AWS AgentCore Agentic Slack Bot - AgentCore Memory and Toolsđ„
aka, be a teammate, not just a chat bot
This blog series focuses on presenting complex DevOps projects as simple and approachable via plain language and lots of pictures. You can do it!
These articles are supported by readers, please consider subscribing to support me writing more of these articles <3 :)
Hey all!
In the last article, we covered how Vera connects to tool providers through the MCP Gateway and direct connections. Now letâs talk about something that makes AgentCore feel genuinely different from Lambda: memory.
This is persistent memory that survives across conversations, across days, across sessions. Not only can users teach the bot to call them a nickname, users can teach Vera multi-step business processes: âWhen I ask for standup notes, check Jira for my tickets, pull my recent PRs from GitHub, and summarize my Confluence updates from the past week.â Once learned, Vera executes that workflow every time without the user repeating the instructions. In the first month of deployment, Vera memorized roughly 2,000 facts across our user base, including work patterns, team structures, preferred workflows, and procedural preferences.
This is one of those features where the âlearning AIâ model really pays off. In Lambda, every invocation starts with a blank slate. You can bolt on memory by writing to DynamoDB or S3, but youâre building and maintaining that whole system yourself. AgentCore gives you a managed memory service with strategies, namespaces, and semantic search out of the box.
AgentCore memory has two layers that work together. Short-term memory events capture each conversation as it happens. A backend process then analyzes those events and extracts durable facts and preferences into long-term memory records. This article covers both layers, how we use the user preference strategy to give Vera per-user memory, the identity model that ties it all together, and the tools we built so users can see and control whatâs been remembered about them.
Letâs get into it.
If youâd prefer to skip the write-up and just read the code, the entire codebase is public and MIT open sourced here.
