Googles Interaction - The feature everybody missed
In this video, we explore Google’s new Gemini Interactions API. It allows AI to remember previous conversations using an interaction ID, making prompts faster and more efficient. We also cover its multimodal capabilities, background agents, and how it modernizes the way we interact with AI.
—
TIMESTAMPS:
0:00 - Intro
—
Unlock the full potential of your online presence with Kabarza and Samuel—experts in web design and development (respectively), powered by cutting-edge AI solutions. We blend creative design with advanced tech to deliver smart, high-impact websites that stand out. Ready to elevate your business? Contact us today and see what AI-driven innovation can do for you!
LINKS & RESOURCES:
Check out Kabarza's amazing work: https://kabarza.com
Visit Samuel's website for more: https://samuelgregory.co.uk
📷 Follow on Instagram: https://www.instagram.com/cmdaishow
—
HASHTAGS:
#ai #podcast #aidesign #aidevelopment #vibecoding #webdesign #webdevelopment #ainews #webnews #designnews #devnews
Transcript
Claude are really the o only people who are really and we'll go through it later on in the episode are really pushing what these AIs can do. The ecosystem around it. They got skills um they got command agents they really pushed the hooks is another one. All these kind of tools whereas everyone else has been quite stagnant in actually developing feature sets around until the interactions API has just come out and that gives us a whole bunch of really interesting features. You can just send you can just send your query straight up, right? You can just use it like a normal chat interface. What it gives you back is a previous interaction ID. So remember we talk about stateless. AI is ultimately stateless and it gives you everything and then you need to send everything back. Every interaction is completely unique with every um chat message you send. It's just sending all of that context. Now we get an interactions ID back and we can then provide that interactions ID with just one single prompt and so we get access to the complete conversation up on um Gemini's end and all we're doing is sending a single prompt. We're not sending the complete history and you can just reference that uh inter that previous interaction ID to gain access to that statefulness which is really really cool. What that helps with was it it helps with caching because a lot of these tools they'll give you discounts and just generally the speed will help when prompts are cached if you send the exact same cash. So this is this is really cool and it's again it's just it's opening up a new level of how we interact with AI. You know what we've been stuck on the open AI standard for quite a while. So this is really cool multimodal as well. often times you've got one endpoint for your images but you've got one endpoint for your chat whereas this just accepts an image you just send it an image and it can actually do it so it's yeah um agents as well you can give it agents to run in the background whilst doing it as well so it's really just consolidating it's updating how we interact with AIS to to the modern age it's not it's it's sort of saying well this is how we're using AI nowadays how can we rewrite this interface it's nice to see that they are taking now. You can really see Google taking more of a stance, catching up and and making making an impact on the AI world. Their their confidence is there. They they it feels like they're confident in what they're doing now. And uh yeah, again, I reckon I reckon Open AAI is shaking in their boots. This is part of a larger conversation on my show, Command AI, which we stream live every single week. We discuss the news and all things related to AI in the world of design and web. Catch us next week and join in the banter.