Lessons from our talk at AWS Built on Bedrock

We recently were invited to give a talk at Built on Bedrock, a monthly meetup for AI builders hosted by Arte Merritt and the Amazon Bedrock team at the AWS Builder Loft in downtown San Francisco. Each startup presented a slide-free 10-minute demo, followed by time for questions and mingling. We enjoyed seeing how others are finding ways to uplevel their offerings using Bedrock, Amazon’s platform for building generative AI applications and agents at production scale.

You can watch the full recording here:

And check out Arte’s recap here. Here are some of our highlights from the event:

First off, Jean Malha shared a brief demo using Amazon Bedrock AgentCore and Kiro, AWS’s new agentic IDE.

Next, coming all the way from Australia, the Bolt team shared how their coding agents help teams spin up internal tools and brand-consistent external-facing websites in minutes. They even have agents that can review your output and ensure it’s compliant with your organization’s security standards.

Following that, Britive shared how their product uses an agent to supply other agents with temporary just-in-time (JIT) access to sensitive information so that the user never has access to the security tokens, using the example of a chatbot that serves employees information about their remaining PTO.

Coreviz, a photo editing platform built on Nano Banana, showed how users can quickly search, tag, and edit a photo collection in bulk using natural language, making it ideal for commercial and law enforcement uses.

Next, Distributional CEO Scott Clark stepped up to showcase how DBNL gives teams insight into how their AI agents are behaving in production, so they can course correct. He also shared how DBNL helps teams track the effects of those changes over time, to ensure agents stick to desired behaviors. 

Finally Manifold shared how they’re building an AI agent that life science researchers can use to get faster insights from their data, using natural language to ask questions about various datasets—ultimately bridging the gap between data scientists and life scientists. 

Sign up for next month’s event on Tuesday, February 17th, 5-7:30pm: https://luma.com/gjbrd5p7

Get started

Distributional’s full service is open and free to use. Try it today to begin to explore hidden signals in your production AI logs. If you prefer, you can directly access the data from this demo and click to understand the insights in our read-only demo SaaS environment as well. We are also always happy to learn more about your use case and enterprise needs, so reach out to us at nick-dbnl@distributional.com with any questions.