Corey Ganim

25K posts

Corey Ganim banner
Corey Ganim

Corey Ganim

@coreyganim

Simplifying AI for non-technical entrepreneurs. Built an eCom biz to $16 M+ revenue. Built (then sold) a coaching biz to $340 k ARR.

Build With AI Podcast 👉 Katılım Haziran 2022
124 Takip Edilen48.5K Takipçiler
Sabitlenmiş Tweet
Corey Ganim
Corey Ganim@coreyganim·
Build With AI is live. Here's what you get as a founding member for $799/year: ✅ 4-module classroom (zero to working AI agent) ✅ 7-day guarantee (working agent or full refund) ✅ Bi-weekly office hours with me and @NickSpisak_ ✅ Monthly guest workshops (90-min live builds) ✅ Quarterly build challenges with prizes ✅ The Build With AI plugin (auto-updates monthly) ✅ Community skill library ✅ Weekly AI Intel Brief Founding pricing: $799/year (first 100 members or 7 days, then $999). Join here: skool.com/buildwithai
Corey Ganim tweet media
English
7
7
79
39.9K
Corey Ganim
Corey Ganim@coreyganim·
@gregisenberg tweet below and this YouTube video are your playbook (youtu.be/BI-MNjm1tTQ?si… Build for yourself first on your own infrastructure. Make sure it works and does what you promise it’ll do. Then you can use something like orgo computer to deploy for clients (YouTube vid shows you how)
YouTube video
YouTube
GREG ISENBERG@gregisenberg

How to build a vertical AI agent cash-flowing startup: find painful workflow in a boring industry → talk to 10 people who do that workflow every day → map every step, every tool, every spreadsheet, every phone call → do the workflow manually first → be the agent before you build the agent → find the edge cases that break everything → document them in obsidian as structured markdown → set up your agent stack → hermes for the harness → obsidian vault as the knowledge base → composio for authentication across apps → build your first 1-3 skills that solve the core pain → use claude code or codex to build the product → use agents to set up other agents → use perplexity MCP and context7 for up-to-date docs → let the agent handle the scaffolding while you focus on the workflow logic → ship the agent to your first 5 customers for free → watch what they actually use it for → they will surprise you → the thing you built for isn't always the thing they need most → build content around the niche → not "building in public" content → useful content → the tips, the shortcuts, the pain points that only someone who does this workflow would know → become the person for that niche → charge per outcome not per seat → per lease renewed, per claim processed, per candidate sourced → the ROI conversation takes 10 seconds when it's tied to a result → set up watchdogs and alerts → your agent emails you when a cron job breaks or a skill fails → the customer should never have to tell you something is broken → connect to open router → see exact costs per model per task → use GPT 5.5 for tool calls → use open source for lightweight tasks → route the right model to the right job → watch your margins double → let hermes write to its own memory after every task → the agent compounds → the longer it runs the better it gets → that accumulated memory becomes your moat → a competitor can clone your product but they can't clone 6 months of context → expand the workflow → you started with one step → add the next → then the next → now you own the entire workflow end to end → you went from a tool to the operating system for that vertical → stack the agents → one agent is a side project → five agents across five customers is a business → each one runs in its own environment → you check in once a day → raise only if you need capital not credibility → most agent businesses should never raise → the margins are too good to give away equity → stay lean → stay profitable → repeat i'm rooting for you

English
1
0
3
209
Corey Ganim
Corey Ganim@coreyganim·
This is sauce. One thing I’d add: The first agent you build will RARELY be the money maker. We built 4-5 different niche agents before landing on the one the market was willing to pay for (speed to lead agents). But the lessons learned from those first agent builds are what turn the 5th, 10th, 20th agents into a 7 (or 8) figure business.
GREG ISENBERG@gregisenberg

How to build a vertical AI agent cash-flowing startup: find painful workflow in a boring industry → talk to 10 people who do that workflow every day → map every step, every tool, every spreadsheet, every phone call → do the workflow manually first → be the agent before you build the agent → find the edge cases that break everything → document them in obsidian as structured markdown → set up your agent stack → hermes for the harness → obsidian vault as the knowledge base → composio for authentication across apps → build your first 1-3 skills that solve the core pain → use claude code or codex to build the product → use agents to set up other agents → use perplexity MCP and context7 for up-to-date docs → let the agent handle the scaffolding while you focus on the workflow logic → ship the agent to your first 5 customers for free → watch what they actually use it for → they will surprise you → the thing you built for isn't always the thing they need most → build content around the niche → not "building in public" content → useful content → the tips, the shortcuts, the pain points that only someone who does this workflow would know → become the person for that niche → charge per outcome not per seat → per lease renewed, per claim processed, per candidate sourced → the ROI conversation takes 10 seconds when it's tied to a result → set up watchdogs and alerts → your agent emails you when a cron job breaks or a skill fails → the customer should never have to tell you something is broken → connect to open router → see exact costs per model per task → use GPT 5.5 for tool calls → use open source for lightweight tasks → route the right model to the right job → watch your margins double → let hermes write to its own memory after every task → the agent compounds → the longer it runs the better it gets → that accumulated memory becomes your moat → a competitor can clone your product but they can't clone 6 months of context → expand the workflow → you started with one step → add the next → then the next → now you own the entire workflow end to end → you went from a tool to the operating system for that vertical → stack the agents → one agent is a side project → five agents across five customers is a business → each one runs in its own environment → you check in once a day → raise only if you need capital not credibility → most agent businesses should never raise → the margins are too good to give away equity → stay lean → stay profitable → repeat i'm rooting for you

