> ## Documentation Index > Fetch the complete documentation index at: https://docs.decimal.ai/llms.txt > Use this file to discover all available pages before exploring further. # Batch compute unified verdicts > Batch compute unified verdicts for multiple traces. Provide either trace_ids or manifest_id (to score all traces from that manifest). ## OpenAPI ````yaml /openapi.json post /api/v1/traces/batch-decision openapi: 3.1.0 info: title: DecimalAI Platform description: Agent Dataset Lifecycle Platform — Backend API version: 0.1.0 servers: [] security: - BearerAuth: [] tags: - name: traces description: >- Ingest, search, and inspect agent execution traces. A trace is the atomic unit of the platform — every other feature (evaluation, compatibility scoring, dataset building) operates on traces. Each trace is auto-tagged with the manifest hash of the agent that produced it. - name: eval-scores description: >- Push, fetch, and aggregate per-trace evaluation scores. Scores carry source provenance (built-in, DeepEval, LangSmith, custom) and feed the unified decision engine, which produces a keep / repair / replay / drop verdict per trace. - name: skills description: >- Manage reusable instruction blocks (SKILL.md files) that modify agent behavior. Skills are first-class manifest components — changes to a skill appear in your regression-check impact reports. Use these endpoints to create, version, fork, and sync skills with your local SKILL.md files. - name: manifests description: >- Register and inspect manifest versions. A manifest is a snapshot of your agent's structural identity (tools, prompts, models, skills) at a point in time. The SDK registers manifests automatically; these endpoints expose the underlying records. - name: datasets description: >- Build versioned SFT/DPO training datasets from manifest-classified, eval-scored traces. Datasets are reproducible — each version locks the manifest and filter set used to build it. Export as JSONL, Parquet, or push to HuggingFace Hub. - name: replay description: >- Re-execute historical traces against a new manifest version. Replay is the deferred-future capability for behavioral verification of agent changes. The SDK creates a replay batch, your worker executes each task, then submits results back here for eval scoring. - name: registry description: >- Browse and install community skills from the public skills registry. Each registry skill carries a SkillScore — an evidence-tiered quality composite computed from real-world evals, benchmarks, and ratings across organizations. Installing creates a fork in your org — edits don't affect the public version. - name: agents description: >- List and inspect agents, plus their multi-agent topology (orchestrator → sub-agent edges discovered from traces). Agents are identified by a stable agent_name string set in your SDK init() call. - name: import description: >- Bulk-import historical traces from another observability platform or a JSONL backup. Useful for migrating from LangSmith / Braintrust / Langfuse. Duplicate trace IDs are silently skipped — re-running an import is safe. paths: /api/v1/traces/batch-decision: post: tags: - eval-scores summary: Batch compute unified verdicts description: >- Batch compute unified verdicts for multiple traces. Provide either trace_ids or manifest_id (to score all traces from that manifest). operationId: batch_decision_api_v1_traces_batch_decision_post parameters: - name: Authorization in: header required: false schema: type: string title: Authorization - name: decimal_session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Decimal Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/BatchDecisionRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchDecisionResponse' example: decisions: - trace_id: trc_001 verdict: keep quality_avg: 0.92 compat_avg: 0.95 quality_scores: [] compat_scores: [] reasons: [] total: 1 verdict_counts: keep: 1 repair: 0 replay: 0 drop: 0 '400': description: Either `trace_ids` or `manifest_id` is required. '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: Python label: Python SDK source: |- import httpx # Score every trace from a manifest in one call. resp = httpx.post( "https://api.decimal.ai/api/v1/traces/batch-decision", headers={"Authorization": "Bearer dai_sk_..."}, json={"manifest_id": "mfst_abc123"}, ) resp.raise_for_status() print(resp.json()["verdict_counts"]) components: schemas: BatchDecisionRequest: properties: trace_ids: anyOf: - items: type: string type: array - type: 'null' title: Trace Ids description: Specific trace IDs to score manifest_id: anyOf: - type: string - type: 'null' title: Manifest Id description: Score all traces from this manifest type: object title: BatchDecisionRequest description: Request for batch verdict computation. BatchDecisionResponse: properties: decisions: items: $ref: '#/components/schemas/DecisionResponse' type: array title: Decisions total: type: integer title: Total verdict_counts: additionalProperties: type: integer type: object title: Verdict Counts type: object required: - decisions - total - verdict_counts title: BatchDecisionResponse description: Response from batch verdict computation. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError DecisionResponse: properties: trace_id: type: string title: Trace Id verdict: type: string title: Verdict quality_avg: type: number title: Quality Avg compat_avg: type: number title: Compat Avg quality_scores: items: additionalProperties: true type: object type: array title: Quality Scores compat_scores: items: additionalProperties: true type: object type: array title: Compat Scores reasons: items: type: string type: array title: Reasons type: object required: - trace_id - verdict - quality_avg - compat_avg - quality_scores - compat_scores - reasons title: DecisionResponse description: Response from the decision engine. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: BearerAuth: type: http scheme: bearer description: Enter your API key (e.g. dai_sk_test_key_001) ````