🦾Eric Nowoslawski

Growth Engine X

Founder

Clay

Certified Expert

Smartlead

Instantly.ai

REITIUM

Advisor

Gated

Advisor to an exciting Startup called Gated. Gated challenges unknown senders to donate to charity in order to reach you - so everything in your inbox is worth your attention.

It's like a postage stamp for email. 

As a huge email sender, I'm most excited for the ability of our messages to cut through the noise, prove to our prospects that we are being intentional and we want to solve their problems, instead of relying on fancy copywriting and sending 10s of thousands of emails.

Gateway Regional Chamber of Commerce

Vice President

Help Chamber Members grow their business
Facilitated Connecting Members through observed Synergies
Public Policy Research and Advocacy
Negotiate discounts on behalf of the Chamber
Engaged with Local Municipalities in Economic Development and Business Policy

The Gateway Regional Chamber of Commerce is the largest business association in the New York Metropolitan Area with about 1,200 members. We hold approximately 150 events per year from large 600-person dinners to small 10-person breakfasts, and everything in between, with a great emphasis on networking and business promotion.

The Gateway Chamber has a long history dating back to 1911 when it was founded as the Elizabeth Chamber of Commerce by John D. Rockefeller and other New Jersey industrialists.

Today, the Gateway Chamber serves as an umbrella organization for a number of regional and local chambers and networking groups including: the Union County Chamber of Commerce; the Central Jersey Chamber of Commerce; the Route 22 Chamber of Commerce; the Kenilworth Chamber of Commerce; the Roselle Park Chamber of Commerce; the Clark Chamber of Commerce; the Linden Chamber of Commerce, the Somerset Hills Business Network; the Black Business Alliance; the Gateway Warehouse Association; the Gateway Hospitality Alliance; and The Irish Business Association. When you join the Gateway Chamber you automatically become a member of ALL these groups at no additional cost.

The Gateway Chamber is a strong advocate for its members. It works at the federal, state and local levels on both legislative and regulatory issues.

We consider it to be core to our mission to help our members grow their businesses, and as a result our retention rate has averaged 95% over the last five years. 

Members of the Gateway Chamber run the gamut from large corporations like Merck, Comcast, Verizon and Continental Airlines, to small and medium-sized business, to a very active home-based business group.

Director of Special Projects

CCFGiving

Operations Associate

Eastern National Academy

Instructed, refined, and improved skills for gymnasts of all levels
• Earned a 100% retention rate for all Recreational classes 3 months after starting
• Created Ninja Warrior Program that retained 180% of students over 9 months
• Manage employees and planning for Birthday parties and special events

Men's Gymnastics Coach

I am a direct response outbound lead generation expert. And by that jumble of words, I mean that I leverage cold email to build predictable revenue pipelines for my clients. 

I leverage over 20 databases to merge Firmographic, Technographic, and Persona data to build highly targeted playbooks with my clients. 

I believe we need to arm sales teams with the knowledge of their total Target Addressable Market and teach them how to score that Market for which companies have the most pain and need their solution. 

The best way to do this is to look at public indicators such as open jobs data, employee growth/attrition, social media growth, web traffic, new product launches, employee sentiment, individual employee tech investment, company tech stacks, etc.

With this data, not only are you only messaging with people that you know have a problem that you can solve, you also are armed  with powerful messaging that cuts through the noise. 

I teach sales teams to embrace technology and multiply what is possible per employee.

Instantly.ai just released something I've even gone as far to build for myself. But it's way more powerful because of their scale.

They just released their upgraded email verification enrichment for catch all/risky email addresses. 

This is huge for a company like them to be doing because they are using their scale to be able to verify the email addresses with real sending instead of an SMTP check or other methods of catch all verification. 

Now users will be able to check if anyone else on the platform has sent an email to the email address you uploaded and see if it went through successfully in the past. 

Allowing you to contact people that usually don't get as many emails because platforms have a tough time with catch all verification. 

We tried to build this based on our own sending data too but it just didn't have the scale necessary to be useful. With the amount of emails Instantly sends on a daily basis, it's incredibly valuable data for those serious about keeping their bounce rates down. 

I don't think this was publicly announced either but I've noticed that if you upload a lead list, they are automatically taking out leads that have a history of bouncing 100% of the time and I haven't even been charged for that. 

Very interesting development for them to keep pushing features for the cold email community.

Founder Growth Engine X | Clay Enterprise Partner

I've been completely wrong about AI prompting, and it's cost me thousands of dollars and it might be costing you money too. 

