B2B prospect research agent

Summary

Research, enrichment and CRM workflows for sales teams.

Sales teams spent time collecting prospects, checking fit, finding decision-makers and keeping outreach records consistent.

A pipeline that gathers company information, enriches prospect records, prepares personalised outreach and connects activity to CRM and reporting tools.

Tech Stack

  • Python
  • AWS
  • OpenAI
  • Postgres
  • HubSpot API
  • Woodpecker API
  • Gmail API
  • PhantomBuster
  • Google Sheets API
  • Slack API

Project workstreams

  1. 01

    2 weeks

    Solution Architecture Design

    Solution Architect

    AWS Cloud Infrastructure Setup

    DevOps
  2. 02

    3 weeks

    Initial AI Agent Setup

    System Engineer, NLP Engineer

    Development of WebSearch and Scraping Tools

    System Engineer, NLP Engineer
  3. 03

    3 weeks

    Prospect Sources Integration

    System Engineer

    Development of Prospect Processing and Filtering Pipeline

    System Engineer, NLP Engineer
  4. 04

    4 weeks

    Designing Personalized LLM-based Outreach Campaigns

    Sales Consultant, NLP Engineer

    Setup Email and LinkedIn Automated Outreach

    Sales Consultant, System Engineer
  5. 05

    1 week

    Setup Agent Analytics

    System Engineer
  6. 06

    1 week

    Integration, Testing & Deployment

    System Engineer, NLP Engineer, Dev Ops

Tech Challenge

  • To find suitable prospects, we had to identify relevant databases containing up-to-date information on potential customers. Therefore, the primary challenge was efficiently gathering information from various private data providers and other research solutions. Additionally, ensuring the accuracy and relevance of the extracted insights presented a significant hurdle.

  • Another envisioned functionality was enriching the shortlist of prospects with relevant insights. The Agent can search and add insights based on publicly available data on each company — website information, press releases, articles, posts, etc.

  • The final solution should work as a fully Autonomous Agent capable of making outreach through platforms for sending emails, including personalized sequences to drive engagement with prospects.

  • Finally, the solution have to integrate with the sales team's existing toolkit through APIs, including email marketing, contact verification, CRM systems, and LinkedIn.

Solution

  • The main task of the Market Research Agent is gathering, combining, and filtering prospects from multiple sources. The Agent collects unstructured data about companies that may be interested in IT services using web search, scrapping tools, and data providers' APIs.

  • Next, each company is comprehensively investigated. This includes analyzing the services and products listed on the company's website, the founders' contact information, the headquarters and office locations, etc. Based on the results of the investigation, irrelevant companies are automatically removed.

  • With a full understanding of the potential client, the outreach strategy takes its course. The Agent finds the decision-maker among all company contacts, selects contact methods, writes message sequences, and sets up automated outreach with Woodpecker for email and PhantomBuster for LinkedIn.

  • To simplify statistics collection, the Agent Analytics system was developed. All important conversions on each step are aggregated in real-time, allowing the sales department to enhance predesigned campaign parts and adjust prospect sources.

  • Market Research Agent was also successfully integrated with the IT company's HubSpot CRM, which prevents doubling contacts and, along with Agent Analytics, ensures the clarity and visibility of the outreach results.

Outcome

A connected prospect-research and outreach workflow, evaluated in a three-month experiment.

The workflow was evaluated over a three-month experiment.

Published

DRL Team