Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
4 contributions to AI INSIDERS 👨🏻‍💻
I let Instantly's AI agent build my cold email campaign
Instantly now has an AI chat that builds campaigns, automations and workflows for you. I wanted to know if it's real, so I built a campaign with it on camera. It picked the niche, the targeting and the copy fast. Honestly faster than I expected. The part worth stealing is what I did next. I asked it to go through the first 10 to 20 leads it found and check each one was a real fit before I spent a single credit. Then I kept going back and forth until most of them were. Same move works with any AI that builds lists for you. The video also covers the prebuilt agents, which ones are worth their credits, and the one I'd replace with something that doesn't charge per reply. Want Claude running your Instantly account instead? My free Backdoor MCP does that: https://www.skool.com/lead-gen/free-backdoor-mcp-for-instantly-email-bison-and-plusvibe Full video: https://www.youtube.com/watch?v=UuqgUgJAe7o&list=PL0Yyhj9Mcbg8zog1pSTOTVfmyHKbtRClF Go watch it, then tell me which part of your outbound you'd hand to an agent first.
1 like • 17h
Checking a sample of leads for fit before spending credits is the step most people skip. Same rule I use with any AI build: let the agent draft the campaign, but a person checks the list and the first few sends before it scales.
Research Agent for Cold Calls
Hey guys, I’ve made over 30,000 cold calls in the past year, so I have a pretty good understanding of what to say and how to say it. Now I’m looking to automate the research and script personalization. What works really well for me is researching each company right before calling. I enter the company name or website into a prompt I’ve built, get a personalized script based on my existing template, and make the call. The problem: this sometimes takes more than 30 seconds per company, which slows me down and breaks my calling flow. I could research everything in advance, but some phone numbers turn out to be wrong, and some contacts no longer work at the company. That means spending time researching leads I can’t actually reach. I haven’t tried batch research yet, but before spending hours doing it manually, I’d rather build a repeatable workflow that processes an entire lead list for each service I offer. Ideally, it would: - Research each company’s specific services and target customers. - Personalize my existing script without changing its wording or structure beyond the designated placeholders. - Identify or verify the relevant decision-maker and, where possible, suggest an alternative if the original contact isn’t the right person. The goal is to have concise, call-ready scripts prepared so I can focus entirely on calling. Has anyone built something similar, or can you recommend a setup for this?
0 likes • 2d
Jay's overnight batch is the way to go. One thing from running call teams: keep a column for which research detail you actually used on the call and whether it led to a real conversation. After a few weeks you'll know which fields are worth researching and which ones just slow the batch down, and you can trim the template to what moves calls.
Log the raw transcript next to what your agent saved
A tip I picked up this week and I'm adding to my test runs: for every call or message an agent handles, store the raw transcript right next to the value it saved, like the phone number or the booking time. When something comes out wrong, you can see in seconds whether the speech to text lost it, the agent misheard it, or your own workflow mangled it. Without that you end up tuning the wrong half. What's the one field you wish you had logged earlier in your workflows?
1 like • 8d
Great habit, Umer. I'd add two more columns next to the transcript: the value after your workflow cleaned it up, like "next Tuesday at four" turned into an actual date, and the value a human corrected it to when it was wrong. Over time that correction column tells you exactly which fields to fix first, and it doubles as your test set every time you change a prompt.
Workflow or agent: where do you draw the line for clients?
When a client asks for an AI agent, how often does it end up being a plain workflow with one model step in the middle? I lean workflow by default and only hand control to an agent where the path really can't be predicted, like a live phone call. Everything around it stays boring and testable. Where do you draw that line, and has a client ever pushed back on it?
0 likes • 16d
Same line for me. If I can draw the process on a whiteboard, it is a workflow. The agent only gets the step where the path cannot be predicted, and a human reviews anything that touches money or a customer. When a client pushes for an agent, I map the process with them step by step first. Once they see most of it happens the same way every time, they usually pick the workflow because it costs less and it does not surprise them.
1-4 of 4
Noel Pena
1
3 points to level up
@noel-pena-5606
Sales and marketing professional with a passion for learning and results!

Active 8h ago
Joined Sep 4, 2025
Powered by