David Shaner and Taylor Cotner spend this episode of Redacted screen-sharing everything they've built since the last one, and it centers on a framework David calls the AI-ification engine, an eight-stage method for turning any proven business process into something an AI agent can reliably run. He walks through the full pipeline, from process mapping through ongoing evaluation, and demos a new ClickUp documentation format the team built to keep every automation legible to both people and models.

Taylor takes the second half to show how he rebuilt Offline's business development system from the ground up, using a single extended Claude conversation to reconstruct years of relationship history from his email and texts, then turning it into a repeatable five-phase playbook that can research a brand-new target company from a cold start.

The conversation covers the practical side of running AI in production, too, why they dropped a synced database in favor of calling the HubSpot API directly with whitelisted fields, and an honest, unresolved discussion of how to evaluate dozens of different AI-run processes once they're all live.

Timestamps
00:00 Cold open

00:41 Welcome back to Redacted

01:53 Taylor's back from two weeks in Europe

02:15 The new "AI-ification engine" board in ClickUp

03:05 Offline's marketplace of auto-updating Claude skills

06:50 Origin story of the AI-ification engine

08:25 The 8 stages, back to back

11:30 The hiring analogy: "This is like HR for AI"

14:40 Inside the "house format" ClickUp table

16:00 Ditching the proxy database for direct HubSpot calls

18:05 Old-school SOPs vs. the new house format

20:10 Walking the company-as-lead process step by step

24:10 Why the old nested-SOP approach never got followed

29:30 Handoff: Taylor's turn

29:55 Offline's accountability chart and the visionary/integrator split

32:05 Digging up the original Claude chat that started it all

34:05 The first draft was terrible
36:50 Timeline artifact and Claude for Chrome doing the research

37:50 The five-phase business development playbook

40:00 Slotting the BD system into the AI-ification board

45:35 The hardest open question: evaluating 50 agent processes

47:00 Show notes, GitHub repo, and where to find David and Taylor

47:50 What Redacted looks for in a guest

Show notes from the episode: https://github.com/instanttaylor/redacted-podcast

Where to Find David:
LinkedIn: https://www.linkedin.com/in/davidshaner/

Where to Find Taylor:
LinkedIn: https://www.linkedin.com/in/taylorcotner/

More about Offline: https://www.linkedin.com/company/offline-media-inc-/

---

This episode of Redacted is hosted by David Shaner and Taylor Cotner, and presented and produced by NC Tweener Fund.

We couldn’t share posts like this without our amazing sponsors:

Platinum:
NC IDEA: https://ncidea.org

Gold Sponsors:
- Balentine: https://www.balentine.com/triangle-entrepreneurs
- EisnerAmpner: https://www.eisneramper.com
- Robinson Bradshaw: https://www.robinsonbradshaw.com

Silver Sponsors:
- Automated Consulting Group: https://automated.co
- Bank of America: https://business.bofa.com/en-us/content/technology-industry-group.html

------
Triangle Tweener Talks is sponsored by:

• Atomic Object: https://atomicobject.com/

Ryan Eade, Chief Product and Technology Officer at PtEverywhere, gave this talk at the June 10th TweenerClaw meetup, and it covers something most practitioners skip: how to actually keep your OpenClaw instance secure. Ryan walks through the three main ways OpenClaw instances get compromised: an open port that older versions left fully exposed, third-party skills that can carry malicious code (36% of early store listings had prompt injection), and prompt injection delivered through external content like X posts or README files. He also covers the upgrade windows that matter most; the March 12th and April 5th releases each contained critical security patches, and what to do right now: curl port 18789 on your OpenClaw and see if you get a response back. The practical framework Ryan closes with is worth listening to by itself. He calls it "staff not software" with the idea that every access decision for your OpenClaw should mirror how you'd onboard a new employee: scoped API keys with minimum permissions, a purpose-built email account, one-time credit cards for purchasing tasks, and human approval gates before any destructive action runs. If you've been meaning to lock down your setup but kept putting it off, Ryan gives you everything you need to do it in under 20 minutes.

