** 착륙:** 기술, 플러그인 및 서브 시약 Tech: Claude Managed Agents 멀티 시약 + 맞춤 스킬 + 사전 제작된 docx 기술 시간: 60분 입력: 팬이 3-5명의 전문가에게 서브 시약을 일하는 코디네이터 대리인은, 그들의 자신의 기술에 각각, 진짜 상표가 붙은 낱말 문서를 조립합니다.

피치

다음 $ 50M 변환 거래를 이기는 아키텍처입니다. 코디네이터 + 전문가 + 기술. 모든 서비스 회사 구조의 실제 작업에 직접지도. 수석 파트너 오케스트라트; 전문가 (아직, 가격, 기술) 자신의 차선을 소유; 수석 파트너 합성과 전달.

Deal Desk 시나리오 주위에 60 분에서 정확히 구축 할 것입니다. RFP를 떨어뜨리고, 브랜드 응답 doc을 얻고, 이벤트 스트림에서 병렬을 실시간으로 볼 수 있습니다.

설정 (5 분)

콘솔에서 작업 공간 API 키가 필요합니다 (멀티 시약은 현재 연구 미리보기에 있습니다. - 작업 공간은 액세스 권한을 부여해야합니다).

시나리오 카드를 선택

3 카드 scenario-cards.md. 각은 코디네이터 + 전문가의 다른 로스터를 제공합니다. 하나 선택 다른 팀은 다른 카드를 선택해야합니다.

코어 빌드 (25 분)

1. 명세.

Option 3 — Specialist Swarm

Concept landed: Skills, plugins & sub-agents Tech: Claude Managed Agents multi-agent + custom Skills + the pre-built docx skill Time: 60 minutes Output: A coordinator agent that fans work out to 3-5 specialist sub-agents, each with its own skills, that assemble a real branded Word document.

The pitch

This is the architecture that wins the next $50M transformation deal: coordinator + specialists + skills. It maps directly to how every services firm structures real work. A senior partner orchestrates; specialists (legal, pricing, technical) own their lanes; the senior partner synthesises and delivers.

You’re going to build exactly that, in 60 minutes, around a Deal Desk scenario. Drop an RFP in, get a branded response doc out, watch the parallelism happen in real time on the events stream.

Setup (5 min)

You need a workspace API key on the Console (multi-agent is currently in research preview — your workspace may need to be granted access).

cd 03-specialist-swarm
pip install -r requirements.txt
export ANTHROPIC_API_KEY="sk-ant-..."

Pick a scenario card

Three cards in scenario-cards.md. Each gives you a coordinator + a different roster of specialists. Pick one. Different teams should pick different cards.

Core build (25 min)

1. Create the specialists. Run python create_specialists.py. This creates 3-4 sub-agents (Pricing, Legal, Technical Fit, Competitive) and saves their IDs to .specialist_ids.json.

2. Create the coordinator. Run python create_coordinator.py. This creates the coordinator agent with multiagent: coordinator config, listing the specialists in its callable roster.

3. Upload the skills. Run python upload_skills.py. This packages the custom skills in skills/ and uploads them via the Skills API. Each specialist gets the skill that matches its domain.

4. Run the deal. Run python run_deal_desk.py. This:

   • Uploads the synthetic RFP (synthetic-data/rfp-acme-corp.md) as a file
   • Starts a session against the coordinator
   • Asks the coordinator to produce a full proposal response
   • Streams the events so you can watch the parallel thread fan-out
   • Saves the final docx to outputs/proposal-response.docx

By minute 30 you have a Word document in outputs/, generated by a coordinator + specialists who each used their own skill.

Stretch goals (20 min)

See stretch-goals.md. The big ones:

• Custom firm-voice skill — codify your own firm’s voice (every services firm has one)
• Critic sub-agent — add a fifth agent that reviews the coordinator’s draft before it’s finalised