1. Define the workflow job
Start with the outcome, not the models: support triage, document Q&A, escalation, classification, tool execution, or multi-step analysis.
Multi-model workflows
This guide shows how to deploy an agent-style workflow where different supported steps can use different models, providers, tools, policies, budgets, and approval gates.
Start with the outcome, not the models: support triage, document Q&A, escalation, classification, tool execution, or multi-step analysis.
Add the providers you need, such as Anthropic for reasoning, OpenAI or Azure OpenAI for general chat, Voyage AI for embeddings, Bedrock for AWS-governed access, or Groq/Together where supported.
Create separate provider-backed deployments for each role, for example planner, classifier, summarizer, and final answer model. Each deployment can have its own provider, contract, policies, and budget gates.
Use the workflow editor to compose supported nodes such as input, retrieval, mcp_input, tool_call, function, model, agent, router, condition, approval, and output. Each model or agent node can bind to a different provider-backed deployment.
Use router or condition nodes for tiering and escalation. Use fallback_node_id for supported fallback behavior when a node fails.
Use function/tool_call nodes for HTTP/webhook/internal tools, and mcp_input nodes for external MCP servers. Agent nodes can expose those functions as native provider tools.
Add schema contracts, redact_text, policy_check nodes, budget policies, approval nodes, and enforcement packs before expensive or sensitive model calls.
In the workflow editor, select each model or agent node and choose the deployment that matches its role. You can also use a run default deployment for simple graphs.
Execute the workflow, then inspect node executions, tool calls, model payloads, latency, cost, policy decisions, and errors in observability.
Create golden datasets for the workflow’s important tasks. Use eval runs and comparisons to catch regressions after prompt, provider, routing, or policy changes.
Start simple, then add routing and fallbacks once the main path is reliable:
input → redact_text / policy_check → planner model → retrieval or mcp_input → agent or function → router / condition → specialist model → approval (optional) → final answer model → output
Bind each model or agent node to the deployment that fits the role. For example, use a cheaper classifier model for routing and a stronger reasoning model for native tool-calling.
Yes. Quantlix workflows support per-model-step deployment bindings, so one graph can use different providers and models for different roles.
Yes. Agent nodes run a bounded native tool-calling loop against a provider-backed chat deployment. Tools are configured as HTTP, webhook, or internal functions and every step is recorded in the workflow trace.
Use budget policies, retry limits, route-specific deployments, and approval gates before expensive or tool-heavy branches.
Each workflow execution records node-level inputs, outputs, errors, timings, traces, provider/model metadata, and policy decisions.