Agents and Automation
The Agents and Automation route has four courses that build on each other, from the basics to a final project of your own.
The four courses
- R07-101
Tool Use, Function Calling, MCP and Workflow Automation
The student can build a compliant MCP server exposing typed, idempotent tools and an agent client that selects and executes the correct tool sequence across 30 frozen multi-step scenarios.
- R07-201
Production RAG and Hybrid Search
The student can build a hybrid BM25 + vector + RRF retrieval pipeline over a frozen 1,000-document corpus that achieves ≥90% Recall@5 on keyed queries and abstains on 100% of unanswerable queries.
- R07-301
Stateful Agent Loops, Memory and Human Approval Gates
The student can implement a stateful agent state machine with SQLite/D1 checkpointing that resumes cleanly after interruption, halts on step/cost ceilings, and pauses for explicit human approval before any external write action.
- R07-401
Sandboxed Agents, Trace Evaluation and Cost-Per-Task
The student can run a sandboxed agent against a 50-task benchmark fixture, emit complete step traces and cost-per-task metrics, and pass all sandbox containment and budget-enforcement tests.
What has to be passed
Every course ends with a task marked against a fixed answer key.
- R07-101 Submit an MCP server and client in Python or TypeScript that pass 30 fixed automated protocol, schema-validation, idempotency, and error-recovery tests against a deterministic model stub.
- R07-201 Submit a hybrid retrieval service evaluated by the automated runner against 100 frozen test queries (80 answerable with keyed chunk IDs, 20 unanswerable); must achieve ≥ 90% Recall@5, exact citation formatting, and 100% abstention on unanswerable items.
- R07-301 Submit a stateful agent workflow that passes 35 automated state-machine tests verifying checkpoint resume without duplicate actions, hard circuit-breaker termination at the token/step limit, and 100% blocking of irreversible tool calls until a signed approval token is supplied.
- R07-401 Submit a sandboxed agent runner and trace evaluator that execute against a frozen 50-task suite in the test container, passing all containment checks, staying within the per-task token budget, and producing exact keyed trace metrics.
The lessons for this course are being written. Join the waitlist and we will email you when it opens. Join the waitlist