Unlock your potential, discover your skills
Compass is an innovative, AI-powered chatbot designed to revolutionize the way a young person identifies, articulates, and showcases their skills. Developed by Tabiya, Compass is a personal career assistant, helping youth uncover hidden talents and match them with the best opportunities in the job market.
Compass is an open-source, conversational AI tool that:
Engages in natural dialogue to explore your experience
Analyzes a user's input to identify and categorize skills against localized taxonomies
Identifies skills from both formal and informal work
Creates a comprehensive skills profile tailored to the user
Generates a professional customizable CV highlighting one’s strengths
Matches a user's skills with relevant economic opportunities
Recommends personalized recommendations for skill development and career advancement.
Compass uses a large language model (LLM) and a conversational interface to help job seekers build a CV that highlights their skills. The tool combines a commercial LLM with a human-reviewed skills taxonomy for the labor market.
In today's rapidly evolving job market, Compass tackles two persistent and interconnected problems that hinder effective workforce development:
Challenges in showcasing skills: Crafting a CV that highlights relevant skills is tough for many job seekers. It's about translating experiences into terms that appeal to employers. This is harder for those with non-traditional or informal experience. A poor CV can lead to missed opportunities.
The scalability struggle: Traditional methods rely heavily on human career counselors. While these professionals offer valuable insights, this approach has significant limitations.
Compass breaks down barriers by offering an AI solution that's scalable, affordable, and high-quality.
Expanded geographic reach: Widespread adoption of Compass for use in emerging markets
Multilingual support: Expand language capabilities to serve diverse populations
Voice integration: Enable our users to speak to Compass in their local dialects
Portable skills wallet: Compass skills exploration outputs activated in an interoperable skills wallet
Enhanced features: Develop more advanced career pathing and skills development recommendations
Integration capabilities: Create APIs and tools for seamless integration with existing job platforms and career services
Impact measurement: Implement a multi-site randomized control trial to rigorously estimate impacts
Compass is designed as a digital public good:
The core technology is open-source, allowing for transparency and community-driven improvements
We aim to build a diverse global community of contributors and implementers around Compass
Organizations supporting youth in their career journeys can adapt Compass to their specific needs and contexts
We welcome partnerships and collaborations to further develop and implement Compass:
For inquiries about supporting or implementing Compass, connect with us here
To learn more about our current projects and future plans, visit https://www.tabiya.org
Follow our progress and join the conversation on https://www.linkedin.com/company/tabiya
Together, we can leverage the power of AI to create more inclusive and efficient labor markets worldwide.
For Funders
Scalable Impact: Reach thousands of job seekers efficiently with minimal cost increase.
Data-Driven Insights: Provide valuable data on skills gaps and labor market trends to guide policies and programs.
Promote Equity: Value skills from diverse backgrounds, including informal and unpaid work.
Enhance Existing Programs: Strengthen current workforce development initiatives.
Foster Innovation: Use the Tabiya ecosystem to encourage innovation and address social challenges.
For Partners
Increase Efficiency: Simplify skills identification and job matching.
Improve Outcomes: Enhance job placements and retention with suitable opportunities.
Cost-Effective Scaling: Offer personalized guidance to more job seekers without extra staff
Data-Informed Decisions: Use insights to tailor services and programs.
For Job Seekers
Discover Potential: Identify and articulate hidden skills.
Access Guidance: Benefit from AI-driven career advice with human expertise.
Improved Matching: Find opportunities that fit unique skill sets.
Career Development: Receive tailored recommendations for skill and career growth.
Compass utilizes agentic workflows to interact with users, gather information, and identify their skills.
Compass mimics how a human would approach a conversation and the resulting tasks, acting as an overarching agent that decomposes into smaller agents, each with its own responsibilities and goals.
Each agent within Compass has a specific responsibility and performs multiple tasks to achieve its goal. For example, an agent might converse with a user to collect specific information, process that information, and prepare it for use by another agent.
Agents maintain an internal state that allows them to apply a strategy to accomplish their goal, and have access to the user's conversation history and use tools based on LLM prompts (or not). These tools could be used for tasks such as conversing with the user, named entity extraction, classification, or transforming user input.
Agents are guided by a combination of instructions (prompts) and their internal state. The prompts can vary based on the agent's state to help them accomplish their tasks.
Once Compass has gathered all the necessary information from the user, it processes the data to identify the user’s top skills. This identification is done through a multi-stage pipeline that employs various techniques, such as clustering, classification, and entity linking the a occupations/skills taxonomy.
Compass leverages LLMs in three ways:
To converse, generate questions, and respond to user input. This is a reverse application of LLMs, as they typically respond to user questions, but in Compass, the user is prompted by Compass to provide responses.
To perform standard NLP tasks such as clustering, classification, and named entity extraction.
To reason and provide explanations for the output of specific tasks.
Compass is grounded and protected from hallucinations in multiple ways:
By giving the LLMs smaller tasks to solve.
By using state to induce specific instructions during the conversation with the user.
Using instructions that decrease the probability of irrelevant output from the LLMs.
With the use of the occupations/skills taxonomy that confines the discovered skills to the given space.
Another important feature of Compass is its ability to offer traceability of outputs back to the user’s input. Because Compass includes reasoning for each task it performs, it allows for tracing and explaining why certain skills were selected and how they relate to the user’s experience.
For evaluating Compass, we followed the strategy outlined bellow, tailored to the specifics of each agent:
Agent’s tools where evaluated in isolation. Each component was evaluated based on specific inputs and expected outputs. For example, for component performing a classification task, we used known inputs and expected class labels to evaluate the tool.
Conversational components were evaluated with scripted conversations, where the pre-conducted conversation is treated as a given input and the expected output is evaluated by another LLM (auto-evaluators) or by human inspection.
Additionally conversational components where evaluated, by simulating users driven by an LLM. The conversation between Compass and the simulated user was captured and evaluated by an auto-evaluator or by human inspection. This technique was applied to evaluate Compass as an end-end agent.
On a smaller scale, we conducted user tests and, following the traces of the top skills output to the user’s input, evaluated how well specific agents performed their duties.
Compass utilizes the gemini-1.5-flash-001 model as its LLM and the textembedding-gecko version 3 model for embeddings. For the LLM auto-evaluator, the gemini-1.5-pro-preview-0409 model was used.
The backend is built with Python 3.11, FastAPI 0.111, and Pydantic 2.7. The frontend is developed with React.js 19, TypeScript 5, and Material UI 5. It is a web-based application designed primarily for mobile use but also works well on tablets and desktops.
Data is persisted using MongoDB Atlas, and Compass is deployed on GCP.
Our vision for Compass includes:
Expanded geographic reach: Widespread adoption of Compass for use in emerging markets
Multilingual support: Expand language capabilities to serve diverse populations
Voice integration: Enable our users to speak to Compass in their local dialects
Portable skills wallet: Compass skills exploration outputs activated in an interoperable skills wallet
Enhanced features: Develop more advanced career pathing and skills development recommendations
Integration capabilities: Create APIs and tools for seamless integration with existing job platforms and career services
Impact measurement: Implement a multi-side randomised control trial to estimate Compass impact on career outcomes