Controlled drafting · Agent concept

Controlled Drafting Agent

Prepare reviewable drafts from approved evidence while surfacing unsupported claims and unresolved requirements.

AgentConcept0.1.0-concept
Nothing in this preview is executable and no credentials are issued. This record is Concept — documentation preview only

Overview

01

When to use it

Check that it fits before you look at the detail.

Consider this when

  • Accept drafting requirements and an approved evidence set.
  • Create draft sections linked to supporting evidence.
  • Flag unsupported claims and unresolved requirements.

Do not use it to

  • Export or send an unreviewed draft.
  • Make commitments, approvals, or representations of unsupported capability.
  • Use evidence that the caller did not approve.

Who this is for

Technical evaluatorsInstitutional buyersImplementation partnersQualified reviewers

A team needs a draft assembled from an approved evidence set without hiding unsupported claims or bypassing review.

Assumes: Ability to inspect structured outputs, evidence, limitations, and the stated human-review boundary.

02

Who decides what

What this concept may decide on its own, and what it may not.

A person decides

A named reviewer approves the evidence mapping, draft content, and any external use.

Drafting assistance does not transfer accountability for claims, commitments, or approvals.

It is not for

  • Unreviewed external communication
  • Automatic commitment or approval
  • Unsupported capability claim
03

What you get back

The shape of the exchange, and what happens when it is not sure.

You send
example_idrequirementsapproved_evidencedrafting_instructionsprohibited_claim_rules
You receive
example_idstatusdraft_sectionsunsupported_claim_flagsunresolved_requirementsapproval_stateexternal_export_allowed

Shape taken from the synthetic supported answer example. It is not a stable contract.

Evidence

Each material draft section is designed to identify the approved evidence used.

Uncertainty

Missing requirements and unsupported claims remain visible rather than being silently completed.

draft sectionsevidence linksunsupported-claim flagsunresolved requirementsapproval state

Continue with the evidence you need.

Information contract

Reference

No base path, method, or schema is validated. The fields below describe intended information needs, not a stable contract.

FieldTypeConstraint
requirementsarrayNamed sections or requirements to address.
approved_evidencearrayEvidence identifiers that the workflow may use.
drafting_instructionsobjectAudience, format, tone, and boundaries.
prohibited_claim_rulesarrayClaims the draft must not make.
template_structureobjectApproved section order or response template.

Workflow

Produce a controlled draft from approved evidence and route it through explicit review.

Context

The caller provides requirements and an approved source set.

Agent work

The concept produces evidence-linked output and surfaces uncertainty.

Approval

A qualified reviewer interprets, approves, and decides any next action.

Approval points

  • review of evidence mapping
  • approval before export or external use

Outputs

draft sectionsevidence linksunsupported-claim flagsunresolved requirementsapproval state

Each material draft section is designed to identify the approved evidence used.

Error and limit states

StateMeaning
invalid_inputRequired input is missing or malformed.
unsupported_requestThe request falls outside the documented capability or human decision boundary.
unavailable_sourceA required source or supplied representation is unavailable.
review_requiredQualified review is required before interpretation, decision, commitment, or external use.
service_unavailableReserved for a later executable interface; not applicable to this documentation preview.

Data handling is not defined

Do not send production client data, confidential documents, credentials, or secrets through the public preview.

storageNot yet defined
retentionNot yet defined
loggingNot yet defined
deletionNot yet defined

Accepted data classes

  • Synthetic or intentionally generic data for public examples

Access

AvailabilityDocumentation preview only
EligibilityDevelopers, technical evaluators, institutional buyers, and implementation partners may discuss a bounded use case.
OnboardingNo credentials, SLA, pricing, or production integration are offered in V1.
Contact routeEmail me
Synthetic evaluation set

Evidence

Each scenario is fictional or intentionally generic. Together they show a supported answer and the three ways this concept declines to give one — invalid input, abstention, and escalation to human review. No live request is sent.

Supported answer

Draft a reviewable implementation note from approved fictional evidence

Demonstrates drafting from an approved evidence set with an explicit review gate.

Request

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-happy-path",
  "requirements": [
    {
      "id": "REQ-1",
      "text": "Describe the planned review step."
    }
  ],
  "approved_evidence": [
    {
      "evidence_id": "SYN-EVID-001",
      "text": "A named reviewer checks each draft before external release.",
      "source_label": "Example Workflow Note"
    }
  ],
  "drafting_instructions": {
    "format": "short implementation note",
    "tone": "plain language"
  },
  "prohibited_claim_rules": [
    "Do not claim production availability.",
    "Do not add commitments not present in approved evidence."
  ]
}

Response

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-happy-path",
  "status": "draft_ready_for_review",
  "draft_sections": [
    {
      "section_id": "SEC-1",
      "text": "Each draft is checked by a named reviewer before it is released externally.",
      "evidence_links": [
        "SYN-EVID-001"
      ]
    }
  ],
  "unsupported_claim_flags": [],
  "unresolved_requirements": [],
  "approval_state": "review_pending",
  "external_export_allowed": false
}
Invalid input

Reject drafting without approved evidence

Shows that the agent does not invent claims when evidence is absent.

