Updates Weave's landing page with new auto-instrumentation skill - #2985
Updates Weave's landing page with new auto-instrumentation skill#2985dbrian57 wants to merge 4 commits into
Conversation
Readability impactWord-weighted Flesch-Kincaid grade change across 1 changed page: +0.7 (harder). Lower Flesch-Kincaid grade and higher reading ease both mean easier to read. This check is informational and never blocks a PR. Human readability
AI agent comprehensionRated 0-3 (higher is easier for an agent to parse and act on).
Curated-docs baseline median FK grade by type: conceptual 10.5, procedural 8.8, reference 9.4. |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
📚 Mintlify Preview Links📝 Changed (1 total)📄 Pages (1)
🤖 Generated automatically when Mintlify deployment succeeds |
🔗 Link Checker Results✅ All links are valid! No broken links were detected. Preview: https://wb-21fd5541-weave-agent-auto-instrumentation.mintlify.site |
|
|
||
| Project configuration: | ||
| WEAVE_PROJECT=$[YOUR-PROJECT-NAME] | ||
| WEAVE_API_KEY=$[WANDB-API-KEY]`; |
There was a problem hiding this comment.
I wouldn't think it'd be a good idea to pass an API key visibly through a prompt to an LLM?
What about if we told people to set these in their zshrc file instead, and then the prompt could extract it from there?
There was a problem hiding this comment.
I think that's what the $ symbol is kind of denoting here, right? Like echo $WANDB_API_KEY? And we mention that you should set these as env variables in the opening paragraph. Is there a better way here?
There was a problem hiding this comment.
oh, i thought that was setting an environment variable to the value, and that we were asking them to replace [WANDB-API-KEY] (since that's our replaceable format style) with the text of the key?
would we want the brackets on there if it is supposed to be reading from an en var that exists by that name?
also, confused why we're setting WEAVE_API_KEY? i checked the SKILL and it doesn't have this token
There was a problem hiding this comment.
like, the skill has an auth-related section, but says nothing about WEAVE_API_KEY:
- Authentication is the user's job, not yours, so never handle their key. A W&B API key is a
secret, and it must not enter your context or the repo. Tell the user to authenticate in their own
terminal: setWANDB_API_KEY(from https://wandb.ai/authorize), or runwandb login(Python) or
await weave.login(key)once (Node). You may check that a key is reachable (the env var is set,
or~/.netrchas anapi.wandb.aientry), but never read or print its value, and never write it
into source code or into a committed.env.
There was a problem hiding this comment.
i interpret that as these are the instructions we'd give the user up top:: "authenticate in your own
terminal: set WANDB_API_KEY (from https://wandb.ai/authorize), or run wandb login (Python) or
await weave.login(key) once (Node). "
and then that line gets removed from the prompt altogether?
There was a problem hiding this comment.
WEAVE_PROJECT doesn't seem to be used by the skill either? (tho sounds like the skill will prompt for it itself)
maybe i'm just confused ;)
| ```text | ||
| Fetch and then use the following skill to instrument all agents with Weave: | ||
|
|
||
| https://raw.githubusercontent.com/wandb/weave/refs/heads/master/skills/weave-instrument/SKILL.md |
There was a problem hiding this comment.
also, curious why we're providing this 'raw' link instead of the actual repo https://github.com/wandb/weave/blob/master/skills/weave-instrument/SKILL.md?
There was a problem hiding this comment.
I think the idea is to make it as easy as possible for the agent to ingest. This is Andrew's prompt that he designed and put in the Weave UI, so I was just copying the workflow he designed.
Co-authored-by: Anastasia Guspan <aguspan@wandb.com>
2 participants
Description
Resolves DOCS-2949. This updates Weave's landing page with the product's new onboarding workflow that uses a prompt to instruct an agent on how to install Weave into a codebase.