mbrucedogs/ai-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: format chat mode section

Browse Source
This commit is contained in:
Matt Bruce 2026-02-10 15:33:31 -06:00
parent 74555c65cc
commit 762e3d3521
1 changed files with 32 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
docs/ai/usage-tokens.md
View File

@ -65,15 +65,35 @@ Think of each model as a different "speed and cost" setting. Some models are che
## Chat Modes And Cost (Plain Language) ## Chat Modes And Cost (Plain Language)
Copilot chat has four modes. The lighter the mode, the less work you ask it to do. Copilot chat has four modes. The lighter the mode, the less work you ask it to do.
Ask: Questions, summaries, or explanations. Example: "Summarize this file in 5 bullets and list 2 risks." Ask: Questions, summaries, or explanations.
Edit: Small, targeted changes with clear constraints. Example: "Update this function to return nil on empty input. Keep behavior the same otherwise." Example prompt:
```text
Summarize this file in 5 bullets and list 2 risks.
```
Plan: Get steps before edits. Example: "Give me a 5-step plan to refactor this module. Wait for approval before edits." Edit: Small, targeted changes with clear constraints.
Agent: Multi-step work across files or tools. Example: "Refactor these two files, update tests, run the test task, and summarize results." Example prompt:
```text
Update this function to return nil on empty input. Keep behavior the same otherwise.
```
#### Example: Choosing A Model Plan: Get steps before edits.
Example prompt:
```text
Give me a 5-step plan to refactor this module. Wait for approval before edits.
```
Agent: Multi-step work across files or tools.
Example prompt:
```text
Refactor these two files, update tests, run the test task, and summarize results.
```
### Example: Choosing A Model
- Task: "Summarize this file in 5 bullets." Use a 0.33x or 1x model. - Task: "Summarize this file in 5 bullets." Use a 0.33x or 1x model.
- Task: "Refactor three files and update tests." Start with a 1x model. Move to 3x only if the 1x model fails. - Task: "Refactor three files and update tests." Start with a 1x model. Move to 3x only if the 1x model fails.
- Task: "Explain a confusing production issue with lots of context." Start with 1x, and only move up if needed. - Task: "Explain a confusing production issue with lots of context." Start with 1x, and only move up if needed.
@ -149,11 +169,13 @@ If each step is done with a 3x model and a growing chat context, your token use
### Use The Right Chat Mode ### Use The Right Chat Mode
Using the lightest chat mode for the job keeps outputs smaller and cheaper. Using the lightest chat mode for the job keeps outputs smaller and cheaper.
Example: Example prompts:
Ask: "Summarize this file in 5 bullets." ```text
Plan: "Give me a 5-step plan to refactor this module. Wait for approval." Ask: Summarize this file in 5 bullets.
Edit: "Update this function to handle empty input. Keep behavior the same otherwise." Plan: Give me a 5-step plan to refactor this module. Wait for approval.
Agent: "Refactor these two files, update tests, and summarize results." Edit: Update this function to handle empty input. Keep behavior the same otherwise.
Agent: Refactor these two files, update tests, and summarize results.
```
## Quick Checklist ## Quick Checklist
- Is the request specific and scoped? - Is the request specific and scoped?