Foundations
Build the first useful version on a real piece of work.
ORCHESTRATE / OPERATOR
Govern Your AI Agents
Build the control layer around agents: capability trust, tool permissions, authority/effect classification, human approvals, compatibility, cost admission, lineage, stop conditions and evidence about what actually ran. Governance should make useful agents safer to operate, not bury them in paperwork.
Deep diveProven in the LabHands on
Teams moving AI agents from experiments into repeated operationsBuilders maintaining a growing registry of tools, skills and integrationsOperators who need explicit trust and approval boundaries across autonomous workflows
Advanced Pack
Turn it into a repeatable system with deeper implementation, reusable assets and harder operating decisions. Free during Early Access.
Final Lab
Test the capability in a practical scenario when you want another round.
YOU'LL LEAVE WITH
A result you can take back to real work.
An agent governance layer with capability lifecycle, authority/effect rules, tool scopes, approval gates, cost/compatibility controls, lineage and operational-state evidence.
Create governance for one real agent workflow
Inventory capabilities, classify authority/effects, set tool permissions, define stop/human-approval conditions and record enough execution evidence to know what actually happened.
Build a scalable governance system for many agents and tools
Add capability lifecycle/testing, compatibility, cost admission, lineage, version promotion, operational truth, revocation and recurring governance review without blocking useful experimentation.
WHAT ADVANCED ADDS
Take the method back to real work.
Advanced includes reusable artifacts, decision rules and implementation material designed to keep working after you close the Path.
Capability Registry
A lifecycle record for candidate, to-be-tested, tested/approved, restricted and retired capabilities with evidence from real task use.
Authority/Effect Matrix
A classification of what agents may read, recommend, decide or change externally and which classes require human or deterministic approval.
Agent Run Evidence Pack
A minimal record of input/version, tools used, side effects, cost, accepted artifacts, operational state and why the workflow is considered complete.
PATH MAP
Build the first version. Then make it operational.
Foundations takes you through the first useful result. Advanced adds the implementation depth, harder cases and operating discipline needed to reuse it.
- 01Inventory What Agents Can Actually DoFree
- 02Classify Authority and EffectFree
- 03Scope Tools and Data AccessFree
- 04Define Stop and Approval ConditionsFree
- 05Record One Agent Run as EvidenceFree
- 01Build the Capability LifecycleAdvanced
- 02Test Capabilities on Natural TasksAdvanced
- 03Control Model, Tool and Protocol CompatibilityAdvanced
- 04Make Cost an Admission DecisionAdvanced
- 05Preserve Lineage and Release TruthAdvanced
- 06Run the Governance ReviewAdvanced
The Agent Governance Board
Several capabilities are powerful but unevenly tested, a deployment is ambiguous and an agent wants to take an external action. Decide what may run, what needs evidence and where human approval is mandatory.
Complete Advanced, take on the scenario if you want to test the capability, and pass it to create a lightweight shareable record of the result.
How Lab Achievements work →BEGIN THE PATH
Start with a real result.
Sign in with email and work through Foundations for free. Complete Foundations and unlock Advanced free during Early Access.
Start Foundations free