Weights & Biases Weave topics
12 short topics in AI Evaluation LLMOps and Governance. Each one is a single focused exercise with a clear piece of evidence at the end.
12 topics, one exercise each.
Work through them in order, or jump to the one you need.
These are draft topic outlines (draft; instructor review pending). Full lessons follow after review; ask Ajay if you need a topic sooner.
- 01
Trace and span organization
Inspect evidence for trace and span organization in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 02
Prompt and model metadata
Inspect evidence for prompt and model metadata in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 03
Input and output capture policy
Inspect evidence for input and output capture policy in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 04
Session and user correlation
Inspect evidence for session and user correlation in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 05
Token and cost records
Inspect evidence for token and cost records in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 06
Latency and error analysis
Inspect evidence for latency and error analysis in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 07
Dataset and evaluation integration
Inspect evidence for dataset and evaluation integration in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 08
Human feedback collection
Inspect evidence for human feedback collection in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 09
Data redaction and retention
Inspect evidence for data redaction and retention in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 10
Provider and environment comparison
Inspect evidence for provider and environment comparison in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 11
Alert and dashboard design
Inspect evidence for alert and dashboard design in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course → - 12
Instrumentation verification
Inspect evidence for instrumentation verification in Weights & Biases Weave; explain the diagnosis and verify a proposed correction in a lab. Keep the exercise bounded and record the behavior supported by the chosen version.
Open micro-course →
Learn the same ideas beyond Weights & Biases Weave.
These courses share topics with this one, so you can compare how each language or tool handles the same concept.
More in AI evaluation observability and protocols.
You have the curiosity.
Let’s turn it into capability.
Start with a practical workshop or bring a specific question to Ajay.