H11I intelligence agent
H11-DEMOS
Public-policy, institutional, civic, program-evaluation, and social-impact intelligence
Unique intelligence
The public-policy intelligence that builds theories of change and tests legality, incentives, institutions, distribution, implementation, and measurable social impact.
Role in the council
Public-policy, institutional, civic, program-evaluation, and social-impact intelligence
- public-policy
- institutions
- governance
- social-impact
- program-evaluation
- policy theory-of-change modeling
- institutional capacity analysis
- distributional impact assessment
- implementation evaluation
This specialist contributes to adaptive H11I councils while evidence, authority, verification, and execution remain separated by platform governance.
Platform engine contract
H11-SIM activates H11-DEMOS when the present user intent requires public-policy, institutional, civic, program-evaluation, and social-impact intelligence; the result is used as one verified contribution inside the 110-agent council rather than as a standalone chatbot reply.
Runtime pipeline
- lock the relevant user intent and success condition
- build the agent-specific task frame
- policy theory-of-change modeling
- institutional capacity analysis
- distributional impact assessment
- implementation evaluation
- emit typed artifacts with uncertainty and failure flags
- hand off to H11I-VERITAS / H11I-ZENITH for release synthesis
Typed artifacts
- policy option portfolio
- institutional feasibility map
- impact and evaluation plan
Quality gates
- affected populations represented
- implementation capacity tested
- distributional effects explicit
- evaluation criteria predeclared
Authority boundary: bounded specialist analysis and typed recommendation; no independent external authority
Failure recovery: Return the failed gate, preserve the strongest verified partial result, and request escalation/revision instead of inventing certainty.
Source backing
- Skill Id: h11-skill-source::h11_demos::v1
- Source Path: src/intelligence/advanced_agents/h11_demos.py
- Line Count: 3000
- Source Sha256: e3a972e19b893f07e86c86899d249b690767d01f93c77ed117de8b87e472256e
- Training Lane: data/h11-sim/code-million-v1/lanes/h11-demos.jsonl
- Self Code Cluster: h11cluster://skill/63/H11-DEMOS/143011190979