For months, I've been telling my team (and all of you) to structure prompts like this:

1. Tell the AI what you want it to do
2. Give it the data to analyze and reference
3. Provide examples of good outputs

I didn't realize that this approach wastes tokens. Especially when you're running outbound campaigns at scale.

I know this may seem obvious to technical people out there but I didn't even consider making a change. 

I had a call with my enterprise rep from OpenAI last week and they asked me why I wasn't using cached inputs based on my use case. 

I didn't even consider it because we use the Clay OpenAI integration.

Cached inputs save 50% on input tokens for GPT-4o mini, and 90% on GPT-4 when the input stays the same.

For those of us using AI for outbound messaging, this is exactly what we're doing. Running the same prompt structure over and over with different prospect data.

But the prompt needs to stay the same for as long as possible for the inputs to cache.

My old approach was mixing up the prompt by putting variable data (company descriptions, prospect info) in the middle.

The correct way:

Put everything that changes at the very bottom of your prompt.

Keep the instructions, examples, and framework identical at the top.

Only vary the prospect-specific data at the end.

I met with Jeff Barg on the Clay team directly about this and you shouldn't have to change all your integrations. The prompt will cache automatically with how they have the integration set up. 

This might seem obvious to technical people, but this is the ignorance debt you pay when you're not technical.

I'm sorry I made the wrong suggestion for so long.

If you're running AI-powered outbound campaigns and not using cached inputs correctly, you're burning money.

Here's everything I built with Cursor over Thanksgiving weekend. Some things were done in one prompt, some things took me a whole day. 

1. Automated our entire company/contact workflow
One form → Companies to Supabase → Contacts on-demand → Campaign auto-refill at 2am

2. Overhauled analytics

We already had pretty good analytics, but everything would run at midnight, and I wouldn't get snapshots during the day. So, I built this. 

- Snapshots of sending at 12pm, 3pm, 6pm EST
- Warnings if anything looks wrong
- Faster action on issues

3. Built our own email lookup API

One endpoint: first name + last name + domain
Checks our database cache first
Then LeadMagic → Prospeo.io → Icypeas → MillionVerifier guess → No duplicate paying for emails

4. Souped up our Google Maps scraper
- Now finds contacts mid-scrape
- Maps + contact data in one run

5. Automated campaign setup
- Settings done automatically
- Reads copywriting
- Suggests how to structure the Clay table

6. Batch API + cached inputs for scoring
- 50% off a request so we can make the prompts longer with more detail.
- 90% off GPT-5 token costs when you use a cached input on top of the batch API discount. 
- Company scoring at scale

7.  AI Lead Categorization 

- Uses the Smartlead API to pull all unassigned category leads. 
- We use the same prompt with GPT-5 Nano, GPT-40 Mini, and GPT-4.1 Nano. As long as they all agree on what category it automatically uploads the category. 

And now we only have to manually categorize what it doesn't agree on. This was a way harder issue than I thought, which is why I kind of hammered it with the three APIs, and we only have to filter 30-50 replies a day manually.

8. Bulk Contact Enrichment Flow for our biggest senders. 

We have 6 customers sending 50k+ emails per day (1 sending 120k emails per day) that just need a ton of data. 

I'm right this second processing 14M leads to be enriched, qualified, and distributed to the right campaigns. 

Can't wait to see what I can get done this week in Cursor.

Made this video explaining how you can use Cursor to scrape Google Maps and stop messing with custom coding it yourself. Here's the overall guideline to get this done below. 

Why Scrape Google Maps?

LinkedIn isn’t enough: Some businesses, especially local ones, lack a LinkedIn presence.

Google Maps is universal: Almost every legitimate business is listed here.

This method is ideal for local businesses or industries with limited LinkedIn activity.

Tools You'll Need:
Cursor: An AI-powered coding assistant and development environment.

Google Maps Extractor API:
RapidAPI version: Affordable and reliable.
Serper.dev, Outscraper, or similar APIs are also compatible.

CSV of ZIP codes or locations: Optional, but useful for targeted searching.

Clay or CRM: For storing and using your scraped data in email workflows.

Step-by-Step Instructions
1. Get Your API Access Set Up
Visit RapidAPI.com's Google Maps Extractor page (or your preferred API provider).

Subscribe to a suitable plan (e.g., $100/mo for 500,000 requests).

Copy your API key from the provider.

Note: One API request = 1 Google Maps page of results.

