tutorialintermediate

Multiagent: coordinate a specialist team May 2026 • Agent Patterns Tools Heterogeneous team via the multiagent coordinator config — a coordinator runs three specialists (web-search researcher, file-reading librarian, rules-based pricer) with scoped toolsets to assemble a sales proposal. Covers the multiagent field, the thread_created / thread_message_received event types, and per-role tool scoping.

May 7, 2026cookbook

This cookbook demonstrates building a multiagent coordinator system using Claude Managed Agents to automate sales-proposal generation. A coordinator agent orchestrates three specialist subagents—a web-search researcher, a case-study librarian, and a rules-based pricing modeler—each with scoped toolsets and specific responsibilities. The pattern shows how to structure heterogeneous teams, use per-role tool scoping, and leverage thread_created/thread_message_received events for agent coordination to assemble tailored sales proposals.

Key Points

•Use the multiagent coordinator pattern to delegate specialized tasks to subagents, each with its own system prompt, output schema, and scoped toolset
•Implement per-role tool scoping to restrict access—researcher gets web search, librarian accesses only case-study files, pricer sees only pricing rules—preventing context pollution and maintaining data governance
•Create specialist agents with clear descriptions and focused system prompts that define their input expectations and output format (e.g., send_to_parent JSON structures)
•Leverage agent_toolset_20260401 configuration to define which tools each subagent can access, enabling fine-grained control over capabilities
•Structure the coordinator to sequence specialist outputs: research → case-study selection → pricing modeling → proposal assembly
•Provide agents with local file access (/mnt/user-data/) for reference materials like case-study libraries and pricing rules rather than embedding in context
•Use the Managed Agents beta API with appropriate beta headers (managed-agents-2026-04-01) and thread event types for inter-agent communication
•Design output contracts (JSON schemas via send_to_parent) so the coordinator can reliably parse and combine specialist results
•Scope data access by role to prevent unintended information leakage (e.g., keep competitor pricing away from the pricer, full library away from coordinator)
•Test with realistic collateral (product one-pagers, pricing rules, case-study library) to validate agent decision-making and proposal quality

Found this useful? Add it to a playbook for a step-by-step implementation guide.

Workflow Diagram

Start Process

Step A

Step B

Step C

Complete

Quality★★★★★

Concepts

MCP Servers Coordination Skills & Tools Multi-Agent Systems Agent Teams Tool Use

Artifacts (3)

multiagent_coordinator_setup.pypythonscript

import os
import anthropic
from dotenv import load_dotenv

load_dotenv()

BETAS = ["managed-agents-2026-04-01"]
MODEL = os.environ.get("COOKBOOK_MODEL", "claude-opus-4-6")

client = anthropic.Anthropic()

def make_agent(name, description, system, tools):
    a = client.beta.agents.create(
        name=name,
        description=description,
        model=MODEL,
        system=system,
        tools=tools,
        betas=BETAS,
    )
    print(f"{name}: {a.id}")
    return a.id

# Define specialist agents
prospect_researcher = make_agent(
    "prospect_researcher",
    "Researches what companies in a given industry segment and size tier typically prioritize.",
    """Given a prospect's industry and size, use web search to find:
    - What companies in that segment typically list as strategic priorities
    - Recent trends or pressures in that industry
    - Common operational pain points at that scale
    Return via send_to_parent: {"priorities": [...], "recent_moves": [...], "pain_points": [...], "sources": [...]}""",
    [
        {
            "type": "agent_toolset_20260401",
            "configs": [{"name": "web_search"}, {"name": "web_fetch"}],
        }
    ],
)

case_study_picker = make_agent(
    "case_study_picker",
    "Selects the two most relevant case studies from the library for a given prospect profile.",
    """The case study library is in /mnt/user-data/case_studies/. Each file is one customer story.
    You will be given a prospect's industry, size, and top priorities. Read the library, score each study on relevance, and pick the two best matches.
    Return via send_to_parent: {"picks": [{"file": ..., "customer": ..., "why_relevant": ...}, ...]}""",
    [{"type": "agent_toolset_20260401"}],
)

