Skip to content

Commit 51df236

Browse files
committed
Update
1 parent b638243 commit 51df236

File tree

1 file changed

+16
-7
lines changed

1 file changed

+16
-7
lines changed

building-effective-agents/README.md

Lines changed: 16 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ All of these examples focus on performing specific tasks, rather than do-it-all
1212

1313
## About the project
1414

15-
- This is a basic Node.js project, so it doesn't include any UI.
15+
- This is a basic Node.js project, so doesn't include any UI.
1616
- Each of the different AI agent patterns is implemented as a [Trigger.dev](https://cloud.trigger.dev) task.
1717
- The [AI SDK](https://sdk.vercel.ai/docs/introduction) is used to work with OpenAI models.
1818

@@ -22,7 +22,7 @@ All of these examples focus on performing specific tasks, rather than do-it-all
2222

2323
Breaking down a task into a series of steps, guided through a pre-determined sequence.
2424

25-
#### Example: Prompt chaining
25+
#### Prompt chaining task
2626

2727
1. Generate marketing copy on a subject you provide. (LLM call 1)
2828
2. Check the word count fits a target range. (Gate)
@@ -34,7 +34,7 @@ View the Trigger.dev prompt chaining task code: [src/trigger/trigger/translate-c
3434

3535
You can think of routing as an AI traffic controller. Instead of forcing one LLM to handle everything, you first figure out what type of task you're dealing with, then send it to the right specialist.
3636

37-
#### Example: Routing
37+
#### Routing task
3838

3939
1. User asks a question.
4040
2. Determine if the question is simple or complex.
@@ -47,7 +47,7 @@ View the Trigger.dev routing task code: [src/trigger/trigger/routing-questions.t
4747

4848
Sometimes you need to do multiple things at once – that's where parallelization comes in. Rather than working through tasks one by one, you split them up and run them simultaneously. This is where batch.triggerByTaskAndWait shines, allowing you to execute multiple tasks in parallel and efficiently coordinate their responses.
4949

50-
#### Example: Parallelization
50+
#### Parallelization task
5151

5252
This example responds to customer questions by simultaneously generating a response and checking for inappropriate content.
5353

@@ -57,13 +57,13 @@ This example responds to customer questions by simultaneously generating a respo
5757
2. The second task checks for innapropriate content.
5858
3. The third, main task coordinates the responses by using batch.`triggerByTaskAndWait` to run the two tasks in parallel. If the content is inappropriate, this task returns a message saying it can't process the request, otherwise it returns the generated response.
5959

60-
View the Trigger.dev parallelization task code: [src/trigger/trigger/parallelize-tasks.ts](./src/trigger/trigger/parallelize-tasks.ts).
60+
View the Trigger.dev parallelization task code: [src/trigger/trigger/parallel-llm-calls.ts](./src/trigger/trigger/parallel-llm-calls.ts).
6161

6262
### Orchestrator-workers
6363

6464
This pattern is like having a project manager (the orchestrator) who breaks down a big job into smaller tasks and assigns them to specialists (the workers). The orchestrator keeps track of everything and puts all the pieces back together at the end. Using batch.triggerByTaskAndWait, it efficiently coordinates multiple tasks while maintaining clear control over the entire workflow.
6565

66-
#### Example: Orchestrator-workers
66+
#### Orchestrator-workers task
6767

6868
1. Extracts distinct factual claims from a news article.
6969
2. Verifies each claim by considering recent news sources and official statements.
@@ -76,7 +76,7 @@ View the Trigger.dev orchestrator-workers task code: [src/trigger/trigger/orches
7676

7777
Here's where you add quality control to your AI system. The evaluator checks the output, and if it's not quite right, the optimizer suggests improvements. Think of it as having a friendly editor who reviews your work and helps make it better.
7878

79-
#### Example: Evaluator-optimizer
79+
#### Evaluator-optimizer task
8080

8181
1. Generates a translation of the text.
8282
2. Evaluates the translation.
@@ -88,3 +88,12 @@ View the Trigger.dev evaluator-optimizer task code: [src/trigger/trigger/evaluat
8888
## Blog post
8989

9090
Read the blog post: [Building Effective Agents with Trigger.dev](https://trigger.dev/blog/ai-agents-with-trigger).
91+
92+
## Learn more about Trigger.dev
93+
94+
To learn more about Trigger.dev, take a look at the following resources:
95+
96+
- [Trigger.dev Documentation](https://trigger.dev/docs) - learn about Trigger.dev and its features.
97+
- [Batch Trigger docs](https://trigger.dev/docs/triggering) - learn about the Batch Trigger feature of Trigger.dev.
98+
- [Realtime docs](https://trigger.dev/docs/realtime) - learn about the Realtime feature of Trigger.dev.
99+
- [React hooks](https://trigger.dev/docs/frontend/react-hooks) - learn about the React hooks provided by Trigger.dev.

0 commit comments

Comments
 (0)