> ## Documentation Index > Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Ultimate AI SDR > Building a sophisticated AI SDR agent leveraging internet search and evals to draft personalized outreach emails in 15 seconds ### The Problem: Generic Sales Outreach Doesn't Work
❌ Before

Dear John,

I hope this email finds you well. I wanted to reach out about our security services that might be of interest to YMU Talent Agency.

Our company provides security personnel for events. We have many satisfied customers and would like to schedule a call to discuss how we can help you.

Let me know when you're available.

Regards,
Sales Rep

Response rate: 1.2%
✅ After

Subject: Quick security solution for YMU's talent events

Hi John,

I noticed YMU's been expanding its roster of A-list talent lately – congrats on that growth. Having worked event security for talent agencies before, I know how challenging it can be coordinating reliable security teams, especially on short notice.

We've built something I think you'll find interesting – an on-demand security platform that's already being used by several major talent agencies.

Best,
Ilya

Response rate: 9.5%
This cookbook shows you how to build an AI-powered system that: * **Researches prospects in real-time** using up-to-date web data * **Crafts personalized emails** based on prospect-specific insights * **Self-evaluates and improves** its output before sending * **Scales to thousands of prospects** at a fraction of the usual cost ## Multi-Agent Architecture ```mermaid theme={"system"} graph LR classDef main fill:#e1f5fe,stroke:#01579b,stroke-width:2px classDef research fill:#f3e5f5,stroke:#4a148c,stroke-width:2px classDef eval fill:#e8f5e9,stroke:#1b5e20,stroke-width:2px classDef io fill:#fff3e0,stroke:#e65100,stroke-width:2px A[Input]:::io B[Claude 3.7
Orchestrator]:::main C[Perplexity
Sonar Pro]:::research D[OpenAI
o3-mini]:::eval E[Output]:::io A --> B B --> C C --> B B --> D D -->|Approved| E D -->|Revise| B style A font-size:14px style B font-size:14px style C font-size:14px style D font-size:14px style E font-size:14px ``` Our system combines three specialized AI models: 1. **Orchestrator (Claude 3.7)**: Generates research queries, drafts emails, and refines based on feedback 2. **Researcher (Perplexity)**: Gathers real-time web information about prospects and companies 3. **Evaluator (OpenAI)**: Reviews email quality, providing scores and improvement suggestions This architecture delivers superior results because: * Each model handles tasks it excels at * The system includes built-in quality control * Cost efficiency through right-sized models and targeted research ## Creating the Prompt Templates ### What You'll Create The Orchestrator template handles three different roles depending on which "mode" is activated: 1. **Research Query Generator**: Creates targeted questions for the researcher 2. **Email Drafter**: Uses research findings to write personalized outreach 3. **Email Refiner**: Incorporates evaluator feedback to improve the email ### Variables You'll Need | Variable | Purpose | Example | | ---------------------------- | -------------------------------- | -------------------------------------------------------- | | `our_offering` | Your product/service description | "Umbrella Corp offers 'Uber for personal protection'..." | | `company_name` | Prospect's company | "YMU Talent Agency" | | `company_industry` | Industry sector | "Elite Talent Management" | | `target_person_name` | Contact name | "John Wick" | | `target_person_designation` | Contact's role | "Event Organizer" | | `requirement_gathering_mode` | Activates research query mode | "TRUE" or "" (empty) | | `research_mode` | Activates email drafting mode | "TRUE" or "" (empty) | | `evaluator_mode` | Activates email refinement mode | "TRUE" or "" (empty) | | `researcher_output` | Data from the researcher | (JSON response from research) | | `evaluator_output` | Feedback from evaluator | (JSON with score and comments) | ### Step-by-Step Setup 1. **Create template** in [prompt.new](https://prompt.new/) with **Claude 3.7 Sonnet** ### What You'll Create The Researcher template powers the real-time web research capabilities of your AI SDR system. ### Variables | Inputt | Description | Source/Destination | | ------------------------------ | ---------------- | -------------------------- | | `requirement_gathering_output` | Research queries | Received from Orchestrator | ### Setup Steps 1. Create a new prompt template with **Perplexity Sonar Pro** as the model 2. Add researcher instructions: Add these system instructions that define the researcher's role: You are a world-class researcher who, when given key info about a company, its industry, and the target person, helps your handler write the ultimate sales email by gathering the critical insights about them from the internet. In scenarios where you do not find much info about the company in question, you also try to extrapolate the key information about this company that helps with writing the ultimate opener email. Your completed template should look like this: Researcher template configuration YMU Group is a global talent management agency founded in 1984 and based in London\[1]. It offers full-service talent management, including representation for entertainers, athletes, musicians, and literary figures\[1]. The company works with high-profile clients like Simon Cowell, Graham Norton, Claudia Winkleman, Nicole Scherzinger, Stacey Solomon, and Ant and Dec\[7]. In 2023, YMU reported a pre-tax loss of £32 million on revenue of £42.4 million\[7]. The company was sold in March 2024 for £60 million to Permira Credit\[7]. YMU appears to focus on talent representation and career management rather than event organization. The search results don't mention John Wick or provide details about specific events, security practices, or budgets. For writing a sales email, you might focus on YMU's role as a major talent agency representing top celebrities. Their need for security services likely relates to protecting high-profile clients rather than large-scale event management. You could highlight how your security offerings could benefit their roster of celebrity talent in various professional and personal settings. Without more specific information, it's best to keep the email fairly general, focusing on your company's experience protecting high-profile individuals and how that aligns with YMU's client base. You might also mention your ability to provide flexible, on-demand security staffing to meet the changing needs of busy entertainment professionals. ### What You'll Create The Evaluator template provides quality control for your AI SDR