Score your stack.

Six tests decide whether an agentic architecture is open in practice, whatever its licenses say. Give each one 0 (absent), 1 (partial), or 2 (demonstrated), and write down the evidence. The total is out of 12. Score the system you run, not the one on the roadmap.

Try an example:
  1. 01ReplaceableCan one component be swapped without rebuilding the system?
  2. 02InspectableCan a builder understand what runs and why?
  3. 03PortableCan identity, skills, context, and work move?
  4. 04BoundedAre authority and approval requirements explicit?
  5. 05GroundedDo agents share durable data and semantic meaning?
  6. 06AuditableCan people reconstruct decisions and outcomes?

0 of 6 tests scored

Score every test to see the result. Partial answers are saved in this browser only.

Scoring runs in your browser; nothing is sent to a server. Share links carry the six scores only, not the stack name or evidence.

How to read the score

Using it well

Each test has a full explainer in the knowledge base: Replaceable, Inspectable, Portable, Bounded, Grounded, Auditable.

The scorecard questions and rubric are licensed CC BY 4.0. Reuse and adapt them with credit to Alex Merced, openagenticplatform.com.