CareerDekho

Collects and structures user inputs across three dimensions—technical/soft skills inventory, interest categories, and career aspirations—likely using a questionnaire or interactive assessment UI that maps responses to a normalized skill taxonomy. The system ingests these profiles into a vector embedding space or structured database to enable downstream matching against career pathways, using either rule-based scoring or learned similarity metrics.

Takes user profile embeddings and matches them against a curated database of career pathways using semantic similarity, collaborative filtering, or learned ranking models. The engine likely scores each career option across multiple dimensions (skill alignment, market demand, salary potential, growth trajectory) and surfaces top-N recommendations ranked by relevance. Implementation may use vector similarity search (cosine distance in embedding space) or a learned neural ranker trained on historical user-career matches.

Renders recommended careers as interactive visual pathways showing progression steps, skill development milestones, and timeline to reach target roles. Likely uses graph visualization (D3.js, Cytoscape, or similar) to display career progression as nodes (roles) and edges (transitions), with annotations for required skills, education, and experience gaps. Users can click through pathways to drill down into specific roles and see detailed requirements.

Compares user's current skill profile against requirements for target careers and generates a prioritized list of skill gaps. The system likely uses set difference or similarity scoring to identify missing or underdeveloped skills, then ranks them by importance (e.g., critical vs. nice-to-have) and market demand. May recommend specific learning resources, certifications, or courses to close gaps, potentially integrating with external education platforms via API or curated links.

Enriches career recommendations with real-time or near-real-time labor market data including job posting volume, salary ranges, growth projections, and geographic demand hotspots. Likely ingests data from job boards (Indeed, LinkedIn, local Indian job sites), government labor statistics, or third-party labor market APIs. Displays this data alongside career recommendations to help users make informed decisions about career viability and earning potential.

Synthesizes skill gap analysis and learning recommendations into a sequenced, personalized learning plan that accounts for prerequisites, estimated duration, cost, and user preferences (e.g., self-paced vs. instructor-led). Likely uses topological sorting or dependency graph algorithms to order learning resources such that prerequisites are satisfied before dependent skills. May integrate with learning platforms via APIs to pull course metadata and pricing, or maintain a curated internal database of vetted resources.

Identifies and recommends mentors, industry professionals, or peer learners based on user's target career and current profile. May use collaborative filtering to match users with similar goals, or rule-based matching to connect users with professionals in target roles. Likely includes a directory or matching interface to facilitate introductions, potentially integrated with messaging or video call capabilities for mentorship interactions.

Tracks user's learning progress, skill development, and career advancement against the personalized learning plan and career pathway. Likely maintains a progress dashboard showing completed courses, acquired skills, and milestones achieved. May integrate with external platforms (Coursera, LinkedIn Learning) via APIs to auto-import completion data, or rely on manual logging. Generates periodic progress reports and recommends adjustments to the learning plan based on actual progress.

Evaluates user's readiness to apply for target career roles based on skill alignment, experience, and credentials. Likely analyzes user profile against job descriptions to identify gaps and provides actionable recommendations for resume optimization, portfolio building, or additional certifications. May use NLP to extract skill requirements from job postings and compare against user profile, or employ rule-based scoring to assess readiness across multiple dimensions (skills, experience, education, certifications).

Provides on-demand career advice through a conversational AI interface that answers user questions about career paths, skill development, job market trends, and career decisions. Likely uses a large language model (LLM) fine-tuned on career guidance content, integrated with the platform's career database and labor market data. Maintains conversation context to provide personalized responses based on user's profile and previous interactions.