Skip to content

MLOps conference workshop ​

Workshop slides (PDF)

Six exercises for the MLOps conference edition of Harness Engineering. Each exercise asks you to make a harness design decision and use the trace to assess it.

Choose how you want to participate. Open the public Canvas to follow along without installing anything. You can inspect the saved conversations without a login, model key or new model calls.

OptionWhat you doWhen to choose it
1. Browse the public CanvasOpen the read-only MLOps workshop archive and expand tool calls and results. No installation, login or model key is needed.Fastest way to follow the workshop and inspect the recorded work.
2. Inspect in your own CanvasDownload and import the same histories into a local Canvas.Keep the conversations after the temporary server is removed.
3. Run the exercises yourselfStart fresh conversations with your own configured model and workspace.Change the harness and compare new runs.

The public server is temporary and read-only. It uses plain HTTP. Do not enter credentials or private information. New runs, edits and resumed conversations are blocked.

Use Get started for setup details and saved conversations for direct workshop links. Open the exercise prompts when running a fresh attempt.

ExerciseOpen the instructionsHarness decision
1Compare harnessesSame task and model, different harnesses.
2Choose tool accessMatch tool access to the task.
3Choose contextInspect what context changes in the trace.
4Route modelsWrite a routing and escalation policy.
5VerificationWhat evidence should the harness require before accepting the agent’s work?
6Multi-agent systemsWhen should you use multiple agents, and how should they divide and integrate the work?

The separate MLOps saved-conversation bundle is built and verified in a fresh local Canvas store. It includes all six exercises, with original SVG outputs for Exercise 4 and the migration history for Exercise 5. Download the published edition from the saved-conversation page.

Built as a friendly front door for the runnable OpenHands harness lab.