module-3
Skill4 starsChanged 6 months agoMITView on GitHub
Teaching instructions for Module 3 (Dashboard) — use when module_id is module-3
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- NVIDIA/nemoclaw-communitytheir own version, first seen Oct 13, 2026
- brevdev/workshop-build-an-agenttheir own version, first seen Oct 9, 2026
- midegdugarova/operating-production-agentstheir own version, first seen Aug 3, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- brevdev/workshop-build-an-agent★ 156same name
- NVIDIA/nemoclaw-community★ 142same name
- midegdugarova/operating-production-agents★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- python/deep_tutor/AGENTS.mdAGENTS.md
- python/m5/l5/AGENTS.mdAGENTS.md
- python/m6/dacli_tutor/AGENTS.mdAGENTS.md
- typescript/deep_tutor/AGENTS.mdAGENTS.md
- typescript/m5/l5/AGENTS.mdAGENTS.md
- module-1Skill
- module-2Skill
- module-4Skill
- module-5Skill
- module-6Skill
- module-1Skill
- module-2Skill
- module-3Skill
- module-4Skill
- module-5Skill
- module-6Skill
- module-1Skill
- module-1Skill
- module-2Skill
- module-3Skill
- module-4Skill
- module-5Skill
- module-6Skill
- module-1Skill
- module-2Skill
- module-3Skill
- module-4Skill
- module-5Skill
- module-6Skill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Ask what the student wants to find in the dashboard (a specific trace, a deployment URL, runs by a user, cost metrics, etc.) and describe …
- Distinctive: line 17
If the student asks "where do I see X?", walk them to the section of the dashboard rather than explaining concepts in the abstract.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Module 3 — Dashboard
Lesson Title
The LangSmith Deployment Dashboard
Goal
Orient the student to the LangSmith dashboard so they can find their deployment, inspect runs and traces, and monitor production behavior. This module is delivered as a video walkthrough; the agent's role is to answer follow-up questions about what the student saw.
How to run this lesson
- This module is a video walkthrough — there is no companion script to run.
- Ask what the student wants to find in the dashboard (a specific trace, a deployment URL, runs by a user, cost metrics, etc.) and describe where to look.
- If the student asks "where do I see X?", walk them to the section of the dashboard rather than explaining concepts in the abstract.
- Reinforce the connection to other modules: a trace shows the same
thread_id/assistant_idthey used in module 2; an env-var screen is where they confirm the.envfrom module 1 actually reached the deployment.
Key concepts to cover
- The dashboard URL —
https://smith.langchain.com/; the deployments list is the entry point - A deployment page — graph list, deployment URL, env vars, revisions, traffic
- Traces — one row per run; expand to see the full agent trajectory, tool calls, and inputs/outputs
- Filtering traces by
thread_id,assistant_id, ormetadata.owner— the same identifiers the SDK uses - Monitoring — request rate, error rate, latency, token usage, cost
- Revisions — each deploy is a new image; you can roll back if a deploy breaks
- Env vars — what's actually packaged into the deployment (vs what's only in your local shell)
- The relationship between dashboard objects and SDK calls —
client.threads.search()and the threads tab show the same data
Tone guidance
Concise and practical. The student is not learning new APIs in this module — they're learning where things live. When they ask about a feature, answer with a navigation path ("click your deployment → Traces → filter by …") rather than a conceptual explanation.
Reference material
Full reference material is in information.md in this directory. Read it before answering factual questions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.