Clairos Learn

Learn AI application operations through guided terminal labs.

Operate a simulated model-backed application through manifests, inference requests, prompts, evaluations, retrieval, serving, traces, guardrails, cost, and incident evidence.

Continue Open sandbox

Track progress 0/180 lessons 0/18 missions 0/11 briefings 12 courses

Continue View profile

New learnerrank 0XP 0%complete

learner@aiops:/home/learner $ AI operations lab: type a command, press Enter

Starter prompts

Run aiops models list, then inspect the model catalog JSON.
Check the loopback gateway health and metrics endpoints.
Inspect ai-gateway with docker, kubectl, systemctl, and journalctl.
Compare evaluation, retrieval, trace, guardrail, and cost evidence.
Create a local incident note under /home/learner/lab and read it back.

Mission board

AI systems foundations mission

Complete the ai systems foundations course and preserve its operator evidence habits.

150 XP

CLI and workspace hygiene mission

Complete the cli and workspace hygiene course and preserve its operator evidence habits.

150 XP

Models, artifacts, and runtimes mission

Complete the models, artifacts, and runtimes course and preserve its operator evidence habits.

150 XP

Inference requests and APIs mission

Complete the inference requests and apis course and preserve its operator evidence habits.

150 XP

Prompt and configuration operations mission

Complete the prompt and configuration operations course and preserve its operator evidence habits.

150 XP

Evaluations and datasets mission

Complete the evaluations and datasets course and preserve its operator evidence habits.

150 XP

Retrieval and embeddings mission

Complete the retrieval and embeddings course and preserve its operator evidence habits.

150 XP

Serving, containers, and resources mission

Complete the serving, containers, and resources course and preserve its operator evidence habits.

150 XP

Observability and tracing mission

Complete the observability and tracing course and preserve its operator evidence habits.

150 XP

Safety, privacy, and governance mission

Complete the safety, privacy, and governance course and preserve its operator evidence habits.

150 XP

Cost, capacity, and reliability mission

Complete the cost, capacity, and reliability course and preserve its operator evidence habits.

150 XP

Incident response and capstones mission

Complete the incident response and capstones course and preserve its operator evidence habits.

150 XP

AI systems foundations + CLI and workspace hygiene

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Models, artifacts, and runtimes + Inference requests and APIs

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Prompt and configuration operations + Evaluations and datasets

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Retrieval and embeddings + Serving, containers, and resources

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Observability and tracing + Safety, privacy, and governance

Complete both course endpoints to prove the operational handoff is intact.

250 XP

AI operations final response

Finish the last three incident capstones and demonstrate a complete evidence-first response loop.

500 XP

Save progress

Your Learn profile.

Save completed lessons, task completions, mission wins, XP, course status, and streaks with your Clairos account. Lab files, nano drafts, command history, and typed commands stay only in this browser.

Checking account status...

Progress sync is idle.

0XP New learnerrank 0day streak 0best streak 0daily streak 0lessons 0courses 0missions 0tasks Noverified

Continue

Progress sync stores completion IDs, scores, streaks, badges, and game settings. Terminal contents, editor snippets, lab scratch, email, and real names are never published on leaderboards or share cards.

Course categories

AI Ops lessons, grouped for steady progress.

Move from technical foundations to semi-advanced AI operations through exact commands, observable evidence, concept briefings, and progress-based missions. UNIX experience helps, but the CLI refresher makes it optional.

0/15 AI systems foundations

Understand models, requests, components, failure boundaries, and the operator's evidence-first role.

15 short lessons · 1 checkpoint 0/12 CLI and workspace hygiene

Build careful command, path, redaction, configuration, and evidence habits for AI operations work.

12 short lessons · 3 checkpoints 0/16 Models, artifacts, and runtimes

Inspect model manifests, versions, artifacts, runtime compatibility, accelerators, and rollout evidence.

16 short lessons · 2 checkpoints 0/16 Inference requests and APIs

Inspect bounded loopback requests, response envelopes, status codes, timeouts, retries, and streaming signals.

16 short lessons · 3 checkpoints 0/14 Prompt and configuration operations

Version prompts and configuration, compare changes, validate variables, and prepare controlled rollbacks.

14 short lessons · 2 checkpoints 0/18 Evaluations and datasets

Operate golden sets, evaluation runs, thresholds, regressions, slices, annotations, and release evidence.

