A design-time Agent Skill for engineering teams

Investigate the change before you recommend it.

It does not simply ask an agent to propose a MERGE, SPLIT, or UNMERGE. It investigates the entity-resolution workflow from multiple angles before producing a reviewable recommendation and a structured engineering plan.

A confident entity match is not permission to merge.

Platform links may include affiliate attribution. A qualifying purchase through an affiliate link may support the author without changing the buyer's price.

Multi-angle investigationExplicit controls and gapsEngineering-ready handoff
INVESTIGATION MODEL01 — 04
Four stages: operation context, multi-angle investigation, recommendation and guardrail design, and engineering handoff
From proposed identity change to reviewable engineering plan
11investigation angles
12controls in the example
9planning deliverables

Counts refer to the published methodology and synthetic CRM demonstration; they are not universal fixed output limits.

The problem

Entity resolution is not just a matching problem.

Two records can look similar and still represent different entities. A shared name, domain, contact, identifier or address may be a useful signal — but no single similarity signal automatically establishes that two records refer to the same real-world entity.

When an AI agent proposes a persistent identity change, the decision can affect more than the two records on screen. Relationships, ownership, history, downstream systems, permissions and derived data may all be involved.

Before deciding whether records should be merged, split or restored, the workflow needs to establish what is known, what conflicts, what can change, who has authority and what must happen when something is uncertain.
01

Similarity is a signal

It can help identify a candidate pair. It is not, by itself, proof of co-reference or authorization.

02

Identity changes have dependencies

A mutation may affect relations, history, linked records, indexes and external workflows.

03

Uncertainty must remain visible

Missing evidence, conflicting claims and unknown write boundaries should not become invented certainty.

Why not just prompt an agent?

One question is not a complete investigation.

A general-purpose agent can produce a plausible answer. The Planner provides a defined investigation structure so important dimensions are less likely to disappear between a persuasive recommendation and the engineering work needed to make it safe.

A generic prompt

One question. One answer.

A request to review a proposed merge may focus on the visible records and the available similarity signals.

  • Coverage depends on the prompt and context supplied.
  • Unknowns can be overlooked or treated as assumptions.
  • The answer may not translate into a complete engineering handoff.

The Guardrail Planner

A structured investigation. A reviewable plan.

The Skill works through a defined set of investigative dimensions and translates findings into explicit requirements.

  • Considers evidence, conflicts, scope, authority and downstream effects.
  • Surfaces unknowns, conditions and customer-owned decisions.
  • Connects recommendations to controls, validation and implementation responsibilities.

This is a difference in method and deliverable structure, not a claim that every general-purpose prompt will fail or that the Planner guarantees a correct decision.

The investigation

Eleven angles. One connected view of the proposed change.

The Planner examines the workflow before it produces a recommendation. The areas below are connected: a conflict can change the evidence assessment; the evidence assessment can change the authorization path; and an unknown commit boundary can stop the proposed operation altogether.

01

Entity and evidence

01

Scope

What operation is proposed, which entities and relationships are involved, and what state could be affected?

02

Entity context

What kind of entity is involved, what does identity mean in this domain, and what context is required to interpret the records?

03

Evidence and provenance

Which claims are supported, by what sources, with what provenance, validity and verification status?

04

Conflicting attributes

Which attributes or documents disagree, and which contradictions remain unresolved rather than silently reconciled?

02

Authority and impact

05

Authorization

Who or what is allowed to approve this specific operation, under which policy and separation-of-duties conditions?

06

Downstream impact

Which linked records, identity-bearing relationships, indexes, integrations and dependent processes may be affected?

07

Commit boundaries

Where does the change become persistent, what belongs to the atomic write set, and which checks must hold before that point?

03

Failure, recovery and proof

08

Failure modes

What can fail before, during or after persistence — including stale state, partial effects and ambiguous commit outcomes?

09

Recovery paths

How should the system reconcile uncertain outcomes, handle idempotency, compensate where proven, or quarantine and escalate?

10

Validation scenarios

Which positive, negative, boundary and failure cases should engineering validate before deployment?

11

Open gaps

What facts, policies, permissions, technical boundaries or customer decisions are still unknown or unverified?

How it works

From proposed operation to engineering handoff.

The investigation is not a decorative checklist. Its findings inform the recommendation, the required controls and the conditions under which the proposed change should not proceed.

01 / CONTEXT

Qualify the operation

Establish the operation type, entity context, candidate scope and the identity-bearing state that may change.

02 / INVESTIGATE

Examine the workflow

Work through evidence, provenance, conflicts, authority, downstream effects, commit boundaries, failure and recovery.

03 / DESIGN

Form a reviewable recommendation

Translate findings into controls, approval conditions, version binding, HOLD points and unresolved decisions.

04 / HANDOFF

Prepare the engineering plan

Produce structured Markdown deliverables and a machine-readable JSON specification for customer-side implementation and validation.

Not every path ends in approval

When the facts are not established, the plan can say HOLD.

Depending on the findings, the recommendation may require further evidence, defer the operation, request human review or block the proposed change. Unknowns remain explicit; the Skill does not invent customer policy or convert model confidence into authorization.