2. Open Cursor and Start a Project

Launch Cursor and create a new workspace.
Use natural language prompts like:
"Help me set up a workflow to search Google Maps for businesses in a CSV of ZIP codes. Use the RapidAPI Google Maps Extractor endpoint."
Cursor will write the necessary code for you (this might be Python, JavaScript, etc.).

3. Teach Cursor the API Endpoint
In Cursor, paste in the API documentation from RapidAPI (e.g., the search or locate endpoint).

Show it the input parameters and expected response format.

This improves Cursor’s ability to generate valid code.

4. Build Your Scraping Workflow
Provide prompts like:
"Loop through this list of ZIP codes, perform a Google Maps search for 'restaurants', and save the business name, address, category, and phone number to a CSV."

Modify as needed: e.g., "Go 3–5 pages deep" or "also fetch review data".

Let Cursor adjust the code and test locally within the tool.

5. Once you’ve scraped your data:

Export it into a clean CSV.
Import it into Clay to find owner email and contact information.

Here's how we custom coded a process to make sure all of our cold email campaigns are full of leads and get warnings when they aren't.

For years, it was the same manual process: download CSVs, upload into Clay, repeat.

So we built a system using Cursor, Supabase, Clay, and Railway.

Here are the inputs:

- Campaign ID
- Link to TAM list
- Webhook to Clay

Supabase stores:
- Campaign record
- Job record
- Scraped contacts

Cursor handles the scraping:
- Scrapes all contacts from the provided link
- Stores them in Supabase

The nightly worker (runs on Railway at 2AM ET):

Checks all campaigns + jobs.

Decides how many leads to send to Clay webhook.

Batch size options: 500 / 5,000 / 50,000 per day. really anything that you want

Tracks whether each contact was processed or used before.

Clay staging → processing:

Staging in Clay ensures the contact has never been used for that client.

Approved contacts move to the processing table (cleaning + enrichment).

Auto-delete on the Clay table keeps the system running autonomously.

Smartlead:

Leads flow into active campaigns automatically.

The alerts:

Supabase sends a Slack message when all contacts are processed: "All contacts processed" warning.

This tells us it's time to add more leads or the campaign will run dry.

Optionally for you, we use ClickUp analytics to verify leads are being added.

The outcome: we never have to manually upload CSVs again, and we get proactive warnings before campaigns run out of leads.

How are you currently managing lead intake for your cold email campaigns?

I was just thinking about how far we have come since AI. Here's a list of data points that used to be cutting edge and are now so easy with AI. 

When I first started my agency, one of the things we were asked to do was score a company for any signs of GDPR or SOC II compliance. That used to be a crap ton of google search operators (that each cost .01 per call). 

Now you can use a website markdown like Firecrawl to get what you need and score it with AI.

I had another customer that wanted to know 

1) if a company offered phone support and if so
2) what times were they available. 

Again, a google search nightmare and running tons of if/then formulas to parse out the times that they were available on the phone. 

Now you can easily just ask Claygent to get this information for you from the homepage. 

We also had someone that wanted to take a screenshot of an ecom companies sustainability page and put it in the email. 

Wow so many problems. Finding the page, taking the screenshot, saving the screenshot, finding screenshots that had pop ups and deleting them, etc. 

Now browser automation companies can take care of all that. I'd still find the page with Claygent to get down on that compute time and then have Browserbase navigate to the page, make sure there are no pop ups and then take a screenshot. 

What's possible for sales and marketing teams is just getting crazier and crazier with all the new AI tools.

Brandon Charleson

Top of Funnel

Top of Funnel is a veteran-owned growth marketing agency where our mission is to help your company grow in all aspects of lead-generation -- sales, marketing, and recruiting/sourcing efforts.

Cold email outreach: We specialize in the latest AI tech-enabled, automated, and hyper-personalized targeted outreach to drive opportunities for businesses. Simply put, we bring interested leads to you who fit your ideal customer profile.

Digital marketing: We specialize in search and social media marketing to help B2C companies reach their ideal customer. As an expert filmmaker and storyteller, we leverage the latest storytelling mediums to grow your brand in a compelling way.

Website design and optimization: Your website is a lead generation tool, we help you design a lead-generation machine! Website design, optimization, SEO, we do it all.

We are proud to have worked with some notable hyper-growth startups through Fortune 500 companies named Top 100 Forbes experts in 2023.

If you or your sales team find yourself spending tons of time the process of prospecting for new business, reach out to contact@topoffunnel.com.

Proud to be veteran-owned and operated.

I push the limits of Clay and show all of my workflow secrets to help the best of the best "Clay-makers" out there. Specialize in all things AI and automation at scale.