pricing_modeler = make_agent(
    "pricing_modeler",
    "Builds two or three pricing options for a prospect based on seat count and expected usage.",
    """Pricing rules are in /mnt/user-data/pricing_rules.md. Given a prospect's estimated seat count and usage tier, build:
    - a conservative option (annual commit, lower per-seat)
    - a flexible option (monthly, higher per-seat)
    - if seat count > 500, an enterprise option with a platform fee
    Show the first-year total for each.
    Return via send_to_parent: {"options": [{"name": ..., "structure": ..., "year_one_total": ...}, ...]}""",
    [{"type": "agent_toolset_20260401"}],
)

case_studies_data.pypythontemplate

CASE_STUDIES = [
    {
        "slug": "stclair_health",
        "title": "St. Clair Health",
        "industry": "regional hospital network",
        "employees": 6200,
        "summary": "Challenge: credentialing and prior-auth workflows spread across 11 systems. Result with Northstar: consolidated to 3 automated workflows; prior-auth turnaround down 58%; $1.9M annual labor savings.",
    },
    {
        "slug": "blueridge_health_plan",
        "title": "BlueRidge Health Plan",
        "industry": "regional payer",
        "employees": 2800,
        "summary": "Challenge: claims-adjudication exceptions queued in email; 19% required manual rework. Result with Northstar: exception routing automated end-to-end; rework rate down to 6%; 11-day faster average claim resolution.",
    },
    {
        "slug": "calder_mfg",
        "title": "Calder Manufacturing",
        "industry": "industrial",
        "employees": 3100,
        "summary": "Challenge: purchase-order approvals averaging 9 days. Result with Northstar: PO cycle time cut to 2.1 days; 14% reduction in maverick spend.",
    },
    {
        "slug": "northwind",
        "title": "Northwind Logistics",
        "industry": "3PL",
        "employees": 4400,
        "summary": "Challenge: carrier-onboarding paperwork took 3 weeks per carrier. Result with Northstar: onboarding down to 4 days; 22% more carriers activated in Q1.",
    },
    {
        "slug": "harborview_retail",
        "title": "Harborview Retail Group",
        "industry": "specialty retail",
        "employees": 5600,
        "summary": "Challenge: store-level inventory exceptions handled by regional managers over Slack and spreadsheets. Result with Northstar: exception triage automated across 140 stores; stockout incidents down 31%.",
    },
    {
        "slug": "aperture_fintech",
        "title": "Aperture Payments",
        "industry": "fintech",
        "employees": 1900,
        "summary": "Challenge: KYC and merchant-onboarding reviews averaging 6 business days. Result with Northstar: review SLA cut to 36 hours; onboarding throughput up 2.4x with the same team.",
    },
    {
        "slug": "summit_county",
        "title": "Summit County Government",
        "industry": "public sector",
        "employees": 3700,
        "summary": "Challenge: building-permit applications routed through five departments by paper packet. Result with Northstar: single digital intake with parallel department review; median permit time 41 to 17 days.",
    },
]

PRODUCT = """# Northstar Platform — One-Pager
Northstar is a workflow automation platform for mid-market operations teams.
Core capabilities: visual process builder, 200+ SaaS connectors, role-based approvals, SOC 2 Type II.
Typical results: 40-60% reduction in manual ticket handling, 3-week time-to-first-workflow."""

PRICING = """# Pricing Rules (internal)
- Per-seat list: $65/mo (monthly) or $52/mo (annual commit).
- Usage tiers: light = 1.0x, standard = 1.15x, heavy = 1.30x multiplier on per-seat.
- Enterprise (>500 seats): add $48,000/yr platform fee."""

pricing_rules.mdmarkdownconfig

# Pricing Rules (internal)

## Per-Seat Pricing
- **Monthly**: $65/month per seat
- **Annual Commit**: $52/month per seat (billed annually)

## Usage Tiers
Apply multiplier to per-seat base:
- **Light**: 1.0x
- **Standard**: 1.15x
- **Heavy**: 1.30x

## Enterprise Tier (>500 seats)
- Add $48,000/year platform fee
- Negotiate per-seat discount (typically 15-25%)
- Include dedicated support and custom integrations

## Discount Guidelines
- Annual commit: 20% off monthly rate
- Multi-year: additional 10% off
- Non-profit/public sector: 25% discount
- Startup (< $10M ARR): 30% discount