[REDACTED]: The AI Workflow Graveyard: CRMs, Agents, and... Tamagotchis?
David Shaner and Taylor Cotner dig into what happens when AI workflows move from demos into real business operations, from messy CRM cleanup to shareholder updates that actually work.
Recap: What Happened to Tweener Talks?
Earlier this month we launched [Redacted], a new podcast under the NC Tweener Talks network.
This podcast shows you the messy middle of how AI is made and tested. As we made some of the first episodes, we learned that we frequently had personal information and business secrets on screen. Instead of deleting that part totally, we’re keeping it REDACTED (where appropriate) and showing you the steps in between that everyone else skips.
What’s the [Redacted] Blog All About?
[Redacted] is a YouTube-first, twice-monthly show where David and Taylor:
Walk through what they actually shipped that week
Screen share real systems inside their business
Break down what worked, what didn’t, and why
You’ll be able to listen and watch on our normal NC Tweener Platforms. As a special, [Redacted] is getting it’s own sub-substack with us which you can find in the menu.
Episode 2: The AI Workflow Graveyard: CRMs, Agents, and... Tamagotchis?
In episode 2 of Redacted, David and Taylor get into the messy middle of building with AI inside a real business.
After compressing Offline from a 34-person team to a much smaller operating crew, AI stopped being a fun experiment and became a necessity. This episode is about what that actually looks like: rebuilding lead-gen workflows, trying to make HubSpot reflect reality, keeping AI agents alive like Tamagotchis, and testing whether Claude Code can help generate a real shareholder update from scattered company data.
What They Cover
Why David and Taylor are sharing their AI experiments publicly
How Offline compressed from 34 full-time employees to a much smaller team while still serving hundreds of restaurants and thousands of subscribers
Why CRM cleanup is way harder than it sounds
The difference between n8n workflows and locally built AI agent systems
Taylor’s attempt to build a multi-agent flow for HubSpot cleanup
The “AI existential crisis” that happens when a system kind of works, but not enough
David’s shareholder update experiment using Claude Code
How AI pulled context from financials, GitHub commits, payroll, board notes, and prior updates
Why the best AI workflows are often context problems, not prompt problems
The takeaway: AI can do a lot more than send one email, but only if you teach it where the business actually lives.
How to watch:
It’s best viewed on YouTube to fully see the examples (make sure to subscribe!)
But also available on all audio podcast players through Tweener Talks!
What’s Next?
New episodes drop twice a month/every other Wednesday. If you want to be on the show as a guest and show your [REDACTED] builds, email us here.