Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ntropii.com/llms.txt

Use this file to discover all available pages before exploring further.

Claude Managed Agents are Anthropic-hosted agents with bundled bash / write / read tooling, Skills (e.g. the docx skill for Word document generation), MCP server bindings authenticated via Anthropic Vaults, and Environments for custom pip packages. Ntropii integrates with them via ntro.workflow.agents.invoke from inside a runbook step. This page is the end-to-end walkthrough for the production adapter. The working reference implementation lives in claude-managed-agents on GitHub.

​
When to use

Reach for a Managed Agent when a runbook step needs LLM-driven artefact generation that doesn’t fit the deterministic capabilities surface:
  • Multi-section narrative documents (auditor handover .docx, NAV pack PDF, year-end letter)
  • Open-ended document drafting where the structure varies by period
  • Tasks where the agent benefits from bash + python-docx + the docx Skill working together in a sandbox
For structured extraction, classification, and quality checks, prefer ntro.ai.extract and ntro.ai.check. They’re cheaper, faster, and observable through the same Reasoning tab.

​
Lifecycle

┌────────────────────────────┐
│ 1. Build on Anthropic       │  Anthropic Console — Agents, Environments, Vaults
│    Console                  │
└────────────────────────────┘
              ↓
┌────────────────────────────┐
│ 2. Register with Ntropii    │  ntro agent create --path anthropic://agents/<id>
└────────────────────────────┘
              ↓
┌────────────────────────────┐
│ 3. Store API key in Vault   │  Plaintext shown once at registration
└────────────────────────────┘
              ↓
┌────────────────────────────┐
│ 4. Reference from runbook   │  ntro.workflow.agents.invoke(agent_id, …)
└────────────────────────────┘

​
1. Build on Anthropic Console

Author the agent in Anthropic Console. The shape of an agent.yaml that registers cleanly with Ntropii: 
name: audit-handover
model: claude-sonnet-4-6
description: |
  Produces an auditor handover .docx for a completed NAV close.

system: |
  # System message — what the agent is + how it should behave.
  # See claude-managed-agents/agents/audit-handover/system-prompt.md
  # for the production reference.

tools:
  - type: bash
  - type: write
  - type: read
  # mcp_toolset binds the Ntropii MCP server. Vault-injected auth at
  # session start; no env-var-based auth.
  - type: mcp_toolset
    mcp_server_name: ntropii

mcp_servers:
  - type: url
    name: ntropii
    url: https://mcp.ntropii.com/mcp  # Streamable HTTP MCP path

skills:
  # Anthropic's pre-built docx skill — pairs well with python-docx
  # for richer document authoring.
  - skill_id: docx
    type: anthropic
    version: latest
Three platform objects to set up:
ObjectCarriesNotes
Agentname, model, system, tools, mcp_servers, skillsPer-agent definition
Environmentpip packages (python-docx, ntro, …), networking, metadataReusable across agents
VaultAPI keys (Ntropii agent API key)Injected into MCP server auth at session start
No env vars on Managed Agents. Auth flows through Vault → MCP server only.

​
2. Register with Ntropii

Once the agent exists in Anthropic Console and you have its native id (e.g. agent_01SxpziMunFrUbnAYkGB5Hu3): 
ntro agent create \
  --path anthropic://agents/agent_01SxpziMunFrUbnAYkGB5Hu3 \
  --tenant byng \
  --name audit-handover
The CLI returns the Ntropii agent UUID, the resolved external_ref, and an API key plaintext shown once.

​
3. Store the API key in an Anthropic Vault

Create a Vault on Anthropic, paste the plaintext API key, and reference the Vault from the agent. The Ntropii MCP server uses this key to authenticate the agent’s callbacks (e.g. ntro_task_get).

​
4. Reference from a runbook step

From any @ui_step method: 
from ntro.workflow.agents import invoke

@ui_step(name="draft_auditor_handover", title="Draft auditor handover", icon="FileText")
async def _step_draft_auditor_handover(self, ctx, ...):
    if not ctx.audit_agent_id:
        return None  # Skip when the entity hasn't opted into an agent

    period_summary = {
        "entity": {"slug": ctx.entity_slug, "currency": "GBP"},
        "period": ctx.period,
        "tb": tb_dict,
        "journal_proposal": proposal_dict,
        "documents": [...],
    }

    result = await invoke(
        ctx.audit_agent_id,
        input={"period_summary": period_summary},
        tenant_slug=ctx.tenant_slug,
        entity_slug=ctx.entity_slug,
        task_id=ctx.task_id,
    )
    return result
The agent receives input as its kickoff user message (JSON-serialised for dicts), runs to terminal status, and emits any output files. The Ntropii adapter handles the rest.

​
File output

The agent writes generated files to /mnt/session/outputs/<filename> — Anthropic’s runtime auto-promotes that path into the session’s file list. The Ntropii adapter:
  1. Polls the Anthropic Sessions API until the session is terminated.
  2. Lists session files via GET /v1/files?scope_id=<session_id> (with backoff for the index-eventual-consistency race).
  3. Downloads each file’s bytes.
  4. Persists to ingest.submitted_documents with source = 'agent_output:<ntropii-agent-id>'.
The persisted file is then accessible from the task UI like any other document — including via the audit-handover step’s download link.

​
Reference implementation

The claude-managed-agents repo on GitHub contains the production-ready definitions and integration spec: 
claude-managed-agents/
├── README.md
├── docs/
│   ├── integration-spec.md
│   └── sdk-reference.md
└── agents/
    └── audit-handover/
        ├── agent.yaml
        ├── system-prompt.md
        ├── tools.md
        ├── handover-template.md
        └── README.md
Use audit-handover as the template for your own Managed Agents.

Register agents

Generic registration flow, lifecycle, and reference table.

ntro.workflow.agents reference

invoke() signature, AgentResult shape, adapter polling + backoff semantics.

Build runbooks

The runbook-side of invoking an agent inside a @ui_step.

Anthropic Managed Agents docs

Anthropic’s reference for Agents, Environments, Vaults, and Sessions.