English
3
0
45
6.7K
Corey Ganim
Corey Ganim@coreyganim·
@gregisenberg Composio is so sick, had never heard of it until your recent pod Can’t believe it’s free tbh
English
2
0
12
2K
GREG ISENBERG
GREG ISENBERG@gregisenberg·
How to build a vertical AI agent cash-flowing startup: find painful workflow in a boring industry → talk to 10 people who do that workflow every day → map every step, every tool, every spreadsheet, every phone call → do the workflow manually first → be the agent before you build the agent → find the edge cases that break everything → document them in obsidian as structured markdown → set up your agent stack → hermes for the harness → obsidian vault as the knowledge base → composio for authentication across apps → build your first 1-3 skills that solve the core pain → use claude code or codex to build the product → use agents to set up other agents → use perplexity MCP and context7 for up-to-date docs → let the agent handle the scaffolding while you focus on the workflow logic → ship the agent to your first 5 customers for free → watch what they actually use it for → they will surprise you → the thing you built for isn't always the thing they need most → build content around the niche → not "building in public" content → useful content → the tips, the shortcuts, the pain points that only someone who does this workflow would know → become the person for that niche → charge per outcome not per seat → per lease renewed, per claim processed, per candidate sourced → the ROI conversation takes 10 seconds when it's tied to a result → set up watchdogs and alerts → your agent emails you when a cron job breaks or a skill fails → the customer should never have to tell you something is broken → connect to open router → see exact costs per model per task → use GPT 5.5 for tool calls → use open source for lightweight tasks → route the right model to the right job → watch your margins double → let hermes write to its own memory after every task → the agent compounds → the longer it runs the better it gets → that accumulated memory becomes your moat → a competitor can clone your product but they can't clone 6 months of context → expand the workflow → you started with one step → add the next → then the next → now you own the entire workflow end to end → you went from a tool to the operating system for that vertical → stack the agents → one agent is a side project → five agents across five customers is a business → each one runs in its own environment → you check in once a day → raise only if you need capital not credibility → most agent businesses should never raise → the margins are too good to give away equity → stay lean → stay profitable → repeat i'm rooting for you
English
77
50
581
45.4K
Corey Ganim retweetledi
Ryan McLaughlin
Ryan McLaughlin@trystuffco·
I copied @coreyganim’s AI Concierge offer stack. Two strategy calls. Voxer. Notion workspace. Hands-on builds. Built donkeydesk.com in 24 hours. No clients. No revenue. Just live. Can’t just clone though. Already building on top of it. Day 1.
English
1
1
9
1.1K
Corey Ganim
Corey Ganim@coreyganim·
I built 9 context documents for my Hermes agent so it operates with the same baseline knowledge as my human employees. These docs are stored in a shared Gbrain that all my agents have access to. Here's what's in each one: → company_context.md Master business overview. What the company is, how it makes money, the major business units. Every agent starts from the same baseline. → offers.md Offer catalog. What's being sold, pricing, who each offer is for. Stops agents from misrepresenting the business. → media_community_icp.md ICP for AI Operator Academy + Media businesses. Audience, pains, motivations, buying context. Sharpens content and targeting. → services_icp.md ICP for the Services business. The ideal buyer for the speed-to-lead offer. Keeps service outreach and positioning accurate. → marketing_channels.md Channel strategy. The purpose of each platform, the audience context, the role content plays. Agents tailor output by channel instead of posting generic. → current_goals_q2_2026.md Active rocks, targets, and ownership. Keeps agent work aligned with what matters right now, not what mattered six months ago. → corey_brand_voice.md How I sound in writing. Preserves voice consistency across every piece of content the agent touches. → team_roles_and_responsibilities.md Who owns what across me, Nick, Kate, and Ingrid. Improves routing, delegation, and org accuracy. → readme.md Repo-level explanation of the shared GBrain source. Lists the seed docs and their purpose. Makes the whole context system maintainable. Took me about an hour to put all these docs together but now my agents know exactly who I am, what our business does, and who we serve. This is the boring foundational work that makes agent deployments successful.
