Governed Quant Research Agent
Zeto extends beyond a research platform into a governed quant research agent for systematic experimentation. Local LLMs operate through MCP tools to inspect workflow state, build diagnostic context, retrieve research memory, review failure modes, propose controlled improvements, generate draft configurations, and interpret post-run results. The agent can reason across the research lifecycle, but it cannot bypass the engine: validation, approval, YAML rendering, and execution remain explicit, auditable, and human-controlled.
Natural-language research requests are transformed into structured research actions linked to deterministic diagnostics and provenance-aware artefacts. AI proposes; Zeto validates; the researcher approves; execution only occurs after explicit RUN authorisation.
Five architecture layers — from research intent to governed execution to evidence-grounded AI review.
Natural language or structured request from researcher
Parse and classify intent into typed workflow actions
Select tools, data, configurations, and review strategy
Generate candidate experiment configuration draft
Researcher reviews draft, compares, and validates intent
Final approved configuration is persisted
Explicit human control before any execution is initiated. The LLM cannot run experiments or bypass approval.
Quant research platform executes the approved configuration
Metrics, diagnostics, plots, configs, and metadata are generated
Relevant artefacts, diagnostics, metadata, plots, and lineage assembled into structured context
Deterministically detect and flag issues before LLM review
Review, comparison, and synthesis using structured evidence
Reviews, decisions, and insights linked into lineage and stored for future use
End-to-end walkthrough from research request to evidence-grounded review and research evolution.
Intent Routing
Natural-language research requests are converted into typed workflow actions before planning and review occur.
Context Engineering
Research artefacts are transformed into structured context containing diagnostics, metadata, plots, and failure modes before any LLM interaction.
Governed AI Review
Deterministic evidence is assembled before interpretation, ensuring reviews remain traceable, reproducible, and evidence-grounded.
Research Memory
Reviews, proposals, lineage records, and evolution chains preserve research state across iterations.
- LLM output is advisory
- Human approval required
- No autonomous experiment execution
- Quant engine remains source of truth
- Failure modes detected deterministically
- Reviews linked to persisted artefacts