system. ### Variables | Input | Description | Source/Destination | | -------------- | ----------------------------------------- | ---------------------------- | | `work_history` | Research queries + findings + email draft | Received from previous steps | ### Setup Steps 1. Create a template with **OpenAI o3-mini** as the model 2. Add evaluator instructions: Add these system instructions that define the evaluator's role: You are the critical part of an AI SDR agent that helps write opening sales email to a given prospect at a given company. Your key job is look at everything provided to you: The SDR's job to be done, the SDR's persona, the company and the target person in question, the research output, and send back a JSON with two keys: "score" and "comment". The actual JSON object will be: `{"score":, "comment":""}` Based on your feedback, the agent will rework the email and then send it to the prospect. Your completed template should look like this: Evaluator is like an AI sales manager reviewing drafts before they go out - ensuring consistent quality at scale. ```json theme={"system"} {"score": 7, "comment": "The research summary does a good job of contextualizing YMU as a leading talent agency with high-profile clients, emphasizing the need for security services tailored to the protection of celebrities. It provides a solid foundation for a targeted email by suggesting a focus on flexible, on-demand security staffing. However, the information is somewhat generic, lacking specifics that could create a more compelling and personalized pitch. The email would benefit from slightly more emphasis on addressing potential security challenges or pain points unique to managing high-profile talent, even if inferred, to make the value proposition sharper."} ``` ## Implementing the Workflow ```python theme={"system"} from portkey_ai import Portkey # Initialize with tracing client = Portkey( api_key="PORTKEY_API_KEY", trace_id="ultimate-ai-sdr-run-1" ) # Company offering our_offering = """Umbrella Corp offers 'Uber for personal protection'. Using our app, you can get highly vetted, arms-bearing ex-veterans who can accompany you to any place that's supported for any amount of hours or days...""" # Target information company_name = "YMU Talent Agency" company_industry = "Elite Talent Management" target_person_name = "John Wick" target_person_designation = "Event Organizer" ``` ```python theme={"system"} # Activate research query generation mode variables = { "our_offering": our_offering, "company_name": company_name, "company_industry": company_industry, "target_person_name": target_person_name, "target_person_designation": target_person_designation, "requirement_gathering_mode": "TRUE" # Activate research query mode } gatherer = client.with_options(span_name="gatherer").prompts.completions.create( prompt_id="your-orchestrator-template-id", variables=variables ).choices[0].message.content ``` ``` Research Queries: 1. What are the typical event sizes and types that YMU Talent Agency organizes? 2. Have there been any security incidents at YMU's past events? 3. What is John Wick's specific role and experience in event organization at YMU? 4. Does YMU currently work with any security providers? 5. What are the most significant upcoming events that YMU is organizing? ... ``` ```python theme={"system"} # Send queries to researcher researcher = client.with_options(span_name="researcher").prompts.completions.create( prompt_id="your-researcher-template-id", variables={"requirement_gathering_output": gatherer} ).choices[0].message.content ``` ``` Research Summary for YMU Talent Agency: 1. Company Profile: - YMU is one of the world's leading talent management companies - Represents high-profile clients including Simon Cowell, Nicole Scherzinger ... 2. Security Considerations: - Growing concern about celebrity stalking incidents in the industry - Multiple high-profile clients have experienced security threats ... ``` ```python theme={"system"} # Activate email drafting mode variables = { "our_offering": our_offering, "company_name": company_name, "target_person_name": target_person_name, "researcher_output": researcher, "requirement_gathering_mode": "", # Deactivate research mode "research_mode": "TRUE" # Activate email drafting mode } email_one = client.with_options(span_name="email-one").prompts.completions.create( prompt_id="your-orchestrator-template-id", # Same template, different mode variables=variables ).choices[0].message.content ``` ``` Subject: Quick security chat - from one protection expert to another Hi John, As someone who's been on both sides of event security, I know the stress of finding reliable protection for high-profile talent. Especially given YMU's roster including Simon Cowell and Nicole Scherzinger. We've built an 'Uber for security' that top agencies use - you get instant access to vetted, armed ex-veterans through an app. ... ``` ```python theme={"system"} # Send to evaluator evaluator = client.with_options(span_name="evaluator").prompts.completions.create( prompt_id="your-evaluator-template-id", variables={"work_history": gatherer + " " + researcher, "email_output": email_one} ).choices[0].message.content ``` ```json theme={"system"} { "score": 7, "comment": "The email does a good job establishing rapport by acknowledging John's background in event security and mentioning specific clients. However, it could be improved by directly addressing the specific pain point mentioned in the research - 'finding reliable security staff on short notice.'" } ``` ```python theme={"system"} # Activate email refinement mode variables = { "our_offering": our_offering, "company_name": company_name, "target_person_name": target_person_name, "researcher_output": researcher, "evaluator_output": evaluator, "requirement_gathering_mode": "", "research_mode": "", "evaluator_mode": "TRUE" # Activate refinement mode } email_two = client.with_options(span_name="email-two").prompts.completions.create( prompt_id="your-orchestrator-template-id", # Same template, third mode variables=variables ).choices[0].message.content ``` ``` Subject: Quick security solution for YMU's talent events Hi John, I noticed YMU's been expanding its roster of A-list talent lately – congrats on that growth. Having worked event security for talent agencies before, I know how challenging it can be coordinating reliable security teams, especially on short notice. We've built something I think you'll find interesting – an on-demand security platform that's already being used by several major talent agencies. Think of it like having an elite security team in your pocket, available within hours. ... ``` ## Monitoring and Optimization