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/

Redacted Episode 5 goes inside Offline, and what it actually looks like to wire AI into sales, marketing, and project management without a big engineering team behind you. Co-founders David Shaner and Taylor Cotner each take a turn. Taylor walks through Offline's AI lead gen pipeline: a Claude-assisted Google Places script that geocoded 2,000 restaurant locations in about an hour, a deliberate move away from LLMs toward deterministic code for market geography, and the "outreach brief," a context document the system assembles per account before any LLM writes an email. He frames the whole thing as a trust graph, working outward from existing partners in concentric circles. He also gets specific about the human-AI handoff: how a salesperson (Steve) has to trailblaze first, and why you need specific lead-by-lead feedback instead of generalizations to actually improve the system. David then demos the B2B landing page he built entirely with Claude copy from Fathom sales call transcripts, photos pulled from an AI-tagged Google Drive library, live data from the POS back end, and a review filter that's been running for four months without anyone touching it. Taylor closes with the practical bit: after a 36-hour stretch of AI frustration, he asked Claude to audit his own chat logs for recurring failures. Claude named the output a "rage log." He curated it into a "gotcha registry" and baked it into a Claude Code hook that fires during every planning step, so the same mistakes stop happening on repeat. It's a simple technique that doesn't get talked about enough.

Timestamps:
00:00 Cold open: the rage log preview

01:02 Welcome to Redacted, Episode 5

01:50 Offline's AI lead gen pipeline

04:10 Reducing LLM usage: when code beats prompts

05:00 Geocoding 2,000 restaurants with Google Places API in ~1 hour

07:42 Building the outreach brief

09:14 What salespeople actually need before writing an email

11:46 The information a good brief assembles

14:25 Hot, warm, and cold leads defined

15:54 The B2B Hinge: visualizing your lead network

18:24 Why context-aware outreach wins in an AI-spam world

21:00 The resource-constrained case for a trust graph

23:37 The human-AI handoff: salesperson ↔ automation loop

25:00 Specifics over generalizations: how to debug a sales AI

26:22 Taylor's turn: the AI-built B2B landing page is live

28:50 Tagging Offline's photo library with AI (2,000+ images)

30:36 LLM-filtered reviews: 4 months running, never touched

33:52 Building the events page panel by panel

35:07 The Slack bot experiment: Claude as project manager

37:44 What the agent did right

39:58 Project management in the AI era: ClickUp vs. Docs

42:47 The bad AI days

44:04 The rage log becomes the gotcha registry

45:11 How Claude Code hooks inject the registry into every plan

46:38 Compound Engineering and the Every framework

47:50 Guests coming up, wrap

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/

A live recording of my talk at the June 10th NC Tweener Fund Open Claw meetup in Research Triangle Park. The second gathering of our local AI agent community.

A lot has changed since April. Here's what I cover:

- Open Claw by the numbers: 300K GitHub stars, 3.2M active users, fastest-growing project in GitHub history
- What went wrong in April; broken updates, 1,400+ malicious marketplace skills, and why the community got nervous about OpenAI's intentions
- How the project is stabilizing: monthly releases, long-term support plan, leaner core
- The fork landscape: NVIDIA's NemoClaw, Microsoft's Scout, Google's Gemini Spark, Alibaba's Qwen, and Facebook's rumored $200/month Hatch
- Hermes: the MIT-licensed open-source upstart getting the most attention in the Triangle right now
- Why Satya Nadella said "OpenClaw" 28 times at Microsoft Build (and Tim Cook said it zero times at WWDC)
- What Triangle founders are actually shipping with day-to-day

Enjoy the conversation.

Timestamps:
00:02 Welcome & Cold Open
00:23 Sponsor Thanks
01:25 Scot's Intro: The Open Claw Wave #2
04:48 Live Meetup Begins
05:17 Meetup Sponsors Recognized
05:56 Talk Order & How to Give a Future Talk
06:17 Big Picture Check-In Since April
06:29 Open Claw Stats: 300K Stars, 3.2M Users
07:38 LTS Plan, Monthly Releases & Stability Signal
08:33 What Broke in April
09:27 The Marketplace Crisis: 1,400+ Malicious Skills
10:03 Jensen Huang & NVIDIA's NemoClaw at GTC
10:50 "Personal Operating System for AI"
11:15 Satya Nadella at Microsoft Build: Scout Announced
11:43 Two Worlds: Copilot vs. Open Claw Users
13:50 Tim Cook Gets 0 OpenClaw Mentions at WWDC
14:09 Chinese Model Forks
15:05 The Clone Landscape: Gemini Spark, Hermes, Multus
16:07 Facebook's Rumored Hatch ($200/month)
16:59 Perplexity Personal Computer
18:04 Hermes Deep Dive
18:47 Comparison Chart Walkthrough
19:21 Hand-Off & Wrap

---

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/