AI/Automation Consultant & Certified Product Expert

TechRecruiterPro

TechRecruiterPro is a Forbes.Jobs endorsed and veteran-owned executive search and recruiting partner and NPAworldwide recruiting partner. We consult and help companies find the right candidates and other tech specialists for much needed roles.  

Experience with small VC and seed-funded startups, established SMBs, and Fortune 100 corporations. 

Proven history in the technology space including Frontend, Backend, and Full stack software developers with various modern and legacy tech stacks. 

Specialties include:
- Fintech Web3 (blockchain, crypto, NFT) development roles
- Artificial Intelligence (AI), Prompt Engineering, generative AI and NLP
- Application and Web software development & engineering, IT/Technical roles (Frontend, Backend, Full Stack Developers)
- Cybersecurity, database, quality, and implementation roles
- C-Level Executive and Director roles
- Creative roles
- Consulting roles (including IT Strategy and Business Process Outsourcing (BPO))
- Marketing and advertising roles (programmatic)
- Defense & Space, DoD and cleared professional roles
- Manufacturing
- Technicians
- Accounting

If your company is hiring and struggling to find the right person for the job, reach out to us and we are happy to help. 

Contact info:
brandon@techrecruiterpro.com
(415) 862-1960

Recruiting Partner & Owner

Charleson Media

Charleson Media is a multimedia production company. Our strength is the ability to leverage the latest technology and produce visually compelling media.

We have highly skilled and well-versed graphic design, creative, technical writing, video production, photography, animation and web development professionals ready to serve our clients. 

We serve commercial companies from small startups to fortune 500 as well as government agencies of all types. 

Video production:
From ideation to delivery. We help script, storyboard, shoot, edit, and deliver professional video media. Specialties include narrative, documentary, and promo commercials. 

Website development:

- Full stack web design from frontend (what you see) to backend (how it operates)
- SEO optimization and planning
- Content strategy and generation for business

Areas of expertise:
- Website Design & UI/UX Development and SEO (Search Engine Optimization)
- Digital Marketing Strategy
- Motion Graphic and VFX Design
- Photography and Cinematography
- Videography
- Screenwriting/scriptwriting and storyboarding
- Pre-production, production, and post-production walk-through
- Lighting and color science
- Aerial and Drone Photography and Cinematography

Founder & CEO

NPAworldwide Member-Owners

Our members deliver results because they have the support of nearly 500 recruitment firms behind their search efforts. The cooperative spirit of a member-owned network means you pay for one firm’s services while leveraging the strength of the entire global network.

This includes:
-Speed to hire to fill critical rolls, leveraging a global network
-Global reach, members worldwide
-Local Recruiters to leverage relationships at the personal level, bringing you the best
-Passive candidates - Some of the best candidates are the ones that are happy, well-taken care of, and are not actively looking.
-Multiple search firms - leverage a global network while paying one fee

Member / Owner

KIHOMAC

Worked as the key internal full-cycle Tech Recruiter/Talent Acquisition Specialist for various roles including Engineers, Engineering Technicians, Sheet Metal & Composite Technicians, Management, Logistics , and Supply chain. Advised and collaborated with Hiring Managers to develop effective hiring strategies.

Principal Technical Recruiter / Talent Acquisition Manager

United States Air Force

Source, screen, and vet candidates with professional backgrounds including technical and healthcare roles. Manage pipeline of candidates to process into commissioned roles within the Air Force.

Roles include:
- Technical and Engineering roles
- Healthcare roles including doctors, nurses, and allied health roles

Senior Recruiter

Source, screen, and vet candidates for processing as enlisted members of the Air Force. Manage, consult, and mentor candidates with various backgrounds into roles of the enlisted force of the Air Force.

Roles include:
- Technicians
- Mechanics
- Special operations
- Linguists
- Intelligence/Cybersecurity

Recruiter

Aerospace Propulsion Craftsman

AI-powered junkie / Cold email strategist / Marketing & Growth Advisor / Headhunter

(TL;DR) As an AI and automation expert, I help companies develop their lead-generation and go-to-market strategy to implement AI/automation workflows which allows teams to scale quickly, save time and capital. Some people call us an "automation wizard" because we just make some magic happen on the backend!

Just like you, I wear many hats in life: Digital Marketer, Executive Recruiter, Director/Filmmaker, Full Stack Web Developer, Air Force Veteran, and major techie embracing the AI revolution with generative AI. But above all, I'm a family man to my wife and kids.

