Tag: AI
-
What is A2A (Agent to Agent Protocol)?
I recently wrote about MCP, a standardised protocol for LLMs to communicate with AI tools and resources. A couple of days ago Google introduced another exciting standard: A2A (Agent to Agent). Google’s A2A protocol allows AI agents to communicate with each other, securely exchange information, and coordinate actions on top of various enterprise platforms and…
-
Synthesia (Product Review)
My summary of Synthesia before using it – Using generative AI to convert text or voice into video, similar to tools like Captions and Veed. How does Synthesia explain itself in the first minute? “Turn text to video, in minutes.” So Synthesia isn’t converting voice (yet), but will use text to “create studio-quality videos with…
-
Lovable (Product Review)
Last year I started creating rapid prototypes using tools like Vercel V0, Bolt and Cursor, helping me to get ideas across and get quick customer feedback. I’ve since heard good things about Lovable, so let’s give this AI tool a try by creating a simple theatre ticketing app. On the Lovable homepage I enter the prompt…
-
Why product people should know about MCP (and what they should know about it)
I recently did an agentic AI course in which I learned how to create agents and connect them in a workflow. The need for solid data was one of the things that this course reinforced, with a strong focus on knowledge bases and Retrieval-Augmented Generation (RAG). I’ve since then learned about the Model Context Protocol…
-
DeepSeek R1 (Product Review)
By now, the Internet is all about DeepSeek and what makes its LLM different from other LLMs like OpenAI’s ChatGpT or Anthropic’s Claude. What stands out to me is DeepSeek’s thinking and reasoning output. As a simple example of DeepSeek’s ability to think in real-time, I asked it to tell me how to build a…
As I learn ... 