Amazon Bedrock Managed Agents (OpenAI preview): setup and limits
Amazon Bedrock Managed Agents, powered by OpenAI, entered preview on 29 Sep 2026. What it is, how to run a first session, and the preview limits to plan for.
Boris Tane AI in production. How to give coding agents production context, connect them over MCP, and let AI change live systems with the right guardrails.
AI in production covers two things: using AI agents to run and debug production systems, and running AI workloads safely once they are live. Both raise the same questions about access, review and what happens when the agent is wrong.
These guides are for engineers who already use coding agents such as Claude Code or Cursor and want to point them at production. They cover how to give an agent logs, traces and infrastructure context, how much access to grant and how to scope it, how to stop an agent's change from breaking production, and how the managed agent platforms from the large clouds work and where they fall short. Each guide is specific about permissions and review, because that is where most of the risk sits.
How Polylane works on these platforms: AWS and Kubernetes.
Boris Tane More guides
How to keep AI coding agents from breaking production
Stop AI coding agents breaking production: scoped credentials, branch protection they can't bypass, required checks that block, and production-aware review.
Boris Tane How to Use Claude Code to Debug Production Issues
Debug production issues with Claude Code: get logs and traces into the session, test hypotheses against evidence, stay read-only and ship a verified fix.
Boris Tane Is It Safe to Give an AI SRE Read Access to Production?
Read access for an AI SRE is a sound first step if you scope it. The risks are secrets, customer data and exfiltration. Here are the controls and a checklist.
Boris Tane