I thrive on helping people and companies succeed. Whether it's working with a startup to get off the ground, helping a parent who lost their job find their next big career, or telling a compelling story through video, I love connecting with people.

As an AI and automation expert, I push the limits of automation to help businesses grow at scale and reduce time spent on mundane, repetitive tasks. If you're a business owner struggling to find that "go-to-market" strategy or if you and your team find yourselves doing the same manual steps day after day, let's chat.

I am also a filmmaker/digital creator/part 107 drone operator and went to LA Film School where I got to work with and be taught by big budget films. Perhaps you have some upcoming video ideas and need help bringing them to life? Let's chat about that too!

My job is to help you and your business succeed. I do the heavy lifting in areas like marketing, video production, and automation. Having worked with Forbes as a Top 100 industry expert in tech, I bring a wealth of experience and knowledge to the table.

If you're building an awesome SaaS product/business and need help with marketing or have a video idea but aren't sure how to get it on paper, let's connect.

I am your AI Automation Consultant, Recruiter, Filmmaker, Video Editor, Script Writer, Website Developer, Creative Director, UI/UX Designer, AI Prompt Engineer, Digital Marketer, and most of all, your teammate to see you and your business succeed!

PS - why list so many titles? Three letters: SEO. 😉

When I'm not working, I enjoy scuba diving 🤿, shooting video/photos 📸, hiking 🏔, high-intensity training, lifting heavy weights, shredding snow on the mountains 🏂, and teaching people how to live their best life through nutrition coaching and CrossFit training. 🏋🏼‍♂️

I think I've created a monster...

In fact, I think I created a B2B team of monsters...

Using Cursor, I just created a "cold outbound dream team" that takes any list and will apply a team of 6 AI Agents that will completely do everything for you, from source to send.

This is for B2B Outbound teams, recruiting/headhunters, and anyone who does cold outbound really...

Here is how it works:

The frameworks around these agents is CrewAI, where agents can be very easily configured to how you want to create a team. Think of it like having a team of people with a Supervisor and Individual Contributors (IC). 

Just like any Supervisor, it will need a bigger LLM for it's responsibilities, reasoning, and delegation. 

The IC Agents are responsible for lower-level and specialized tasks. This is why I have separated them out to be super specialized in what they do:

We have:

➡️ LeadMagic Agent which finds and validates emails

➡️ Ocean.io Lookalike Agent which will expand your list by finding lookalike companies and people.

➡️ Instantly.ai Agent which specializes in cold email campaigns and analytics.

➡️ HeyReach.io Agent which specializes in LinkedIn campaigns to connect with people.

➡️ Firecrawl Agent which specializes in web scraping, data extraction, and company research/scoring.

If all of this nerd talk goes over your head, this is literally a team of six employees that never call in sick and will generate new opportunities for you and your business. 

The catch?

I'm giving this away for FREE. No gates, no BS, just trying to help fellow sales teams generate opportunities so we can keep feeding our families using the best tools.

Link: https://lnkd.in/eC_FRn6p

Merry Christmas. 🎅🏼🍻

AI-powered junkie / Clay & Automation Expert / Cold email strategist / Marketing & Growth Advisor / Headhunter

Instantly.ai and HeyReach.io just dropped a MAJOR unlock for omni-channel!

Just in time for holiday pipeline boosts.. 

Now you don't have to dive into crazy automation triggers and actions to go chasing your ICP. 

If your prospect doesn't respond to your LinkedIn outreach? No problem...drop 'em an email!

If your prospect doesn't respond to your email? No problem, send 'em a connection request!

We've been doing this forever outside of the platforms, but now it's even easier. 

PS -- AI Prompting + Sora 2 + me jamming out in Adobe Premiere Pro is just wayy too fun. 🤩

Wife and I thought we were doing a 5K, turns out it was 5 mi 😬

Turkey trot ✅

Now time for 🏈 , 🦃, and 🍻

Happy Thanksgiving!

No alternative text description for this image

There's a new data format that's been going viral these past few days and it's challenging the standard "JSON" output. 

It's called "TOON" which stands for Token-Oriented Object Notion. 

It aims to simplify the data structure by being more token efficient when using AI applications (especially when context windows are a current challenge). 

I've tested this and already implemented it into the upcoming Instantly.ai's MCP Server, and already showing improvements in how the responses are handled, thus saving tokens. 

I will say it's a novel idea, but it's not a direct replacement. There are various reasons why JSON still is still relevant, this is why I've implemented things like a "smart handler" where if the output from the MCP Server is uniformed, then it can handle the response on the server-side and respond back to the User in TOON format which will consume less tokens -- thus spending less $$. 

