Criclytics – Agentic AI for Cricket Analytics 

Criclytics is an AI-powered agent that delivers real-time cricket insights, player performance analysis, and match predictions by combining historical data with live feeds from ESPN Cricinfo, Cricbuzz, and the ICC.

Built using FlowiseAI and powered by the deepseek-r1 large language model, Criclytics analyzes team dynamics, evaluates individual players, and interprets match contexts—all through natural language queries. It transforms complex cricket statistics into accessible, interactive intelligence.

Tools Used:

• FlowiseAI – Visual LLM workflow orchestration

• deepseek-r1 – Advanced reasoning LLM

• Web Scraping + API Integration – Live data from leading cricket platforms

As an innovative example of Agentic AI, Criclytics showcases the potential of domain-specific language agents in real-time sports intelligence.

👉 Scroll to the end of this page to test Criclytics in action.

Gantt Chart - A Project Plan

This Gantt chart outlines the high-level project plan for a client's project, spanning from November 2020 to April 2021. Key phases include project initiation, recruitment and training, quality documentation, and technology implementation. Tasks are organized with clear dependencies, milestones, and durations to ensure streamlined execution. Recruitment activities and technical setups are prioritized alongside project assessments and go-live preparations. Visual indicators, such as timelines, deadlines, and task progress, provide a comprehensive view of project flow and coordination, emphasizing strategic alignment and operational efficiency to meet project objectives successfully. . 

Performance Data Analysis with Excel

This report presents a data-driven evaluation of call center performance across wireless and general support desks. Focusing on May–June 2020, the analysis covers key KPIs such as call volume variance, agent workload, SLA compliance, and productivity optimization.

Key insights include:

• Significant spikes in inbound volume (up to 150%) across all channels

• Random arrival patterns impacting agent occupancy and shift planning

• Workforce forecasting using Erlang C modeling

• Concurrency gaps and AHT variability in chat and email handling

The report guided workforce planning and operational decisions, highlighting the need for intelligent staffing models in high-variability support environments. 

Requirement Analysis and Resource Planning

This resource planning file provides a comprehensive analysis of headcount metrics and workload distribution across multiple channels, including inbound and outbound calls, emails, social media, and white mail. Key insights include arrival patterns, effective work hours, and historical data trends to optimize workforce allocation. Separate summaries for customer service and other divisions highlight tailored headcount needs. The data visualizations and workload distribution trends aid in identifying peak periods and resource gaps. Historical comparisons and linear projections support strategic decision-making, ensuring efficient utilization of resources and adherence to service level (SLA) targets.