Control architecture

From broad investigation to explicit controls.

The published synthetic MERGE example contains 12 named controls. They illustrate how investigation findings can become concrete requirements for a customer-side implementation. The exact controls depend on the operation and scenario.

CTRL-01

Operation, scope and action-class binding

CTRL-02

Registry-ID and legal-continuity identity gate

CTRL-03

Evidence eligibility, provenance and independence

CTRL-04

Claim-specific conflict and indeterminate-evidence handling

CTRL-05

Separate human approvals bound to operation and state

CTRL-06

Version binding and stale-state check

CTRL-07

Write-set completeness and atomicity gate

CTRL-08

Pre-commit invariants and transaction abort

CTRL-09

Post-commit validation and downstream reconciliation

CTRL-10

Post-commit and out-of-boundary failure handling

CTRL-11

Ambiguous commit outcome and idempotency

CTRL-12

Reversibility and authorization-path gate

These are design requirements in the example plan, not controls implemented by the Skill or an independently verified runtime security layer.

See the output

A synthetic CRM case, not a theoretical promise.

Explore a complete example of the Planner's output for an AI-proposed MERGE involving two CRM account records. The scenario is synthetic; names and identifiers are fictional.

THE SCENARIO

Two CRM records. Supported continuity, blocked commit.

An agent proposes merging CRM-ACCT-2097 into canonical record CRM-ACCT-1042. The supplied descriptions identify the same official registry ID (FIC-REG-004821) and a legal-name change effective 2024-04-01.

On those descriptions, the identity-continuity proposition is supported. The Planner did not independently verify the registry extract, gateway verification record or 2025 agreement, and the evidence is not yet authorization-eligible. The proposed tests also include a negative control: related companies with different registry IDs must not be merged on name, domain, address or contact similarity alone.

!
Identity continuity is supported on supplied descriptions, not yet authorization-eligible.

The example plan requires HOLD before the first persistent write while material evidence, policy, authorization and transaction-boundary decisions remain unresolved.

Explore the complete demonstration
12named controls in the MERGE example
31proposed customer-operation test scenarios
8blocking customer decisions recorded in the example
9canonical planning deliverables

The engineering handoff

Structured documents, connected by a machine-readable specification.

The example includes a plan overview, operation scope, guardrail and evidence requirements, commit-boundary design, implementation blueprint, validation scenarios, open gaps and JSON.

Read the example in context.

The plan is marked not_implementation_ready. It contains 12 proposed controls, 31 customer-operation test scenarios and three proposed Planner-level checks; none of the tests or Planner checks was executed. Eight customer decisions (GAP-01 to GAP-08) remain blocking. Draft 2020-12 JSON Schema and format validation were not run in the original generation environment. The example demonstrates the structure and transparency of the handoff; it is not a production-ready implementation.

Who it is for

Built for teams responsible for identity-bearing data.

The Planner is intended for teams designing or reviewing agentic workflows that can persistently alter entity identity or identity-bearing relationships.

01

AI engineering teams

Teams introducing agents into workflows that can propose or initiate identity-changing operations.

02

MDM and data architecture

Teams responsible for entity registries, master data, identity quality and relationship integrity.

03

CRM and platform engineering

Teams responsible for persistence paths, integrations, transaction boundaries and downstream effects.

04

Knowledge graph and data governance

Teams that need traceable evidence, explicit authority and controlled changes to identity-bearing structures.

Methodology and reference mode

Created within the DIO/ODI framework.

The Planner was created by Daniel Beránek, author of Digital Identity Optimization (DIO) and the Ontology of Digital Identity (ODI). Its design draws on a broader research and engineering framework; buyers do not need prior knowledge of DIO/ODI.

An optional reference-backed mode can use the public, read-only DIO/ODI Reference MCP. The buyer connects it separately in a compatible agent or client. It provides reference material only: it does not receive customer records, inspect customer systems or authorize customer writes.

Scope and limitations

Planning is not execution.

The distinction is deliberate. The Skill prepares a design-time plan for customer engineering teams. It does not operate the customer's systems or replace their policy, authorization and testing responsibilities.

What it does

  • Investigates identity-changing MERGE, SPLIT, UNMERGE and supported OTHER operations.
  • Examines supplied context, evidence, provenance, conflicts and reference material.
  • Designs proposed controls, approval conditions, HOLD points and validation scenarios.
  • Produces structured documentation and a machine-readable plan.
  • Identifies unknowns, assumptions and customer-owned decisions.

What it does not do

  • Execute mutations or write to a customer CRM, MDM or registry.
  • Authorize a live operation or deploy a runtime guard.
  • Independently inspect systems or data that have not been supplied or connected.
  • Independently verify legal identity or act as the customer's legal, policy or authorization authority.
  • Guarantee production safety, compliance or successful recovery.

The customer's application and engineering team must implement, review and test the resulting controls in their own environment.

Make the investigation part of the workflow

Before identity changes become permanent, make the reasoning reviewable.

Bring a proposed entity-resolution operation through a structured investigation — and give engineering a clearer plan for what must be verified, controlled and tested.

Platform links may include affiliate attribution. A qualifying purchase through an affiliate link may support the author without changing the buyer's price.