Labs

Every lab ends the same way a real build should: with a way to prove the work is actually done, not just produced.

Map an Agent-Worthy Workflow

Take a real process from your own work, score it against clear criteria, and decide whether it deserves an agent.

Build a Research and Brief Agent

Build an agent that researches a topic from real sources, cites them, and only reports done when the brief passes a completion check.

PythonOne model provider

Guided 90 min · intermediate

Build a Document-to-Report Agent

Build an agent that reads a pile of messy source documents and writes a clean structured report, then proves every section maps back to a real source.

PythonOne model provider

Guided 90 min · intermediate

Build a Data-to-Decision Agent

Build an agent that reads a CSV, computes the numbers, draws a chart, and checks its own figures before it reports a decision.

PythonOne model provider

Guided 75 min · intermediate

Add Human Approval to a High-Risk Action

Wrap a high-risk action like sending an invoice or issuing a refund in a propose, hold, approve, act state machine, with an audit record for every step.

PythonOne model provider

Runnable 90 min · intermediate

Build an Agent Evaluation Harness

Build a repeatable test set that runs your agent over known tasks, grades the results three ways, and produces a pass or fail regression report.

Pythonpytest

Guided 60 min · intermediate

Trace and Diagnose a Failed Run

Read the execution log of a failed agent run, find the step where it broke, name the root cause, and turn the fix into an evaluation case so it never comes back.

PythonOne model provider

Guided 180 min · advanced

Capstone: Multi-Step Operations Agent

Bring the whole playbook into one operations agent that takes a real request, works it across tools, gets human approval on the risky step, verifies the outcome and logs a full trace.

PythonOne model provider

What the lab statuses mean

Verified: Automated or manual verification passed within the freshness window.
Runnable: Full code and instructions are present.
Guided: Reproduction steps are present, external dependencies required.
Design exercise: Architecture task without a complete executable implementation.
Needs update: A dependency or result is known to be stale.

A lab is never labelled production-ready unless explicit production criteria are documented.