Agents / mcit

Sizing Agent

Agent preparedGovernanceGovernment-RestrictedLimited riskGov Reuse9 runs/30d

Scores a candidate asset against the five sizing rubric factors from the evidence supplied, produces a draft band with the reasoning for each factor, and flags where evidence is missing rather than assuming a score. The funding decision stays with the strategy forum.

Governs the marketplace

Agent preparedAll governance agents →

An agent gathers the evidence, applies the rule, scores the case and recommends an outcome. A named human decides and the decision is recorded against them.

Acts for
Marketplace Operator
Action class
advisory
Decisions / 30d
9
Overturned by a human
11%

Processes covered

  • Sizing and banding of candidate assets

Stages:steer

Memory

Retains scorecards for comparables; purged when the asset is retired.

Safe state

Stops scoring and returns the case with the factors it could not evidence when more than two factors lack evidence.

Reviewer time per case: 15 min with this agent, 90 without.

Tools

  • Sizing rubric (five factors)
  • Evidence bundle reader
  • Comparable-asset index
  • Scorecard writer

Data access scope

  • Read-only: candidate submissions and their evidence
  • Read-only: scorecards of previously banded assets
  • Write: draft scorecards marked as agent-prepared

Guardrails

  • Every factor score cites the evidence it rests on; a factor without evidence is scored as missing, never estimated
  • Cannot move a band once a human has confirmed it
  • Draft bands are never shown as final to the submitting entity

Human-in-the-loop

  • MCIT strategy forum confirms the band and commits funding

Orchestration

Trigger / IntakeLLM Orchestratorfanar-gov-7b-instructSizing rubric (five factors)Evidence bundle readerComparable-asset indexScorecard writerHumansign-off

Every tool call is scoped by the declared data access above; the orchestrator cannot reach systems outside it. Owning entity: MCIT.

Live demo run

Watch the agent execute a real scenario step by step, every tool call, validation, and human checkpoint is traced and auditable. Typical run: ~5.6s.

Owning entity

mcMCIT

Updated 2026-07-21. Run traces retained 24 months for audit under the platform governance policy.

Community · 0 threads

Questions, findings and requests from the entities that use this asset. Owners reply here; threads with upvotes surface to the owning entity's inbox.

No threads yet. Be the first entity to ask, or to share what you found.