AI Agent Patterns with Trigger.dev

Build production-ready AI agents using Trigger.dev's durable execution.

Pattern Selection

Need to...                              → Use
─────────────────────────────────────────────────────
Process items in parallel               → Parallelization
Route to different models/handlers      → Routing
Chain steps with validation gates       → Prompt Chaining
Coordinate multiple specialized tasks   → Orchestrator-Workers
Self-improve until quality threshold    → Evaluator-Optimizer
Pause for human approval                → Human-in-the-Loop (waitpoints.md)
Stream progress to frontend             → Realtime Streams (streaming.md)
Let LLM call your tasks as tools        → ai.tool (ai-tool.md)

Core Patterns

1. Prompt Chaining (Sequential with Gates)

Chain LLM calls with validation between steps. Fail early if intermediate output is bad.

import { task } from "@trigger.dev/sdk";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

export const translateCopy = task({
  id: "translate-copy",
  run: async ({ text, targetLanguage, maxWords }) => {
    // Step 1: Generate
    const draft = await generateText({
      model: openai("gpt-4o"),
      prompt: `Write marketing copy about: ${text}`,
    });

    // Gate: Validate before continuing
    const wordCount = draft.text.split(/\s+/).length;
    if (wordCount > maxWords) {
      throw new Error(`Draft too long: ${wordCount} > ${maxWords}`);
    }

    // Step 2: Translate (only if gate passed)
    const translated = await generateText({
      model: openai("gpt-4o"),
      prompt: `Translate to ${targetLanguage}: ${draft.text}`,
    });

    return { draft: draft.text, translated: translated.text };
  },
});

2. Routing (Classify → Dispatch)

Use a cheap model to classify, then route to appropriate handler.

import { task } from "@trigger.dev/sdk";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { z } from "zod";

const routingSchema = z.object({
  model: z.enum(["gpt-4o", "o1-mini"]),
  reason: z.string(),
});

export const routeQuestion = task({
  id: "route-question",
  run: async ({ question }) => {
    // Cheap classification call
    const routing = await generateText({
      model: openai("gpt-4o-mini"),
      messages: [
        {
          role: "system",
          content: `Classify question complexity. Return JSON: {"model": "gpt-4o" | "o1-mini", "reason": "..."}
          - gpt-4o: simple factual questions
          - o1-mini: complex reasoning, math, code`,
        },
        { role: "user", content: question },
      ],
    });

    const { model } = routingSchema.parse(JSON.parse(routing.text));

    // Route to selected model
    const answer = await generateText({
      model: openai(model),
      prompt: question,
    });

    return { answer: answer.text, routedTo: model };
  },
});

3. Parallelization

Run independent LLM calls simultaneously with batch.triggerByTaskAndWait.

import { batch, task } from "@trigger.dev/sdk";

export const analyzeContent = task({
  id: "analyze-content",
  run: async ({ text }) => {
    // All three run in parallel
    const { runs: [sentiment, summary, moderation] } = await batch.triggerByTaskAndWait([
      { task: analyzeSentiment, payload: { text } },
      { task: summarizeText, payload: { text } },
      { task: moderateContent, payload: { text } },
    ]);

    // Check moderation first
    if (moderation.ok && moderation.output.flagged) {
      return { error: "Content flagged", reason: moderation.output.reason };
    }

    return {
      sentiment: sentiment.ok ? sentiment.output : null,
      summary: summary.ok ? summary.output : null,
    };
  },
});

See: references/orchestration.md for advanced patterns

4. Orchestrator-Workers (Fan-out/Fan-in)

Orchestrator extracts work items, fans out to workers, aggregates results.

import { batch, task } from "@trigger.dev/sdk";

export