AAgentProof

Methodology

AgentProof Capability Zones

A readiness lens that classifies agents by autonomy, data access, and action authority — so you choose the right controls for the agent you actually have.

Three zonesControls by zoneSource-backedAgentProof-defined
Zone 1Lower risk

Informational Agents

Agents that answer questions, summarise content, and guide users — without changing systems of record.

Risk profile: Lower operational risk. Higher reputation risk if it confidently invents answers.

Examples

  • Internal documentation chatbot
  • Onboarding Q&A assistant
  • Customer support FAQ helper

What good design includes

  • A written scope statement of what the agent will and will not answer
  • Source-attribution surfaced to the user on every answer
  • A graceful refusal pattern when context is missing or uncertain
  • A calm tone — neutral, not flattering, not alarming

Questions AgentProof will ask

  • What is this agent's documented purpose?
  • Which knowledge sources is it allowed to read?
  • How does it behave when asked something outside scope?

Moves to a higher zone when: The day it starts drafting customer-facing content, suggesting actions, or reading personal/regulated data, it has effectively moved to Assisted Work.

Zone 2Medium risk

Assisted Work Agents

Agents that use organisational data and help complete tasks — but require a human to commit changes.

Risk profile: Medium operational risk. Quality of recommendations becomes visible quickly; data handling discipline becomes important.

Examples

  • Sales follow-up drafting assistant
  • Internal ops triage helper
  • Research aggregation agent

What good design includes

  • Clear human-in-the-loop step before any commit
  • Provenance shown on every draft (sources + context window)
  • Data classification and access controls applied at the source, not at the prompt
  • Documented behaviour when records or context are missing

Questions AgentProof will ask

  • Which data sources can the agent read?
  • Is the human-in-the-loop step explicit and tested?
  • Where does the agent surface its sources to the user?

Moves to a higher zone when: Any path that lets the agent commit a change — updating a record, triggering a workflow, sending an outbound message — moves it to Action-taking.

Zone 3Higher risk

Action-Taking Agents

Agents that trigger workflows, update records, or make decisions that affect business outcomes.

Risk profile: Higher operational risk. Mistakes touch customers, partners, finance, or systems of record.

Examples

  • Order-routing agent that updates ERP records
  • Service-ticket agent that creates and assigns tickets
  • Internal finance agent that reconciles or proposes journal entries

What good design includes

  • Tight scope on which actions the agent can reach
  • Idempotent action wiring (safe to retry without duplicating)
  • Per-action audit trace with no PII or token leakage
  • Tested rollback / escalation path on every failure mode
  • Explicit human approval gate on the highest-impact actions

Questions AgentProof will ask

  • Which actions can this agent reach? What CAN'T it reach?
  • Are write/workflow actions idempotent?
  • Where is the human approval gate? How is it enforced?
  • What is the rollback if an action goes wrong?

Moves to a higher zone when: Action-taking is the top zone here. Beyond this, agents enter regulated territory (e.g. agents acting on behalf of customers in regulated industries) and require dedicated programme-level governance.

At-a-glance comparison

A side-by-side look so you can place your agent in seconds.

DimensionInformational AgentsAssisted Work AgentsAction-Taking Agents
Can change records?NoNo (drafts only)Yes — by design
Reads org data?Published knowledge onlyYes, scoped per userYes, scoped + audited
Human in the loop?Refusal patterns + scopeOn consequential draftsOn every consequential action
Top control familyPurpose & scopeData access & sensitivityAction authority
Top evidenceRefusal transcriptsProvenance on draftsAudit trace + rollback rehearsal

How to classify your agent

Walk these four questions in order. Stop at the first Yes — that's the zone.

  1. 1. Can the agent commit a change to a system of record without a human confirming?

    Yes → Action-TakingNo → (continue to next question)
  2. 2. Can the agent send outbound messages, create tickets, or trigger workflows on its own?

    Yes → Action-TakingNo → (continue to next question)
  3. 3. Does the agent read organisational data, drafts, or records to help the user do their job?

    Yes → Assisted WorkNo → (continue to next question)
  4. 4. Does the agent recommend a next action the user then takes manually?

    Yes → Assisted WorkNo → Informational

Why this matters before go-live

Most agent incidents trace back to applying lower-zone controls to a higher-zone agent. Pinning the capability zone before wiring tools is the cheapest control you have — and it's what AgentProof asks you to do in step 2 of the readiness assessment.

Ready to assess your own agent?

Start the free assessment to apply this guidance to a real agent. No payment. No public registration required.

A few honest things about AgentProof

  • · AgentProof is a readiness assessment, not an official audit.
  • · Every recommendation cites the intelligence pack version it came from.
  • · Intelligence updates go through a human review gate.
  • · AgentProof does not speak on behalf of Microsoft or any vendor.