Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/vrashmanyu605-eng/Agentic_Sales-Markerting/llms.txt

Use this file to discover all available pages before exploring further.

The competitor analysis agent gives your sales team a clear picture of who the target company already works with or might consider instead of you. It combines your pre-supplied competitor data with a live web search for the most recent competitive landscape, then asks the LLM to synthesize everything into an actionable report. The result is stored in competitor_analysis and is available to outreach and proposal agents that need to position your services against the competition.

​
State inputs

​
company_name
string
required
The name of the target company. Used to build the competitor search query.
​
competitors_data
string
required
Pre-supplied background data about known competitors. This can be a list of competitor names, brief profiles, or any other context about the competitive environment.

​
State outputs

​
competitor_analysis
string
required
A JSON string containing the LLM’s competitive intelligence report. See output schema for the full field list.

​
What it does

1

Build a targeted competitor search query

The agent constructs a search query combining the target company name, the supplied competitors data, and the terms "IT services 2024 2025". For example: "competitors of Acme Corp ERP vendors IT services 2024 2025". This focuses the search on the current year’s competitive landscape.
2

Search for fresh competitor data

The agent calls web_search with the constructed query. The search results provide up-to-date information about vendors the target company uses or is evaluating, recent contract news, and market positioning articles.
3

Generate the competitive intelligence report

The agent sends company_name, competitors_data, and the fresh search_results to the LLM. The LLM produces a structured JSON report covering eight dimensions: competitor strengths and weaknesses, market position, pricing comparison, service gaps, differentiators, market opportunities, and a recommended winning strategy.

​
Tools used

web_search

Retrieves current competitive intelligence including vendor comparisons, market positioning, and pricing data for the target company’s industry.

​
Output schema

The LLM is prompted to return structured JSON only. The expected structure is: 
{
  "competitor_strengths": [
    "Established brand recognition in the manufacturing sector",
    "Large implementation team with local presence"
  ],
  "competitor_weaknesses": [
    "High licensing costs",
    "Slow implementation timelines (12-18 months average)"
  ],
  "market_position": "The target company currently uses legacy on-premise ERP from a Tier-1 vendor with limited cloud support.",
  "pricing_comparison": "Competitor pricing is 40-60% higher than Webanix's managed service model.",
  "service_gaps": [
    "No dedicated AI/ML integration offering",
    "Limited post-implementation support SLAs"
  ],
  "differentiators": [
    "Faster implementation (3-6 months)",
    "AI-powered analytics module included",
    "Dedicated customer success manager"
  ],
  "market_opportunities": [
    "Upcoming contract renewal in Q2",
    "Recent C-suite change signals openness to new vendors"
  ],
  "winning_strategy": "Lead with speed-to-value and total cost of ownership comparison. Target the new CTO with a proof-of-concept proposal."
}
Pass competitor_analysis to the outreach generation and proposal generation agents to have the LLM automatically weave competitive differentiators into your messaging and proposal narrative.

​
Source code

import json
from llm import llm
from tools.search_tool import web_search

def competitor_analysis_agent(state):
    company_name = state["company_name"]
    competitors_data = state["competitors_data"]

    # Perform internet search for fresh competitor data
    search_query = f"competitors of {company_name} {competitors_data} IT services 2024 2025"
    search_results = web_search(search_query)

    response = llm.invoke(
        f"""
        You are a Competitor Analysis Agent.

        Analyze the competitive landscape using provided data and fresh search results.

        Company Name:
        {company_name}

        Initial Competitor Data:
        {competitors_data}

        Fresh Search Results:
        {json.dumps(search_results, indent=2)}

        Analyze:
        - competitor_strengths
        - competitor_weaknesses
        - market_position
        - pricing_comparison
        - service_gaps
        - differentiators
        - market_opportunities
        - winning_strategy

        Return structured JSON only.
        """
    )

    return {
        "competitor_analysis": response.content
    }

Build docs developers (and LLMs) love

Get started for freeTalk to us