> ## 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. # Set this agent's system prompt > Set or edit the agent's system prompt. A new version only if it changed. Always 200 on success — callers read `action`, not the status code. `action: "unchanged"` is the most important field in this API. The whole reason Phase 3c exists is that the same edit through the manifest hashed identically, deduped, and returned 200 having discarded the write. A no-op that reports itself is fine; a change that reports success and does nothing is the failure mode. `pinned_warning` does the same job for the pin case: editing while pinned writes the version, KEEPS the pin, and says so — rather than silently un-pinning (breaking version stability) or silently no-op'ing. ## OpenAPI ````yaml /openapi.json put /api/v1/agents/{agent_name}/prompt openapi: 3.1.0 info: title: DecimalAI Platform description: Agent Dataset Lifecycle Platform — Backend API version: 0.1.0 servers: - url: https://api.decimal.ai description: Production 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 published 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/agents/{agent_name}/prompt: put: tags: - agents summary: Set this agent's system prompt description: >- Set or edit the agent's system prompt. A new version only if it changed. Always 200 on success — callers read `action`, not the status code. `action: "unchanged"` is the most important field in this API. The whole reason Phase 3c exists is that the same edit through the manifest hashed identically, deduped, and returned 200 having discarded the write. A no-op that reports itself is fine; a change that reports success and does nothing is the failure mode. `pinned_warning` does the same job for the pin case: editing while pinned writes the version, KEEPS the pin, and says so — rather than silently un-pinning (breaking version stability) or silently no-op'ing. operationId: set_agent_prompt_api_v1_agents__agent_name__prompt_put parameters: - name: agent_name in: path required: true schema: type: string title: Agent Name - name: Authorization in: header required: false schema: type: string title: Authorization - name: X-Workspace-Id in: header required: false schema: anyOf: - type: string - type: 'null' title: X-Workspace-Id - 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/SetAgentPromptRequest' responses: '200': description: Successful Response content: application/json: schema: type: object additionalProperties: true title: >- Response Set Agent Prompt Api V1 Agents Agent Name Prompt Put '400': description: Empty, whitespace-only, or oversized prompt. '404': description: No such agent in this org. '409': description: if_match_content_hash did not match (prompt_stale). '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: SetAgentPromptRequest: properties: system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: >- The agent's system prompt. A byte-identical write is accepted and reported as `action: "unchanged"` rather than creating a version. label: anyOf: - type: string maxLength: 200 - type: 'null' title: Label description: Optional note on this version, e.g. 'tightened refund wording'. if_match_content_hash: anyOf: - type: string - type: 'null' title: If Match Content Hash description: >- Optimistic concurrency. Supply the `content_hash` you last read and the write is refused with 409 if someone else has since changed the prompt. Omit for last-write-wins. type: object title: SetAgentPromptRequest description: >- Body of ``PUT /api/v1/agents/{agent_name}/prompt``. ``system_prompt`` is Optional[str] here despite being REQUIRED, for the same reason ``CreateAgentRequest.agent_name`` is (:517-524): declaring it ``str`` would make an ABSENT field a 422 while an EMPTY one is a 400, so a caller would have to handle two error shapes for one mistake. Optional plus an explicit check routes absent, empty and whitespace-only through one 400. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError 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) ````