Corey Ganim tweet media
English
2
2
52
2.8K
Corey Ganim
Corey Ganim@coreyganim·
Full breakdown of the AI Concierge offer that I'm using to make $1,000 per hour: (anyone can do this)
English
6
11
83
12.4K
Corey Ganim
Corey Ganim@coreyganim·
7 ways to find clients for your AI services business (no audience required): 1. AI for Business meetups 2. Door knock local businesses 3. LinkedIn outreach (done right) 4. Free AI audits 5. Partner with agencies 6. AI Office Hours 7. Post your wins Bookmark this.
Corey Ganim tweet mediaCorey Ganim tweet mediaCorey Ganim tweet mediaCorey Ganim tweet media
English
7
11
115
5.9K
Corey Ganim
Corey Ganim@coreyganim·
@danielrbridges Cowork wouldnt be the best agent harness for speed to lead, something like a zapier agent or even a Hermes would be better
English
0
0
2
209
Daniel Bridges
Daniel Bridges@danielrbridges·
@coreyganim Would the speed to lead agent just be using Cowork with a dedicated machine to use the mail client in the browser?
English
1
0
0
147
Corey Ganim
Corey Ganim@coreyganim·
@GetAIAudit You could always do a quicker or longer one, I’ve just found that 45 mins is a sweet spot to pull out not only quick wins but potential bigger projects that can be upsell opportunities as well
English
0
0
1
243
William Gould | AI Audit
Great video Corey, enjoy your content. The one item I'd push back on is that an audit takes 45 minutes on a video call to assess their bottlenecks and recommend solutions. We've been doing it with a well thought out set of 10 questions which on average takes a client 3 minutes to fill out. The report gives them actionable insights right out of the gate. I agree there is a model for consulting in this space, but most small business owners are needing a few quick wins to start their AI Journey.
English
1
0
0
307
Corey Ganim
Corey Ganim@coreyganim·
3 AI business ideas that can replace your full time income: (All 3 models explained + easiest way to get clients 👇)
English
7
9
134
17.3K
Shanks G
Shanks G@shanksG9·
@coreyganim Can you coach me because I have started to do it too and would be great to have a mentor
English
1
0
0
126
Corey Ganim
Corey Ganim@coreyganim·
@cloudoffice21 CFO handles my personal/business finances, ops acts as my personal assistant and marketing helps with my content
English
1
0
0
105
snearch
snearch@cloudoffice21·
@coreyganim What does the whole setup effectively do for you?
English
1
0
0
110
Corey Ganim
Corey Ganim@coreyganim·
I spent the entire week building 3 Hermes agents from scratch. The full architecture: 4 separates Gbrains as the foundation: -1 shared brain (company knowledge base, shared among the 3 agents) -3 private brains (role-specific working memory) 3 separate Hermes profiles: -CFO -Ops -Marketing Agent/brain mapping: CFO -> Finance brain + Shared brain Ops -> Ops brain + Shared brain Content -> Content brain + shared brain What feeds the Shared brain: -Context repo (company docs, offers, brand voice, ICPs, team roles, etc.) -Call/meeting transcripts (syncs every 2 hours) -Gmail (syncs every 2 hours) -Google Calendar (syncs daily) Cron jobs handle the syncs which makes upkeep hands off for me. Each Hermes profile owns its own config, .env, SOUL.md, memory, logs, sessions, home dir, Telegram bot, and gateway process. Local wrapper scripts force GBrain routing to the right private + shared brain. I created the 3 separate profiles to have role separation. Each profile is a specialist in a specific role but all 3 share the same business context underneath.
Corey Ganim tweet media
English
59
85
721
38.7K
Corey Ganim
Corey Ganim@coreyganim·
@FixerWes that is the median response time in b2b sales according to a study I saw recently
English
1
0
1
208
Corey Ganim
Corey Ganim@coreyganim·
@chams_builds 100% most people never get started because they think they need to be some AI wizard. you don't
English
0
0
1
357
Chaminda Delpagodage
Chaminda Delpagodage@chams_builds·
@coreyganim for the first two models you don’t need to be an expert. you just need to know more than the person you’re helping, and have done the thing yourself hands on
English
2
0
3
406
Nick Brown
Nick Brown@NickBrownCO·
@coreyganim Would love to learn more about it. The space seems really ripe. We’re implementing AI at our company. I’ve been a user for about four years. Interested about how to offer advice / implementation to other companies.
English
1
0
0
22