Practical patterns for LLM scoring in n8n workflows

说明与用途

在 n8n 中集成 LLM 评分：结构化 JSON 输出，规则优先，LLM 次序，错误处理与原因日志记录。

问题

Integrating LLM scoring into n8n workflows while keeping deterministic, auditable rule-based logic and handling model failures.

结果

Lead qualification becomes auditable, cost-effective, and resilient to LLM failures, with structured JSON output and logged reasons enabling review.

工作流

• 1. Run deterministic rule chain first.
• 2. Pass data to LLM node with JSON schema request.
• 3. Receive structured score, verdict, and reasons.
• 4. Use IF node to route based on verdict.
• 5. On error, set default score and reason via Set node.
• 6. Log score and reasons to storage for audit.
• 7. Continue downstream actions (CRM update, alerts).

证据

Never let the model write you a paragraph you then parse with string matching.

来源

Put the scoring step behind your existing rule chain, and put an IF node after it.

来源

Every one of those cases must land somewhere sensible: error branch to a Set node that writes a default score and a reasons: ["model_unavailable"] flag.

来源

Scoring a lead against a rubric is not frontier-model work. A small, fast, cheap model with a prompt that contains your actual rubric — with examples — beats a big model with a vague prompt.

来源

Write score and reasons to your log store every single run.

来源