18 short lessons · 3 checkpoints 0/16 Retrieval and embeddings

Inspect document ingestion, chunks, embeddings, indexes, retrieval quality, freshness, and grounded evidence.

16 short lessons · 3 checkpoints 0/17 Serving, containers, and resources

Inspect services, containers, Kubernetes resources, GPU signals, health, configuration, and rollout readiness.

17 short lessons · 1 checkpoint 0/15 Observability and tracing

Use logs, metrics, traces, request identifiers, latency percentiles, and error budgets to explain behavior.

15 short lessons · 2 checkpoints 0/15 Safety, privacy, and governance

Review guardrails, redaction, data boundaries, access, retention, model cards, and operational approvals.

15 short lessons · 2 checkpoints 0/14 Cost, capacity, and reliability

Inspect token cost, capacity, concurrency, caching, fallback strategy, load signals, and reliability tradeoffs.

14 short lessons · 2 checkpoints 0/12 Incident response and capstones

Combine system, model, retrieval, serving, safety, cost, and evidence habits in operator-style incidents.

12 short lessons · 3 checkpoints

Browse all lessons

Sandbox objectives

An AI application stack you can inspect end to end.

The mission board turns practice into a small game loop: run, inspect, verify, and reset.

AI systems foundations mission

Complete the ai systems foundations course and preserve its operator evidence habits.

150 XP

CLI and workspace hygiene mission

Complete the cli and workspace hygiene course and preserve its operator evidence habits.

150 XP

Models, artifacts, and runtimes mission

Complete the models, artifacts, and runtimes course and preserve its operator evidence habits.

150 XP

Inference requests and APIs mission

Complete the inference requests and apis course and preserve its operator evidence habits.

150 XP

Prompt and configuration operations mission

Complete the prompt and configuration operations course and preserve its operator evidence habits.

150 XP

Evaluations and datasets mission

Complete the evaluations and datasets course and preserve its operator evidence habits.

150 XP

Retrieval and embeddings mission

Complete the retrieval and embeddings course and preserve its operator evidence habits.

150 XP

Serving, containers, and resources mission

Complete the serving, containers, and resources course and preserve its operator evidence habits.

150 XP

Observability and tracing mission

Complete the observability and tracing course and preserve its operator evidence habits.

150 XP

Safety, privacy, and governance mission

Complete the safety, privacy, and governance course and preserve its operator evidence habits.

150 XP

Cost, capacity, and reliability mission

Complete the cost, capacity, and reliability course and preserve its operator evidence habits.

150 XP

Incident response and capstones mission

Complete the incident response and capstones course and preserve its operator evidence habits.

150 XP

AI systems foundations + CLI and workspace hygiene

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Models, artifacts, and runtimes + Inference requests and APIs

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Prompt and configuration operations + Evaluations and datasets

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Retrieval and embeddings + Serving, containers, and resources

Complete both course endpoints to prove the operational handoff is intact.

250 XP

Observability and tracing + Safety, privacy, and governance

Complete both course endpoints to prove the operational handoff is intact.

250 XP

AI operations final response

Finish the last three incident capstones and demonstrate a complete evidence-first response loop.

500 XP

Reference

Small commands, clear jobs.

These are the first tools learners will practice in the training lab.

aiops models

Inspect the simulated model catalog, manifests, and version comparisons.

aiops prompts

Review versioned prompt metadata and deterministic prompt diffs.

aiops evals

Run and inspect bounded evaluation fixtures without model execution.

aiops rag

Inspect retrieval documents, chunks, index status, and reviewed results.

aiops traces

Read deterministic request traces, summaries, and latency evidence.

aiops guardrails

Review simulated guardrail policies, checks, and audit summaries.

aiops cost

Estimate cost and capacity from fixed training metrics.

aiops incidents

Review incident timelines, evidence bundles, and operator notes.

curl

Read only fixed loopback training endpoints; external URLs and request bodies are blocked.

jq

Query JSON fixtures with a small declarative path subset; no expression execution occurs.

docker

Inspect fixed container, log, stats, and compose fixtures; execution and pulls are blocked.

kubectl

Inspect or dry-run fixed Kubernetes fixtures; cluster mutations are blocked.

nvidia-smi

Read fixed accelerator and memory signals for capacity practice.

systemctl

Inspect the simulated AI gateway and supporting service state.

journalctl

Read bounded simulated AI service logs.

ss

Inspect the simulated loopback gateway listener.