Case study 03 · Governed agents
In preparation for release
WAGF
A Water Agent Governance Framework that checks proposed LLM-agent decisions before they update a human–water simulation.
- structured decision contract
- physical + financial + behavioral checks
- deterministic audit trace
Problem
Why this problem matters
A syntactically valid action can still violate physical limits, household finances, behavioral theory, or the current simulation state.
System artifact
Inspect the research logic
The public governance trace is a frozen demonstration of the control flow. It does not call a live model and is not a released product benchmark.
Frozen demonstration · no live model call
- Proposed action
- Parser
- Physical check
- Financial check
- Behavioral check
- Audit record
- State update
Rejected: cost exceeds available household budget
Role & method
What I built
I designed the context builder, structured decision schema, parser, validators, targeted repair loop, audit record, and simulation-state boundary.
- Build context from approved persona and simulation state.
- Require a structured action and ratings.
- Parse before any state mutation.
- Run physical, financial, and behavioral-theory checks.
- Accept, reject, or request targeted repair.
- Write the trace, then update state only for an accepted action.
Validation and limitations
Validation
- Schema validation
- Fail-closed parser boundary
- Named rule results
- Deterministic demonstration trace
- State update occurs after acceptance
Limitations
- Declared rules cannot cover every failure mode.
- Repair can satisfy a rule while still producing a weak decision.
- The framework remains in preparation for release.
- Demonstration records are illustrative, not research outcomes.
What changed
Governance is clearest when every decision exposes the proposal, the rule that failed, the allowed repair, and the exact state transition.
Contact
Build evaluations that connect model behavior to real evidence
I am seeking a full-time Summer 2027 internship from approximately late May through mid-August. I am especially interested in LLM evaluation, agent systems, behavioral simulation, and AI for science.