I've also implemented a JSON to TOON Converter on the Top of Funnel website, case study on my findings, and a good educational piece on what it means if you should be aware and consider using it for yourself. 🍻 (link below)

If this post made you go cross-eyed, just know that "Jason" is still a real person and isn't turning into a cartoon any time soon. 😜

https://lnkd.in/gZE3uBBX

I cannot say enough when it comes to how much I've loved Cursor and how much leverage you can pull with web-scraping and GTM...

For this client, their TAM is not so present online, they definitely do not have a LinkedIn, and there is definitely people who work for certain organizations where if we find their name, and we know the permutation of how their emails are structured in the org, we can get a valid email to send 'em a message.

We do this many times to make sure we leave "no stone unturned" when really going maximum effort for our clients. 

In Cursor, we have everything we need for full context of what the client's persona is, their ICP, all CSVs, all Claude Skills and Cursor Rules, and we set it up in such a way that we know where we have scraped, we know the entire status of their TAM, and we set up a separate Scraping Infrastructure within the project.

Once we've identified names and how the org is structured, we run LeadMagic to validate these emails, which has totally given us opportunity to reach out to these untapped markets where they hardly exist...

Once we have all of this data pulled into the project, we upload to Clay to give it any last touches and send to Instantly.ai for outbound.

These are the type of people that truly respond to cold email (trust me..) 🍻

This is going to sound fake, like I'm blowing smoke & mirrors...

But last night I deployed over 2000 Agents inside of Claude Code new web platform to go in a massive coding sprint to go "full send" while they all worked in parallel & simultaneously without any problems. 

Anthropic was gracious enough to add a $1000 credit to test and build across all projects and aspects I could possibly think of... and I was certainly up for the challenge..

The coolest part is that they all coded and built each task FULLY while I slept last night. 

It wasn't easy, but here is what I was able to do:

➡️ Enhanced Top of Funnel's current and new offerings. Better client experience including being able to add the 'vibe-marketing' aspect I spoke about in my YouTube videos and recent posts. 

This will allow for existing & new clients to really go multi-channel & for us to be a long-term partner in all things 'top of funnel'... 

Also built more internal systems for my team & I to use as a true operating system & be as efficient as possible in order to keep client experience the best we can with systems. 

➡️ Built a fully functional V1 MVP of a Client's idea that they were otherwise not able to afford or even know how to do just months ago. We've been talking about this idea for months, and the budget/timeline just was not realistic. 

Now... it is and has been done. I am now able to show his dream right before his eyes. 👀

➡️ Built a Tesla community light-show SaaS/marketplace where the Tesla community can create awesome light shows using the funnest & game-changing features that a lot of people don't even know their Teslas can do.

➡️ Built a fully functional gym management platform, GoatFit. My wife & I had this idea for months while on a camping trip. I have wanted to go full send & are nearly there for my friends/partners who own CrossFit gyms to begin testing, and then we will launch.

➡️ Expanded on the B2B GoatFit platform and went B2C by creating a fully implemented chat experience for those who want to leverage AI in the best ways that is tailored to each individual person and truly get the best programming and recommendations they can be. After all, to be the 'goat' of something and to be 'fit', this is IMO what it takes to be the greatest you can ever be in your life. 

➡️ Built a community platform I've dreamed of making forever now, AI-Powered Junkies, where people I talk to everyday, people I want to talk to, and people who just want to learn and are just getting into all this "AI stuff" can actually have a good solid platform to 'nerd out' and learn from each other. 

Obviously this type of stuff is very overwhelming and moving so fast, and the documentation is hardly out there. So the best way to learn this stuff is to experiment (just like I did in this Claude Code), and to learn off of each other!

This post is clearly getting long, so more info on HOW I did it with a YouTube video coming! 🍻

PS - Best LLM to date for me is Sonnet 4.5!

Most of the time when you’re working with AI models like Claude, ChatGPT, Gemini, or Grok, the major players get the job done.

In fact, for 99.9% of use cases, they do it extremely well.

But there’s that remaining 0.1% of use cases—where you need information or want to do something the LLM simply won’t do or won’t give you an answer for.

That’s because these models have built-in bias and guardrails.

For most people, that’s a good thing. It’s a safety measure.

But for others (like myself), this is where open-source and open-weight LLMs like the ones on Hugging Face or running locally through LM Studio become a huge asset.

Every model carries the bias of its training data. That bias influences how it answers you and how you interpret what it gives you. Whether that information is “true” is often subjective.

