Skip to content
Sign inOpen the app
Artwork for Using AI at Work: AI in the Workplace & Generative AI for Business Leaders
Using AI at Work: AI in the Workplace & Generative AI for Business Leaders · July 20 · 52 min

113: Using AI Agents for Business: From Chatbots to Autonomous Workflows with Bryan McAnulty

Send us Fan Mail Summary The biggest shift in AI may be moving from asking questions to assigning work. In this episode Chris sits down with Bryan McAnulty, founder and product director of Heights Platform and LatchLoop, to explore why leaders should approach AI as a worker assigned to tasks and projects rather than a chatbot producing one-time answers. Bryan explains how long-running agents can conduct research, analyze information, automate recurring work, and support teams without constant human supervision. Chris and Bryan also unpack the operating model leaders need around context, permissions, approval gates, prompt injection, process ownership, and human judgment. Listen to learn how to begin with specialized agents, protect critical systems, and use expanded AI capacity to create better customer outcomes rather than simply reduce headcount. Chapters 00:00 Episode Trailer 02:11 Meet Brian McAnulty: From Creator Platforms to AI Agents 06:36 New Chat vs. New Task: A Fundamental Shift in AI 12:08 Three Ways to Work with AI Agents 17:23 How AI Agents Actually Work Behind the Scenes 24:16 Security & Guardrails: Keeping AI Agents Safe 29:51 Will AI Agents Replace Jobs? A Better Question to Ask 33:30 Owning Your Processes: Why It Matters in the AI Era 38:06 What Is an Agent Harness? Explained 39:38 How Soon Is Too Soon to Deploy AI Agents? 43:24 Closing the Implementation Gap: Getting Started with Agents 🔎 Find Out More About Bryan McAnulty Bryan McAnulty on LinkedIn: https://www.linkedin.com/in/bryanmcanulty LatchLoop: https://www.latchloop.com/ Heights Platform: https://www.heightsplatform.com/ The Creator’s Adventure Podcast: https://www.heightsplatform.com/the-creators-adventure 🛠 AI Tools and Resources Mentioned: ChatGPT: https://chatgpt.com/ ChatGPT Work: https://help.openai.com/en/articles/20001275/ OpenAI Codex: https://openai.com/codex/ OpenAI GPT-5.6: https://help.openai.com/en/articles/20001354-gpt-56-in-chatgpt Claude: https://claude.ai/ Claude Code: https://www.anthropic.com/product/claude-code Claude Cowork: https://www.anthropic.com/product/claude-cowork Claude Tag: https://www.anthropic.com/news/introducing-claude-tag Google Gemini: https://gemini.google.com/ OpenClaw: https://openclaw.ai/ Hermes Agent: https://hermes-agent.nousresearch.com/ Model Context Protocol: https://modelcontextprotocol.io/ GitHub: https://github.com/

0:00-52:25
Play in podnod

transcript

No transcript — this publisher did not publish one.

show notes

Send us Fan Mail

Summary

The biggest shift in AI may be moving from asking questions to assigning work. In this episode Chris sits down with Bryan McAnulty, founder and product director of Heights Platform and LatchLoop, to explore why leaders should approach AI as a worker assigned to tasks and projects rather than a chatbot producing one-time answers. Bryan explains how long-running agents can conduct research, analyze information, automate recurring work, and support teams without constant human supervision.

Chris and Bryan also unpack the operating model leaders need around context, permissions, approval gates, prompt injection, process ownership, and human judgment. Listen to learn how to begin with specialized agents, protect critical systems, and use expanded AI capacity to create better customer outcomes rather than simply reduce headcount.

Chapters

00:00 Episode Trailer
02:11 Meet Brian McAnulty: From Creator Platforms to AI Agents
06:36 New Chat vs. New Task: A Fundamental Shift in AI
12:08 Three Ways to Work with AI Agents
17:23 How AI Agents Actually Work Behind the Scenes
24:16 Security & Guardrails: Keeping AI Agents Safe
29:51 Will AI Agents Replace Jobs? A Better Question to Ask
33:30 Owning Your Processes: Why It Matters in the AI Era
38:06 What Is an Agent Harness? Explained
39:38 How Soon Is Too Soon to Deploy AI Agents?
43:24 Closing the Implementation Gap: Getting Started with Agents

🔎 Find Out More About Bryan McAnulty


Bryan McAnulty on LinkedIn: https://www.linkedin.com/in/bryanmcanulty

LatchLoop: https://www.latchloop.com/

Heights Platform: https://www.heightsplatform.com/

The Creator’s Adventure Podcast: https://www.heightsplatform.com/the-creators-adventure

🛠 AI Tools and Resources Mentioned:

ChatGPT: https://chatgpt.com/

ChatGPT Work: https://help.openai.com/en/articles/20001275/

OpenAI Codex: https://openai.com/codex/

OpenAI GPT-5.6: https://help.openai.com/en/articles/20001354-gpt-56-in-chatgpt

Claude: https://claude.ai/

Claude Code: https://www.anthropic.com/product/claude-code

Claude Cowork: https://www.anthropic.com/product/claude-cowork

Claude Tag: https://www.anthropic.com/news/introducing-claude-tag

Google Gemini: https://gemini.google.com/

OpenClaw: https://openclaw.ai/

Hermes Agent: https://hermes-agent.nousresearch.com/

Model Context Protocol: https://modelcontextprotocol.io/

GitHub: https://github.com/

links1

more episodes

All episodes