Today I had a brief coding session with the newly launched Kiro [1]: a new agentic IDE that works alongside you from prototype to production.

Today I had a brief coding session with the newly launched Kiro [1]: a new agentic IDE that works alongside you from prototype to production.

I selected a use case I had previously coded myself, which helped me guide the coding agent through some challenging areas. It was impressive how quickly we achieved results, and the experience was genuinely enjoyable.

The use case involves generating a short advertising video from a high-level description. While the advertising video is the final output, the process also creates supporting assets like campaign descriptions, ad copy, and image assets. I requested a multi-agent implementation.

In this case the system has been provided with the following input:

“Launch campaign for a new eco-friendly smartphone that’s made from recycled materials and has a 7-day battery life”

As demonstrated in the video, this approach worked exceptionally well in this session — my impression from one build, not a measured evaluation. Together, we built a multi-agent system featuring four specialized agents: a campaign proposal agent, ad text agent, visual asset agent, and storyboard agent, coordinated by the orchestration layer to accomplish the overall task.

The implementation uses the Strands Agents SDK [2] for the agent orchestration, with models from the Amazon Nova family [3] doing the actual generation of text, images, and video content.

I’m thrilled with the results and look forward to extending this with an intuitive user interface—something I’ve never successfully accomplished on my own. It will be interesting to see how this develops with my AI coding partner’s assistance.

Have you tried Kiro yet? What are your impressions?

[1] https://kiro.dev/blog/introducing-kiro/ [2] https://strandsagents.com/ [3] https://aws.amazon.com/ai/generative-ai/nova/

• AI
• DeveloperTools
• AIAgents
• AWS