Timestamps
00:00 Intro bumper

00:16 Sponsor recognition

01:22 Scot's intro

01:56 Introducing Ryan Eade

02:05 Ryan's topic: cybersecurity for OpenClaw

02:50 Ryan Eade

03:28 "Nobody starts with security"

04:10 Why OpenClaw isn't just a chatbot

05:26 The threat landscape

06:09 Early OpenClaw exposure stats

06:40 Threat 1: The open port

07:28 Docker's dirty secret: it bypasses your local firewall

08:07 Fix: bind to localhost and use Tailscale

09:19 What Tailscale is and why it works

09:26 Threat 2: Third-party skills

10:18 How to vet skills: pull the GitHub and read the code

10:58 Threat 3: Prompt injection from the web

11:39 How prompt injection poisons an OpenClaw session

11:47 Real examples

12:51 The full attack chain: README → backdoor → breach

13:52 System prompts vs. session instructions

14:17 The upgrade reality

15:37 Critical release windows: January, March 12, April 5

16:21 "Staff, not software"

16:44 One-time credit cards for purchasing tasks

17:19 Keep your personal email separate

17:57 Least-privilege API keys

19:10 Build in approval gates

19:52 Summary: vet skills, keep it on a leash, have a no-no plan

20:16 The port 18789 check

20:32 Closing remarks

-----

Where to Find Ryan Eade
LinkedIn: https://www.linkedin.com/in/ryaneade/
PtEverywhere: https://www.pteverywhere.com/

Where to Find Scot Wingo:
LinkedIn: https://www.linkedin.com/in/thescotwingo/
Tweener Times: https://www.tweenertimes.com/
X: https://x.com/scotwingo

---

This episode of Triangle Tweener Talks is hosted by Scot Wingo, presented and produced by NC Tweener Fund, with creative assets and design support from Walk West.

We couldn’t share posts like this without our amazing sponsors:

Platinum:
NC IDEA: https://ncidea.org

Gold Sponsors:
- Balentine: https://www.balentine.com/triangle-entrepreneurs
- EisnerAmpner: https://www.eisneramper.com
- Robinson Bradshaw: https://www.robinsonbradshaw.com

Silver Sponsors:
- Automated Consulting Group: https://automated.co
- Bank of America: https://business.bofa.com/en-us/content/technology-industry-group.html

------
Triangle Tweener Talks is sponsored by:

• Atomic Object: https://atomicobject.com/

In this episode of Tweener Claw, Robbie Allen, the Founder and Managing Director of Automated Consulting Group and General Partner at NC Tweener Fund, shares a live talk from the June 10th Tweener Club meetup in Research Triangle Park.

Robbie has spent the last year and a half deploying AI agents inside real mid-market companies, and he brings three lessons from just the last 60 days: how to build reusable AI skills that compound over time, how to monitor agents when 3 to 5 of your 25-plus will fail on any given day, and why using multiple LLMs to check each other's work has become a standard part of his workflow. Each lesson comes with a real-world example: a three-skill meeting pipeline, a monitor agent that watches the others, and a Codex Opinion skill that consistently finds gaps in Claude's output.

The sharpest takeaway: AI build costs have dropped dramatically, but support and maintenance costs have not. Non-deterministic systems are inherently brittle, and anyone telling you otherwise hasn't run them in production long enough. This is a practitioner's talk for practitioners; specific, candid, and immediately actionable.

Timestamps
01:31 Scot's intro
02:03 60 days of lessons
02:19 Three lessons preview
03:08 Robbie takes the stage
03:25 About Automated Consulting Group
04:13 Reality vs. the AI hype cycle
05:04 The Microsoft / Copilot rant
07:13 Lesson 1: Skills that build skills
08:41 Skills as reusable packages
09:21 "The sawdust of business"
10:58 Building a skills pipeline for meetings
11:57 Skills security risks in the enterprise
12:47 Lesson 2: Agents watching agents
13:44 Build costs are down
14:24 "3 to 5 of my agents fail every day"
15:44 Log everything
17:33 What causes agents to fail in the wild
18:02 Lesson 3: LLMs checking LLMs
18:13 The LLM Council concept explained
19:44 The case for a multi-LLM strategy
20:36 The "Codex Opinion" skill 21:33 Gemini Opinion & LLM Council in action
23:46 Wrap-up & credits

---

This episode of Triangle Tweener Talks is hosted by Scot Wingo, and presented and produced by NC Tweener Fund, with creative assets and design support from Walk West.

We couldn’t share posts like this without our amazing sponsors:

Platinum:
NC IDEA: https://ncidea.org

Gold Sponsors:
- Balentine: https://www.balentine.com/triangle-entrepreneurs
- EisnerAmpner: https://www.eisneramper.com
- Robinson Bradshaw: https://www.robinsonbradshaw.com

Silver Sponsors:
- Automated Consulting Group: https://automated.co
- Bank of America: https://business.bofa.com/en-us/content/technology-industry-group.html

------
Triangle Tweener Talks is sponsored by:

• Atomic Object: https://atomicobject.com/