phowell
/
pocketflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update the doc

This commit is contained in:
zachary62 2025-03-03 11:00:30 -05:00
parent 5c0f466d58
commit 3b6200642b
2 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docs/guide.md
View File

@ -1,6 +1,6 @@
--- ---
layout: default layout: default
title: "Development Playbook" title: "Build your LLM App"
--- ---
# LLM Application Development Playbook # LLM Application Development Playbook
@ -22,12 +22,11 @@ These system designs should be a collaboration between humans and AI assistants:
| 6. Optimization | ★★☆ Medium | ★★☆ Medium | The human reviews the code and evaluates the results, while the AI helps optimize. | | 6. Optimization | ★★☆ Medium | ★★☆ Medium | The human reviews the code and evaluates the results, while the AI helps optimize. |
| 7. Reliability | ★☆☆ Low | ★★★ High | The AI helps write test cases and address corner cases. | | 7. Reliability | ★☆☆ Low | ★★★ High | The AI helps write test cases and address corner cases. |
1. **Project Requirements**: Clarify the requirements for your project, and evaluate whether an AI system is a good fit. 1. **Project Requirements**: Clarify the requirements for your project, and evaluate whether an AI system is a good fit. An AI systems are:
- An AI system is suitable for routine tasks that require common sense (e.g., filling out forms, replying to emails). - suitable for routine tasks that require common sense (e.g., filling out forms, replying to emails).
- An AI system is suitable for creative tasks where all inputs are provided (e.g., building slides, writing SQL). - suitable for creative tasks where all inputs are provided (e.g., building slides, writing SQL).
- An AI system is **not** suitable for tasks that are highly ambiguous and require complex information inputs (e.g., building a startup). - **NOT** suitable for tasks that are highly ambiguous and require complex information (e.g., building a startup).
- > **If a human can’t solve it, an LLM can’t automate it!** - > **If a human can’t solve it, an LLM can’t automate it!** Before building an LLM system, thoroughly understand the problem by manually solving example inputs to develop intuition.
Before building an LLM system, thoroughly understand the problem by manually solving example inputs to develop intuition.
{: .best-practice } {: .best-practice }
2. **Utility Functions**: AI system is the decision-maker and relies on *external utility functions* to: 2. **Utility Functions**: AI system is the decision-maker and relies on *external utility functions* to:

2
docs/index.md
View File

@ -59,4 +59,4 @@ We model the LLM workflow as a **Nested Directed Graph**:
- [(Advanced) Multi-Agents](./multi_agent.md) - [(Advanced) Multi-Agents](./multi_agent.md)
- Evaluation - Evaluation
## [LLM Application Development Playbook](./guide.md) ## [Build your LLM App](./guide.md)