Request

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-invalid-input",
  "requirements": [
    {
      "id": "REQ-1",
      "text": "Describe delivery capability."
    }
  ],
  "approved_evidence": [],
  "drafting_instructions": {
    "format": "proposal paragraph"
  },
  "prohibited_claim_rules": []
}

Response

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-invalid-input",
  "status": "invalid_input",
  "error": {
    "code": "APPROVED_EVIDENCE_REQUIRED",
    "message": "Provide at least one approved evidence item or mark the requirement unresolved.",
    "field": "approved_evidence"
  },
  "approval_state": "blocked"
}
Abstains

Flag a service-level claim that is not in the approved evidence

Demonstrates abstention on unsupported commercial commitments.

Request

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-abstention",
  "requirements": [
    {
      "id": "REQ-1",
      "text": "State the promised response time."
    }
  ],
  "approved_evidence": [
    {
      "evidence_id": "SYN-EVID-002",
      "text": "The team discusses support expectations during pilot scoping.",
      "source_label": "Example Pilot Note"
    }
  ],
  "drafting_instructions": {
    "format": "one sentence"
  },
  "prohibited_claim_rules": [
    "Do not invent an SLA or response time."
  ]
}

Response

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-abstention",
  "status": "completed_with_unresolved_requirements",
  "draft_sections": [],
  "unsupported_claim_flags": [
    {
      "requirement_id": "REQ-1",
      "reason": "The approved evidence does not state a response-time commitment."
    }
  ],
  "unresolved_requirements": [
    "Confirm whether an approved response-time commitment exists."
  ],
  "approval_state": "blocked"
}
Human review

Block external release until a named approver reviews the draft

Shows the approval point that remains outside automation.

Request

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-human-review",
  "requirements": [
    {
      "id": "REQ-1",
      "text": "Prepare a client-facing delivery statement."
    }
  ],
  "approved_evidence": [
    {
      "evidence_id": "SYN-EVID-003",
      "text": "The proposed pilot scope will be confirmed after technical and privacy review.",
      "source_label": "Example Scope Note"
    }
  ],
  "drafting_instructions": {
    "format": "client-facing statement"
  },
  "prohibited_claim_rules": [
    "Do not represent proposed scope as approved."
  ]
}

Response

Synthetic JSON
{
  "example_id": "controlled-drafting-agent-human-review",
  "status": "review_required",
  "draft_sections": [
    {
      "section_id": "SEC-1",
      "text": "The proposed pilot scope remains subject to technical and privacy review.",
      "evidence_links": [
        "SYN-EVID-003"
      ]
    }
  ],
  "unsupported_claim_flags": [],
  "unresolved_requirements": [
    "Assign the named approver."
  ],
  "approval_state": "named_approver_required",
  "external_export_allowed": false
}

What this record does not yet state

These facts have no value yet. They are listed rather than hidden, so the gap is visible before anyone relies on the record.

FactGroup
Named ownerLifecycle
Operational contract reviewLifecycle
Last review dateLifecycle
StorageTrust
RetentionTrust
LoggingTrust
DeletionTrust
Allowed toolsTechnical
Memory and persistenceTechnical

Provenance

SourceScopeResult
SRC-REQ-001Purpose, input/output categories, proof requirement, examples, boundaries, and release posture.Verified against supplied specification
SRC-CAND-DRAFTING-001Executable contract, source behaviour, supported limits, and operational evidence.Defer

Source products

ProductSourceVerification
RFP, credit-paper, or comparable controlled-drafting workflowSRC-CAND-DRAFTING-001Not yet supplied
Version record

0.1.0-concept

Initial concept record derived from the approved content specification.

No compatibility commitment

No stable operational contract or backward-compatibility commitment exists.

Last reviewedNever reviewed
Content aligned12 Aug 2026

Publication blockers

  • Controlled-drafting workflow not supplied
  • Approval and export controls not validated
  • Owner and reviewer not assigned
  • Data-handling posture not defined
Getting in touch

Discuss a use case

Tell me enough to work out whether this fits — but please don’t send anything confidential.

  1. 1Start with the record

    Each record already says what it does, where it needs a person to decide, how it behaves when something goes wrong, and what I haven’t settled yet. Nothing is held back for a conversation.

    Open the catalogue
  2. 2Ask a specific question

    Tell me the decision or the piece of work you want help with, who needs to check the results before anyone acts on them, and anything that limits how your data can be handled.

    Email me
  3. 3Run it yourself

    Not yet. Nothing here runs, no keys are issued, and I don't accept real data — so there is nothing to give you access to.

Please don’t send passwords, API keys, client data, or confidential documents.