AgenticMSP

AgenticMSP

MSPs: Expand Your Conversations to Expand Your AI Business

Two of the most valuable things Anthropic did with Claude recently were first to enable voice mode, and then to make voice mode two-way, at least in the desktop version.

Howard M Cohen's avatar
Howard M Cohen
Jun 02, 2026
∙ Paid

Please Note: Once again this is a particularly long post, so subscribers will find the emailed version of this issue cut off at the end. Please go to the web version for the complete version.

If You Find AgenticMSP Valuable: Please recommend AgenticMSP to your friends and colleagues. Also, please offer up your comments, observations, questions, or any other responses in the chat below. Let’s get a hearty conversation going!

Two of the most valuable things Anthropic did with Claude recently was first to enable voice mode, and then to make voice mode two-way, at least in the desktop version.

They weren’t first. Gemini has long had two-way “Gemini Live” capability, and Perplexity introduced it’s Comet browser fully equipped with an Assistant capable of two-way voice.

Conversation

Of course, another term for “two-way voice” is simply conversation. Especially with the three voice-enabled agents I mentioned, it is easy and natural to converse with them because none require you to click anything. They sense when you’ve finished speaking and then respond. Gemini, for what it’s worth, usually needs to be reminded to give you time to take a breath before answering in the middle of your question.

In my introduction to an IBM Think article later in this issue, I start out observing, “After “vibe coding” we got serious and talked about “prompt engineering” which spawned a million books and guides. Before their ink dried, we were talking about “context engineering” which had replaced prompting. Then there was “harness engineering.” Now we’ve graduated again, this time to “agentic engineering” which does seem much more all-encompassing.”

Experientially, however, I really have to suggest we’ve gone beyond that to the point where we can have a true collaboration with our AI agent assistants by talking through the development of systems rather than slaving over a lengthy prompt and then going back and revising and revising and revising.

Maintain Methodology

I’m not suggesting a return to vibe coding. Anything but. There are clear steps, stages, and phases to the development of a true system. System development methodology includes:

User's avatar

Continue reading this post for free, courtesy of Howard M Cohen.

Or purchase a paid subscription.
© 2026 Howard M Cohen · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture