## Compatibility
The whole hunk
from line 4, old and new numbered
/
lines
from line 4
44description: Tell the agent what 'done' looks like, and let it iterate until it gets there.
55---
66
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10
711An outcome tells the session what the end result should look like and how to measure its quality. The agent works toward that target, self-evaluating and iterating until the outcome is met.
812
913When you define an outcome, the harness automatically provisions a *grader* to evaluate the artifact against a rubric. The grader uses a separate context window to avoid being influenced by the main agent's implementation choices.
from line 14
1014
1115The grader returns an explanation summarizing which criteria passed or failed, or confirming that the artifact satisfies the rubric. That feedback is handed back to the agent for the next iteration.
1216
13<Note>
14 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
15</Note>
16
1717## Create a rubric
1818
1919A rubric is a markdown document describing per-criterion scoring. The rubric is required.
from line 816
816816
817817 // Download a file
818818 if len(files.Data) > 0 {
819 resp, err := client.Files.Download(ctx, files.Data[0].ID)
819 resp, err := client.Files.Download(ctx, files.Data[0].ID, anthropic.FileDownloadParams{})
820820 if err != nil {
821821 panic(err)
822822 }