Orchestrator Pattern - Ascend Gateway V5

What is the orchestrator?

The orchestrator is an agent config with no direct tools. Its job is to classify an incoming request and route it to the right specialist agent. This lets you expose a single endpoint to users while keeping specialists tightly scoped.

User message
    ↓
Orchestrator (classifier_model classifies intent)
    ↓ routes to
┌─────────────────────────────────────────────┐
│ gtm_analyst  │ outreach_writer │ crm_enricher │
└─────────────────────────────────────────────┘
    ↓ specialist runs, returns result
Orchestrator (synthesis_model merges if multi-domain)
    ↓
Final response to user

Setting up an orchestrator

Create an agent config with tools: [] and a classifier_model:

curl -X PUT https://ascend-gateway-v5.ascendgtm.workers.dev/admin/agent-configs/kahuna/orchestrator \
  -H "Authorization: Bearer <admin-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "max_tokens": 1024,
    "max_iterations": 3,
    "system_prompt": "You classify GTM questions and route to specialists. Respond only with {\"route\": \"<agent_type>\", \"refined_message\": \"<message>\"}. Agent types: gtm_analyst, outreach_writer, crm_enricher, report_builder.",
    "tools": [],
    "classifier_model": "claude-haiku-4-5",
    "synthesis_model": "claude-sonnet-4-5"
  }'

The classifier_model is used for the intent classification step (cheaper, faster). The synthesis_model merges results from multiple specialists when a request spans domains.

Routing logic

When a request hits the orchestrator:

Classify — classifier_model reads the message and returns {route, refined_message}
Delegate — Hermes starts the target specialist agent with refined_message as the input
Synthesise (multi-domain only) — if the message required more than one specialist, synthesis_model merges the responses
Return — the unified response goes back to the caller

Multi-domain example

User: “Pull last month’s Google Ads performance and draft a Slack update summarizing it for the team.”

Orchestrator classifies: ["gtm_analyst", "outreach_writer"] (two domains)
gtm_analyst runs → performance summary
outreach_writer runs → Slack message draft using the analyst output
synthesis_model merges into one response

When NOT to use the orchestrator

Known single-domain requests — route directly to the specialist; skip classification overhead
Scheduled jobs — use explicit agent_type in the job config, no orchestrator needed
High-frequency calls — orchestrator adds 1–2 LLM calls per request; direct routing is cheaper

Admin API reference

Endpoint	Description
`GET /admin/agent-configs/:tenant`	List all configured agent types
`GET /admin/agent-configs/:tenant/:type`	Get one agent config
`PUT /admin/agent-configs/:tenant/:type`	Create or update config
`DELETE /admin/agent-configs/:tenant/:type`	Remove config

Tool validation is enforced on PUT — unknown tool names in the tools array are rejected with VALIDATION_ERROR.

​What is the orchestrator?

​Setting up an orchestrator

​Routing logic

​Multi-domain example

​When NOT to use the orchestrator

​Admin API reference