Prepare files for handoff
Check architecture, specs, context files, design principles, and operating rules before sending them to devs or stakeholders.
A coherence and behavior-drift layer for AI-native projects.
Review the system around the model.
Mesh Sentinel reviews dense AI system packets — context architecture, behavior specs, workflows, diagnostics, and eventually code — to detect contradictions, missing operating rules, and behavior drift risks before humans approve the system.
Why: teams lose coherence as AI systems move from idea → specs → context → code.
Sentinel review goals are presets over the same core workflow: source of truth, evidence, review question, report.
Check Intelligence Hub alignment
Compare tools, repos, and outputs against project principles, source-of-truth strategy, and operating intent.
Check whether a repo matches specs
Review README, code, tests, configs, and implementation snippets against intended behavior and acceptance criteria.
Check drift from approved baseline
Compare new artifacts or commits against an approved packet, spec, prior report, or project baseline.
The hosted demo includes a stable walkthrough, live K2 reviews, document packet review, and repo coherence review.
1. Ingest packet
Read files, pasted artifacts, or selected repo files.
2. Review coherence
K2 reviews contradictions, missing rules, and drift risks.
3. Normalize
The harness validates JSON and normalizes status.
4. Report
Generate human-readable approval blockers and next tests.
5. Trace
Preserve inputs, files, model, outputs, and finding provenance.
Sample test files
Use this packet to test Sentinel with a known source-of-truth/evidence mismatch. The final sample will include source-of-truth requirements, behavior rules, workflow expectations, and a public GitHub repo with intentionally drifted implementation evidence.
Sample output reports
Compare your run against a prepared Sentinel report from the same sample packet. The report will show approval readiness, blockers, contradictions, drift risks, recommended next tests, and the reviewed file trace.
- View sample Sentinel report
- Download sample JSONComing soon
To run the demo, use the Sample Packets section above. These resources explain the framework behind Sentinel and the Public Service Assistant sample.
AI Behavior & Context Architecture Framework
The source framework and sample documentation pattern behind the Public Service Assistant source packet.
The System Around the Model
A long-form article explaining why AI behavior depends on context, workflow, constraints, and the system around the model.
AI Reasoning Field Guide
A field guide for reading, evaluating, and diagnosing AI reasoning behavior in context-aware systems.
- Field guideComing soon
Testing & Diagnostics
A future guide on testing AI behavior by architecture layer, including workflow drift, permission leakage, routing errors, and escalation failures.
- Diagnostics guideComing soon