Use Orq.ai as the model control layer for AWS Strands. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your Strands agent logic or deployment path.
What is AWS Strands?
AWS Strands Agents is a production‑angled, model‑first Python SDK for building AI agents on AWS, with built‑in observability via OpenTelemetry, support for tools and MCP, and clean integration into Amazon Bedrock and other providers. It helps teams focus on agent workflows instead of wiring every observability and routing component from scratch. Learn more here.
Why use Orq with AWS Strands?
Trace Strands agent runs end to end, including prompts, planner steps, tool calls, model responses, and errors in one place. You get clearer visibility into agent behavior without stitching together custom traces across Strands, Bedrock, and downstream tools.
Test new models, add providers, or assign different model tiers to different Strands workflows from Orq.ai, while keeping your Strands agent code and AWS integration stable.
Use real Strands conversations and traces to build datasets, compare prompt or model changes, and move from subjective tuning to measurable quality checks. You can turn failed or slow agent runs into eval inputs for future experiments across providers.
Track token usage and spend per agent, team, and workflow so you can see which Strands routes drive cost. Add budgets, rate limits, and approved‑model lists at the Orq platform layer instead of enforcing governance separately inside each Strands agent configuration.
How the integration works
Configure Strands model calls (for example Bedrock or other provider clients used by Strands) to use Orq.ai’s OpenAI‑compatible base URL instead of calling each LLM provider directly. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.
Route Strands’ LLM calls through Orq.ai’s AI Router while keeping Strands’ own OpenTelemetry instrumentation enabled. Strands continues to emit spans for planner steps and tool calls, and Orq logs the LLM interactions and cost metrics for those requests.
Create routes for key Strands workflows and assign them model tiers, fallback chains, and region/data policies. Strands sends the model request to the configured Orq route, and Orq applies the routing rules you define before calling Bedrock or other providers.
Once connected, use Orq’s dashboards to watch latency, errors, and cost for Strands agents, and run evals or experiments on their traces. You can then adjust routes, models, or prompt configurations centrally where supported, without changing Strands’ agent loop or Bedrock wiring.
Use cases
Multi‑agent products with real observability
Trace which Strands agent, planner branch, tool call, and model contributed to a failed workflow or unexpected outcome.
Cost‑aware internal tools
Route routine steps to lower‑cost models while keeping complex reasoning or Bedrock‑backed flows on stronger routes configured in Orq.
Eval‑driven agent improvements
Reuse failed conversations and Strands trace trees as eval inputs before shipping prompt, tool, or model changes.
Safer experimentation across providers
Test a new model or provider on a small share of Strands 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 Strands agents to use Orq.ai?
In many cases, you can repoint Strands’ LLM calls to Orq.ai’s OpenAI‑compatible endpoint and keep Strands’ OpenTelemetry setup as‑is, adding only minimal configuration instead of rewriting your agents. The agent loop, tools, MCP connectors, and Bedrock integration stay in Strands.
Does Orq.ai replace Strands’ own runtime or observability?
No. Strands remains your agent SDK and observability source on AWS. Orq.ai sits alongside it as the control plane for models, routing, cost tracking, and evaluation across multiple providers.
You still design and run agents in Strands, 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 Strands if I move to Orq.ai?
Yes. You can bring your existing provider keys (for example Bedrock models and other LLM APIs) into Orq.ai and route Strands traffic through them, alongside any new models you add later. That way you centralize access, routing, and tracking without losing the AWS and non‑AWS providers you already rely on.
