Techathon 6.0

Problem Statement 4: FMCG

About the Business:

A large Industrial products manufacturing business (client) with operations across Fast-moving consumer goods (FMCG), wires and cables has seen considerable growth over the last five years. This growth has been driven by significant business-to-business (B2B) requests for proposals (RFPs) and tenders from infrastructure build-out in India. The client wishes to further grow the B2B business by increasing the number of RFP qualifications and responses. 

Context on B2B RFPs

Typically, large projects—such as government projects—are launched by government departments or public sector undertakings (PSUs). These projects are executed by lumpsum turnkey (LSTK) project executors (PSUs or private enterprises). The LSTK project executors raise RFPs for material supplies—such as wires, cables other materials —to be supplied by Original Equipment Manufacturers (OEM) vendors.

A typical RFP consists of technical scope of supply (quantity of wires/cables), technical specifications (for wires and cables), test requirements and acceptance tests to be conducted before accepting the delivery of wires and cables (refer to the sample RFP). OEM vendors bid for these tenders and the lowest-priced tender is awarded the contract. The client is one of the large wires and cables OEMs in India, which regularly bids for such RFPs. 

B2B RFP response process

  • Once the RFP is received to the client Sales Team, they qualify the RFP based on the date for submission, past experience and product coverage.
  • Qualified RFPs are passed on to the Product Technical Team to match the client product SKUs to RFP product requirements. Refer sample of product specs.
  • The Product Technical Team finalizes the client product SKUs which are the closest match.
  • This is then worked on by the Pricing Team, which estimates the price of the products, additional costs required to meet the testing and acceptance test requirements at project site.
  • The Sales Team consolidates the inputs from Product technical team and Pricing Team to submit the RFP response to the LSTK project executor.
  • In case the client product SKUs have a low match for RFP product requirement, a internal request for new made to order SKUs is prepared to meet the RFP product requirements. 

Bottlenecks in the B2B RFP Response

  • Once the RFP is received by the client Sales Team, they qualify the RFP based on the submission date, past experience and product coverage.
  • Qualified RFPs are passed on to the Product Technical Team to match the client product SKUs to the RFP product requirements. Refer to the sample of product specifications.
  • The Product Technical Team finalizes the client product SKUs that are the closest match.
  • This is then worked on by the Pricing Team, which estimates the price of the products and additional costs required to meet the testing and acceptance test requirements at the project site.
  • The Sales Team consolidates the inputs from the Product Technical team and Pricing Team to submit the RFP response to the LSTK project executor.
  • In case where the client product SKUs have a low match for the RFP product requirements, an internal request for new made-to-order SKUs is prepared to meet the RFP product requirements. 

Bottlenecks in the B2B RFP response:

  • The entire RFP response process is manually driven, with manual handoffs between each team.
  • In many cases, the Sales Team may not be aware of the release of RFPs by LSTK project executors in time. These are typically released on the LSTK project executors’ website or received via email. Delay in initiating response to RFPs can certainly lower the chances of winning. 
  • The technical matching of RFP requirements to product SKUs is manually done, requiring knowledge of technical standards, specifications and product knowledge. 
  • While standards, specifications and product details are well documented, the Technical Team often manages multiple RFPs concurrently, which leads to a longer turnaround time for their responses. The Pricing Team can only work on pricing after receiving the Technical Team’s responses. 

Problem statement:

The client aims to enhance their B2B business channel. With significant credentials from past growth driven by B2B RFPs, they believe their team has the “right to win” in this segment. However, rapid growth has led to bottlenecks in the RFP response process, impacting timely submissions.

Analyzes of past RFP outcomes revealed: 

  • 90% of wins correlated with timely received and actioned RFPs
  • 60% of wins correlated with adequate time given to the technical team to align product requirements with RFPs
  • Technical product SKU matching with RFP requirements is the most time-consuming aspect
  • Delays in RFP submission significantly reduced the chances for win

The client seeks to improve the number of RFPs responses per year and the timely response by using an Agentic AI approach. The solution should simulate the B2B RFP response process through a Sales Agent and Technical Agent, automating the identification of RFPs and mapping the appropriate SKUs. 

