of most builders’ work. We use instruments reminiscent of Cursor, Windsurf, OpenAI Codex, Claude Code, and so forth, to grow to be rather more productive at work. Nonetheless, from discussions with individuals working in non-technical strains of labor, I typically see numerous processes that may be optimized utilizing AI.
On this article, I’ll present how different non-tech industries can profit from utilizing AI. I’ll spotlight this by automating the method of discovering prospects with AI, a typical gross sales job that requires numerous guide work. The purpose of the article is to focus on how even non-technical individuals could make use of the most recent coding brokers to create highly effective automation instruments.
All through the article, I’ll be highlighting my most important ideas with:
It is a most important tip
Why do we want automated prospect discovering
Enterprise improvement representatives work with:
- Discovering attention-grabbing prospects
- Retrieving their contact data, reminiscent of their LinkedIn profile or electronic mail tackle
- Reaching out to prospects, making an attempt to arrange a gathering
From there, an account government normally takes over, although I’ll be specializing in learn how to optimize the primary three steps.
This three-step course of is normally fairly intensive, as discovering prospects on-line requires scouring via numerous LinkedIn profiles or different web sites to seek out attention-grabbing corporations. After discovering an organization, you sometimes begin searching for particular individuals within the group to achieve out to. This may normally be key choice makers, who generally is a center supervisor in a bigger firm, or a CFO in a smaller firm. After discovering the proper individual, that you must get their contact data, normally discovered on LinkedIn or on the corporate’s web site. Lastly, it is best to attain out to this individual with a personalised message.
Discovering attention-grabbing prospects
I’ll begin growing this software utilizing Claude Code. You may primarily use any coding software there, reminiscent of Codex, Cursor, Windsurf, Replit, and so forth. The primary level is the instructions you employ to make the appliance.
All the time use planning mode earlier than creating a brand new software
I at all times begin off utilizing plan mode, which tells the mannequin to learn your immediate, create a step-by-step plan, and ask any clarifying questions. That is very helpful, because it helps you slim down the scope of your software and ensures you present your ideas on any ambiguity. For instance, I obtained prompted on:
- Which location are you concentrating on (in my case, I’m prospects in Norway)
- Which programming language would you like your software in (I selected Python, however TypeScript or different languages are in fact additionally attainable)
- What are some web sites you need to take a look at (in Norway, proff.no has numerous data on corporations and workers, so yow will discover comparable instruments, and even ask your coding agent to seek out these web sites itself utilizing an internet search)
- What output format do I choose (I selected an Excel sheet)
These are all nice inquiries to make clear, which is why utilizing plan mode is so helpful.
Additionally, be sure that to immediate your mannequin to make use of publicly obtainable API’s, and solely search for data from related corporations. Fetching private data may very well be towards the laws, relying on the place you reside.
All the time present your coding agent as a lot instruments as attainable. It may very well be MCP servers, OpenAI credentials, or entry to any packages via an API.
Moreover, I additionally made an OpenAI key, which I advised Claude Code it may load from my .env file with OPENAI_API_KEY. That is helpful as a result of numerous operations will in all probability require utilizing an LLM to seek out or course of data. Thus, offering Claude Code entry to a strong API service is essential. If in case you have different related API’s, you must also present Claude Code with the documentation for these API’s and inform it to make use of them.
I, for instance, knowledgeable Claude that it has entry to internet search, and may carry out it with the perform beneath:
response = consumer.responses.create(
mannequin="gpt-5",
instruments=[{"type": "web_search"}],
enter="What was a optimistic information story from right now?"
)After I answered all of the clarifying questions, I advised Claude to start out constructing, and it constructed an software to discover a listing of prospects, returned in CSV format. This covers each step 1 and a couple of, of first discovering attention-grabbing prospects, and getting a maintain of their contact data.
After discovering all of those prospects, you must also do a guide assessment, making certain correctness. Moreover, I like to recommend prompting GPT-5 or an equal mannequin to undergo your outcomes and confirm any inconsistencies.
Have an LLM undergo your outcomes to confirm correctness
Lastly, it’s additionally necessary to abide by laws when discovering prospects. You need to solely be discovering related corporations on-line, after which discovering people manually to abide by GDPR laws. Thus, to seek out extra data, such because the identify, electronic mail, and position of particular person prospects, I manually discover the knowledge from the businesses supplied with my software.
Reaching out
After discovering contact data, you now want to achieve out. You may learn numerous stats and data on learn how to carry out chilly emails, however I’ll not get into that right here, since my focus is on the expertise and the way we are able to use it to optimize our processes.
Up so far, I assume you’ve fetched an inventory of related prospects, together with their contact data, and also you’re prepared to start out reaching out. We now need to create personalized messages to every particular person, which is fortunately a activity that LLMs are actually good at.
LLMs are capable of craft customized messages
For instance, at this stage, I’ve the next data per prospect:
- Particular person identify
- Particular person electronic mail
- Particular person position
- Firm identify
- Firm dimension
- Firm income
Additionally, basically, including extra data to your prompts is normally higher. If you happen to choose a particular type or tone in your emails, it is best to add that data. A good suggestion can also be to point out examples of you’re earlier emails, highlighting the way you write emails your self, and thus utilizing few-shot prompting to enhance output high quality.
Add as a lot data to your prompts as attainable
I’ll now use this data to draft up a personalized message. This may be performed comparatively merely utilizing GPT-5 for instance:
immediate = f"""
You're an knowledgeable at creating customized emails. You're given data
about a person and must create an electronic mail to achieve out to them for the
first time.
Title: {identify}
Electronic mail: {mail}
Function: {position}
Firm identify: {company_name}
Firm dimension: (company_size}
Firm income: {company_revenue}
Create each a topic tag, and the complete electronic mail, together with no different feedback
or reasoning.
"""
consumer = OpenAI(api_key=OPENAI_API_KEY, base_url=API_URL)
import os
from openai import OpenAI
consequence = consumer.responses.create(
mannequin="gpt-5",
enter=immediate,
reasoning={ "effort": "low"},
textual content={ "verbosity": "low" },
)When you’ve the define of the message, you possibly can then manually tweak and optimize it for the individual you’re reaching out to, given the knowledge you’ve discovered.
Now you can attain out utilizing these emails. To keep away from breaching any phrases of service and spamming individuals, I like to recommend reaching out manually and never utilizing an automatic service. I don’t condone spam emails or comparable. AI is simply used that will help you and make processes simpler, to not take away all people from the loop essentially.
Conclusion
On this article, I’ve highlighted how you should utilize the most recent coding instruments, reminiscent of Claude Code, to automate some processes. On this article particularly, I coated learn how to optimize the method of reaching out to prospects by utilizing AI to robotically discover related corporations and robotically create emails whereas staying compliant. We’ve seen immense progress with AI in the previous few years, however I nonetheless imagine AI is lagging behind on the implementation facet. Thus, in the event you may be quick at integrating AI into your day by day life, you possibly can have an enormous benefit over your friends.
👉 Discover me on socials:
📩 Subscribe to my e-newsletter
🧑💻 Get in contact
✍️ Medium
You can even learn my different articles:
