Amazon OpenSearch Service's optimized engine stores agent traces next to logs, keeping prompts and tool calls nested, at no additional charge on OpenSearch 3.7
Agent sessions can now be followed end to end in the same store as their logs, with OpenTelemetry traces queryable field by field.
// Key points
- The optimized engine adds support for agent traces, including OpenTelemetry traces, so traces and logs live in the same place
- Span events, span links, prompts and tool calls keep their nested structure, allowing field-level queries without flattening at ingestion
- On hot-tier data it supports update, delete and upsert by document ID to correct late or erroneous data in place
- OpenSearch UI adds agent traces and sessions views; available on OpenSearch 3.7 at no additional charge in 12 Regions
Builder's takeMistral Studio, AgentCore and now OpenSearch all speak OpenTelemetry for agents, so I'd instrument with OTel now and treat the backend as swappable. If you already keep app logs in OpenSearch, this is the cheapest way to get prompt and tool-call search without adding another vendor.
// Background · from #AI agents
Full timeline →- Nov 7 AWS runs Claude Code as a remote agent on Bedrock AgentCore: one microVM per task, up to three attempts, and a draft pull request unless verification passes
- Nov 7 Anthropic on agent memory: "dreaming" over 128 sessions lifts a wiki-only score from 13% to 48%, and wiki plus search saves about 20,000 tokens per question
- Nov 7 Mistral Studio adds managed agents and apps, with skills, sandboxes, subagents, hooks and OpenTelemetry traces, deployable in your own VPC or on-premises