AWS Bedrock

Amazon Bedrock AgentCore harness: a first look

I created an AgentCore harness in the AWS console with no docs, added a browser tool and memory, saved a memory from the CLI, and the agent read it back.

26 min · 2026-11-08 · Watch on YouTube

The main idea

In the video I explore Amazon Bedrock AgentCore with no docs and no recent tutorials. I wanted a free-flowing session to see where I land. Creating an agent in the console starts with a harness name. I think of the agent as the model plus the harness.

I chose the GPT-6.1 Terra model with the Bedrock API source, because Mantle only had the 5.6 Terra. I wrote a system prompt for drafting tweets, enabled memory with a new memory managed by the harness, and added the browser tool. The console also shows export to code instructions and invocation code with boto3.

The browser tool bills by GB hour, and memory bills for ingestion, retrieval and storage. The agent opened my website and took a screenshot, but I could not open the file. It took a long route, through a base64 version, to see the image on my machine.

For memory, auto memory had already saved six facts from my playground chat. I saved a memory from the AgentCore CLI: my favorite cloud is GCP, but I also use AWS. I then asked the agent for my favorite cloud, and it answered GCP. My own hook that blocks Bedrock calls also got in the way and I had to unblock it.

Key points

Chapters

  1. 0:25Creating a harness in the console
  2. 3:57Enabling memory and the browser tool
  3. 6:53Export to code and costs
  4. 11:07Browser tool takes a screenshot
  5. 20:44Saving a memory from the CLI
  6. 24:36Agent reads the memory back
Free live lesson · Dec 7The AWS AI Agent Deployment ChecklistOne hour, live, with Saurav. Free.
Save my free seat →
Get new videos and tips by emailOne short email when there is something new. Unsubscribe any time.

More CloudYeti videos