloud-native architecture is proposed, based on a backend-frontend separation, with the frontend being web-based. The backend is planned as a microservices infrastructure (potentially serverless).

Proposed technologies (non-exhaustive list):

Python/Go: for programming the AI agents
Go/TypeScript: for backend and frontend service implementation
Angular: as the UI framework for the web frontend
LangChain/LangGraph: for AI agent creation and management
PostgreSQL/MongoDB: as databases

Feasibility Analysis

From a technical standpoint, the project is entirely feasible since all the required technologies are readily available. These include frameworks for building AI agents, such as LangGraph, cloud-based execution environments like Google Cloud Platform, RAG (Retrieval-Augmented Generation) implementation techniques using LangChain, and HTTP APIs for integration and communication.

However, there are potential risks to consider. A key challenge will be ensuring that the AI agents consistently meet the defined KPIs and deliver predictably reproducible results. This is particularly challenging because LLM-based agents rely on statistical, non-deterministic models, which can sometimes produce unpredictable outputs. To address this, we will apply best practices and techniques designed to guide and control the outputs of these predictive models, reducing variability and ensuring reliability in their performance.

Project Phases and Work Plan

The project is structured into the following phases:

Phase 1: Analysis of required functionalities and creation of the basic structure of assistants integrated with existing tools.
Phase 2: Implementation of task monitoring and suggestion logic.
Phase 3: Development of system infrastructure and graphical interface.
Phase 4: Testing and optimization based on user feedback.
Phase 5: Release and documentation.

The preliminary timeline (to be refined during the first month of the project) is as follows:

Phase 1: Months 1-3
Phase 2: Months 3-5
Phase 3: Months 1-5
Phase 4: Months 5-7
Phase 5: Month 8

Required Resources and Estimated Budget

Logistics: A workspace for a team (ideally 3-4 people).

Software: Accounts for accessing LLM HTTP APIs (e.g., OpenAI).

Hardware: Access to virtual machines and infrastructure for AI tasks and application execution.

Estimated Budget:

APIs: €80/month → €640 (over 8 months)
Virtual machines and cloud environment: €150/month → €1200 (over 8 months)

Expected Value and Impact

The project will significantly contribute to M31’s project management approach by creating a tool that enhances project oversight. The intelligent assistant will enable students to learn how to develop AI-driven productivity solutions and could serve as a foundation for other project management applications at M31 and in the broader adoption of GenAI solutions.

Apply