Use Orq.ai as the model control layer for Amazon Bedrock AgentCore. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your AgentCore agent logic or runtime deployments.
What is AWS Bedrock Agentcore?
Amazon Bedrock AgentCore is AWS’s agent runtime for building, deploying, and operating AI agents at scale, with built‑in observability via Amazon CloudWatch and OpenTelemetry, plus native integration into Bedrock models, memory, gateway, and tools. It helps teams focus on agent workflows instead of wiring every monitoring, routing, and deployment component from scratch. Learn more here.
How the integration works
Step 1
Point AgentCore at Orq.ai’s router
Configure the Bedrock model invocations inside your AgentCore agents to use Orq.ai’s OpenAI‑compatible base URL (via Orq’s Bedrock provider or HTTP tools) instead of calling every LLM provider directly. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.
Step 2
Enable tracing from AgentCore to Orq
Route AgentCore’s LLM calls through Orq.ai’s AI Gateway / Router while keeping AgentCore’s CloudWatch and OpenTelemetry observability enabled. AgentCore continues to emit metrics, spans, and logs for agent execution, and Orq logs the LLM interactions and cost metrics for those requests.
Step 3
Define routes, fallbacks, and policies in Orq
Create routes for key AgentCore workflows and assign them model tiers, fallback chains, and region/data policies. AgentCore sends the model request to the configured Orq route, and Orq applies the routing rules you define before invoking Bedrock or other providers.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for AgentCore agents, and run evals or experiments on their traces. You can then adjust routes, models, or prompt configurations centrally where supported, without changing AgentCore’s agent runtime or deployment pipeline.
Use Cases
Multi‑agent products with real observability
Trace which AgentCore agent, step, tool call, and model contributed to a failed workflow or unexpected outcome, combining Bedrock’s CloudWatch views with Orq’s router‑level traces.
Cost‑aware internal tools
Route routine steps to lower‑cost models while keeping complex reasoning or high‑stakes flows on stronger routes configured in Orq, all still running through AgentCore.
Eval‑driven agent improvements
Reuse failed conversations and AgentCore runtime traces as eval inputs before shipping prompt, tool, or model changes, turning production telemetry into a continuous improvement loop.
Safer experimentation across providers
Test a new model or provider on a small share of AgentCore traffic, then promote or roll back based on traces and evals, instead of editing each agent definition or Bedrock integration by hand.
FAQ
Do I have to change my AWS Bedrock Agentcore code to use Orq.ai?
In many cases, you can repoint the LLM calls that AgentCore makes (for example through Bedrock model invocations or HTTP tools) to Orq.ai’s OpenAI‑compatible endpoint and keep AgentCore’s observability setup as‑is, adding only minimal configuration instead of rewriting your agents. The agent runtime, tools, memory, and gateway resources stay in AgentCore.
Does Orq.ai replace AWS Bedrock Agentcore’s own runtime or framework?
No. AgentCore remains your agent runtime and primary AWS observability source. Orq.ai sits alongside it as the control plane for models, multi‑provider routing, cost tracking, and evaluation. You still design and run agents in Amazon Bedrock AgentCore, but you use Orq to see what they cost, which models they should call, and how LLM behavior compares across providers under the same agent workflow.
Can I keep using my existing LLM providers with AWS Bedrock Agentcore if I move to Orq.ai?
Yes. You can connect your existing Bedrock account to Orq.ai and route AgentCore traffic through those Bedrock models, alongside any additional providers you add later. That way you centralize access, routing, and tracking without losing the AWS models you already rely on. Bring production controls to Bedrock agents