Goal:

Teams must design an Agentic AI solution where the Sales Agent:

  • Scans a set of predefined URLs to identify the RFPs that are due to be submitted in the next three months
  • Summarizes the requirement of the RFP in terms of products to be shared with the Technical Agent
  • Summarizes the testing and acceptance requirements to be shared with the Pricing Agent 

Key deliverable:

A live demo or recorded video (maximum four minutes) showcasing the end-to-end journey from RFP identification to collating the RFP response from technical and pricing agents.

Master Agent (Main orchestrator)

  • Prepares a summary of an identified RFP to be shared with the Technical and Pricing Agent
  • The summary shared with the Technical and Pricing Agents needs to be contextual to their roles
  • Receives the response from the Technical and Pricing Agents to consolidate the overall response of the RFP
  • The overall response of the RFP needs to contain the OEM product SKUs suggested, their prices and the costs for tests required in the RFP
  • Starts and ends the conversation

Worker Agents

Sales Agent:

  • Identifies the RFPs that are due for submission in the next three months
  • Scans identified web URLs to summarize RFPs with their due dates
  • Identifies one RFP to be selected for response and sends this to the Main Agent

Technical Agent:

  • Receives the summary RFP and RFP document from the Main Agent
  • Summarizes the products in the scope of supply
  • Recommends the top three OEM products that match each of the products in scope of supply, showing a “Spec Match” metric (in %) for each of the OEM product recommendations
  • Recommendations of the top three OEM products come from a repository of product datasheets. Refer to the sample of product specs
  • The spec match metric should reflect the closeness with which the recommended OEM product matches the RFP product specs, considering that all the required specs have an equal weightage
  • Prepares a comparison table of RFP spec parameters requirements and spec values for the top 1, 2 and 3 OEM product recommendations for each RFP product
  • Selects the top OEM product that closely matches the RFP products for all items in the scope of supply based on the spec match metric
  • Sends the final table of products in scope of supply and recommended OEM product SKUs to the Main Agent and the Pricing Agent

Pricing Agent:

  • Receives the summary of the tests and acceptance tests to be done for the product from the Main Agent
  • Receives the product recommendation table from the Technical Agent
  • The Pricing Agent assigns a unit price for each product based on a dummy pricing table and a price for each test based on a dummy services price table
  • Consolidates the total material price and services price for every product in the scope of supply
  • Sends the consolidated price table to the Main Agent
  • RFP data: Teams can download the RFPs from the internet. Two sample RFPs have been provided as a reference 
  • OEM product data sheets: Teams can download the cables datasheets for any of the leading cable manufacturer websites–a few sample URLs have been provided as a reference 
  • Product and tests pricing data: Teams must create synthetic data for the price of products, types of tests and the prices of each of the tests
  • Scanning RFP from websites: The teams can set up sample web pages that display the RFPs for the Sales Agent to scan and summarize

Technical design (40%)

  • Use of an Agentic AI framework (LangGraph, CrewAI, AutoGen, etc.)
  • Well-structured orchestration of Master and Worker Agents

Realism of data and workflow (25%)

  • Quality of synthetic data, APIs and file handling
  • Real-world-like loan decision rules

Output structure (25%)

  • Structured output and responses in tables by each of the agents

Demo quality (10%)

  • Live demo or video walkthrough of the complete journey—from RFP initiation to RFP response collation

Demo: 

Live or three to four minute video

Brief document:

  • System architecture diagram
  • Description of agents and workflows
  • Data assumptions used in the demo (e.g., RFPs, OEM product specs, product and services pricing considered for the demo and others)
  • Provide outputs in a structured summary (bullets rather than long paragraphs) and structured tables
  • Focus on the logic for matching RFP requirements with OEM product recommendations
  • Detail the logic for scoring spec match metric for RFP products and OEM products
  • Emphasize the process of matching requirements rather than the accuracy of matching

Previous    

  Problem Statement 3          


Contact us
Like what you’ve seen? Get in touch to learn more.