Knowing how to work with both closed-source models (ChatGPT, Claude, etc.) and open-source/open-weight models is the perfect balance when you’re pushing the limits of LLMs to get the information or results you actually need.

The right LLM for your use case absolutely exists.

You just have to know which lane to choose so the LLM doesn't say "no" to you. 😉🍻

Anthropic released "Claude Skills" some time ago for a variety of use cases in helping AI Agents be more effective and useful.

Thing is, I don't think many people actually know the true leverage and potential this brings...

If you think about it...for any company that brings on a new employee, you immediately want to do two things:

1️⃣ Onboard them as fast as possible on how the company operates and get them acquainted with their new role. 

2️⃣ Leveraging the new employee's previous skills and knowledge to be able to immediately get to work. 

This is the exact same frameworks around what "Claude Skills" brings when we work with clients and for us internally to stay sharp and perform the best we can.

Inside of Cursor, we always import our 'tofu-claude-skills' which immediately injects the skills for a variety of use cases:

👉🏼 AI Expertise in pushing LLMs to their limits and staying up-to-date

👉🏼 Domain generation and purchasing to build cold email infrastructure

👉🏼 Copywriting ideation to propose to the client with their custom persona applied

👉🏼 Deliverability and analytics management with Instantly.ai

👉🏼 Multi-channel and overall marketing mastery for both GTM and RevOps to go from 0-1, 1-100x, and 100x to infinity

👉🏼 Sales intelligence, sales call feedback to always refine and sharpen sales skills to articulate true and maximum value. 

Thing is...any "skill" we have is knowledge and experience of what we already know. Contrary to that, there is always also knowledge debt of "you don't know what you don't know"...

Applying Claude skills and AI Agents to this really helps us to stay unbiased, apply unknown knowledge so we can continue to perform for our clients the best way we can no matter what. 🍻

Outside of web scraping, cold email, and marketing, two of the MAJOR tools we use every single day in every day ops is Slack and ClickUp.

After all...our business runs on systems!

Slack is a no-brainer (duh).... we communicate, react, virtual hug, send GIFs, (you know what I'm saying...)

We use ClickUp for many things, but key things are task prioritization and tracking. 

OK soooo what's your point!?

One of the HUGE unlocks is being able to leverage MCP Servers to connect these tools in a way that I don't have to copy and paste or explain myself for simple things. 

I can now easily use Claude or Cursor and just send updates per client within the codebase or what I did to communicate to the client/my team on anything. 

There IS an official ClickUp MCP server which works great

Slack does not have an official MCP sever, so I have built one out and already (and open source) and seeing massive unlocks for this purpose. 

Link in comments!

Anthropic's Claude Sonnet 4.5 has been the GOAT for me as a daily driver in Cursor and nearly everything we do. 

One of the biggest advantages of the new Claude models are that they have context awareness, allowing them to track it's remaining window throughout a conversation. 

It's ALL in the prompting and knowing which model you're using and how to really push its limits...

There are two advantages on why you should read the fine print:

1️⃣ It allows you to not be stopped right in the middle of a task with the infamous "you've reached the limit of this conversation, start a new thread" like we see in the Claude. 

2️⃣ You can go further! If you use a sample prompt, like what is displayed from Claude Docs, it will go FURTHER and continue the task. Here is the sample prompt:

"Your context window will be automatically compacted as it approaches its limit, allowing you to continue working indefinitely from where you left off. Therefore, do not stop tasks early due to token budget concerns. As you approach your token budget limit, save your current progress and state to memory before the context window refreshes. Always be as persistent and autonomous as possible and complete tasks fully, even if the end of your budget is approaching. Never artificially stop any task early regardless of the context remaining."

Another great thing about the new Claude models is that they even have a "memory" tool which is becoming tons more usable across various chats so that way you don't have to continue to repeat yourself. 

If you know you're going to go off on a longer task, it's worth also prompting something like "This is a very long task, so it may be beneficial to plan out your work clearly. It's encouraged to spend your entire output context working on the task - just make sure you don't run out of context with significant uncommitted work. Continue working systematically until you have completed this task."

Combine this with Claude's new "Skills" and you're able to be tons more dialed in without having to explain yourself every time. Simply push that Skill to your Github, and then you can pull that Skill into any other project easily. 

This applies to everything, including:

➡️ Building apps

➡️ Building GTM mastermind projects and databases for clients

➡️ Making sense of literally any use case where you feel a bit scattered or overwhelmed, Claude can surely help you organize and put them into executable steps, especially if you use "Plan" mode in Cursor. 

