Skip to content

docs: renumber the README layer table so it matches the "3 layers" claim #205

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rajarshidattapy wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −4
Open

docs: renumber the README layer table so it matches the "3 layers" claim #205

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,10 +32,10 @@ On top of live browser control, WebCMD adds 3 layers of learnings. Each layer co

| Layer | Scenario | What Webcmd Helps With |
| --- | --- | --- |
| 1. Live browser control | The site is unfamiliar. | Use `webcmd browser` to inspect, click, type, extract, capture network calls, and complete the task in a real browser. |
| 2. Sitemap memory | The site is familiar, but the action space is not fully known. | Capture an agent-facing sitemap of observed pages, states, actions, workflows, APIs, pitfalls, and fallback paths. |
| 3. CLI authoring | The action space is known, but the path is still too variable for one fixed sequence. | Explicitly author a reusable `webcmd <site>` adapter with structured output, so future agents spend tokens on the task instead of navigation. |
| 4. Extend existing CLIs | The workflow is deterministic enough to stop browsing. | Extend the `webcmd <site>` adapter with a tailored command so the workflow runs instantly with the least amount of tokens. |
| 0. Live browser control | The site is unfamiliar. | Use `webcmd browser` to inspect, click, type, extract, capture network calls, and complete the task in a real browser. |
| 1. Sitemap memory | The site is familiar, but the action space is not fully known. | Capture an agent-facing sitemap of observed pages, states, actions, workflows, APIs, pitfalls, and fallback paths. |
| 2. CLI authoring | The action space is known, but the path is still too variable for one fixed sequence. | Explicitly author a reusable `webcmd <site>` adapter with structured output, so future agents spend tokens on the task instead of navigation. |
| 3. Extend existing CLIs | The workflow is deterministic enough to stop browsing. | Extend the `webcmd <site>` adapter with a tailored command so the workflow runs instantly with the least amount of tokens. |

## Demo

Expand Down