The sauce to all of these best ways to use LLMs is always the documentations that the makers themselves post:

https://lnkd.in/g_sQysPm

Open article: Prompting best practices by platform.claude.com

One of things I am also doing with Cursor is making "myself" a project where I can essentially give it a role that it is a health and fitness coach to analyze, make recommendations, and give me suggested improvements on ensuring I am always performing at my best to continue to learn/grow, be a better person, a better husband/father, and keep quality of life high. 

The way I set this up is simply open an empty folder, call it whatever you'd like, select "Plan" mode in Cursor, then just brain dump on everything you want from your idea and how you want it executed. From here, I can set up a Github repo, ensure things I want omitted is added to the .gitignore, then I can easily call Claude Code or remote Agent to create a branch, submit a PR/merge, and now I have myself a health/fitness operating system. 

This is a very unique use case, but IMO, we are only limited by what we are exposed to mentally and physically, who we surround ourselves with, and what is "humanly possible"...

This comes into play with ALL aspects of life, but the most important one is clearly taking care of yourself physically and mentally.

Some might argue that "AI Brain Rot" could take over and send people down a rabbit hole of non-productive things, and you'd absolutely be right...

But the key thing here, is being acutely aware of what is actually real, what goals and objectives you want to achieve, I think there is a self-imposed radar where you just "know" what to do and what is the right choice. 

You never know what you might discover and be exposed to, and there certainly have been some amazing real-life case studies on how AI has improved health overall.

Anyone else doing this sort of thing?!

PS -- By the way, Cursor's Plan mode just got another major lift by easily choosing how you want to execute on your plan for anything, which is 🔥

There has never been a better time than now to be a "Builder" ...

I remember when the App Store first came out and there were hardly any apps in the apps store. 

Now (as we all know), the iOS App Store has anything and everything on there. The ecosystem is nuts.

Apple just announced their new "Mini Apps" Partner Program where you can integrate and monetize in new ways, which is a new unlock for many devs. This program is not new to Apple, but they have recently slashed the commissions in half in order to push this further and enhance the ecosystem even more. 

I am a firm believer that 2026 is the year in which more SaaS and web apps are becoming more and more integrated with each other, and nearly all will have their own Chatbot or integrate with an existing Chatbot. 

Whether that is baked in or via protocols like MCP (or "Connectors") -- integrations and partnerships are never more important than now to stay relevant.

I use xAI's Grok every single day..

I use it on my phone, 

I use it in my Cybertruck, 

I also use it on my Mac (in browser), there is just one problem..

There is no macOS native app -- SO I built one!

FREE to download - link is here:

https://lnkd.in/eVj3C49R

One of the biggest programs in the Air Force (and all branches) is recognizing those who serve with outstanding service in effort to give them promotions, awards, and decorations.

Today, my leadership came to me asking if I knew a way to not only to digitize the current methods (i.e manual ways with paper), but to set this up in a much better way that is scalable. 

The catch is that my leadership was thinking this was going to take a lot more time (such as by next week). 

This task took us ~20 min and now they have a new and very easy way to track this entirety.

I pulled up Grok, Cursor, and we jammed this out quickly by speaking in realtime to Grok. 

Have it output all of the info we needed based on what was already tracked and what we have. 

Put that CSV into Cursor to output an excel with formulas and dropdowns to standardize it for apps we already use.

Deliverable done. ✅

Needless to say, got to tell the unit how easy and how much AI can save so much time. 🍻

Excited to be joining Hans Dekker and Ilija Stojkovski next week on how to make your multi-channel campaigns even easier!

If you're looking to learn more on how you can leverage both your LinkedIn and cold email outbound motions with simple and practical use cases, we'd love to have you join. 🚀

Getting started with multi-channel outreach doesn’t need to be complicated.

We’re hosting a session on Dec 3 to give you a clear, practical look at how the new Instantly.ai × HeyReach.io integration works, and how to use it to simplify your outbound workflow.

Register here 👇

Your New Outreach Engine: HeyReach × Instantly Live Demo & Use Cases

taplio

The Battle

🦾Eric Nowoslawski

Brandon Charleson

Followers

Posts

Engagements

Likes

Performance Score🦾Eric Nowoslawski's LinkedIn Performance

Performance ScoreBrandon Charleson's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

🦾Eric Nowoslawski

Brandon Charleson

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}🦾Eric Nowoslawski's LinkedIn Performance

Performance ScoreBrandon Charleson's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance Score🦾Eric Nowoslawski's LinkedIn Performance