# Pointer — Evidence for AI-to-AI Readiness

## What problem are we solving today?

AI can find your website. Can it do business with you—within your rules?

Most readiness scans stop when a machine can discover and read a page. Pointer tests what happens next: can an authorized agent find the right action, understand the rules, complete a bounded task, and return evidence another system can verify?

Pointer defines the measurement and proof requirements inside 3Dogs Nexus. It is not a certification, and no result is released without human approval.

## The gap

A machine-readable site is not the same as a machine-operable business.

1. **Found is not understood.** An agent may reach the page yet choose the wrong product, policy, contact, or next action.
2. **Understood is not authorized.** An endpoint may exist without clear scopes, identity, consent, limits, or human escalation.
3. **Completed is not proved.** A successful response is weak evidence unless the inputs, authority, result, and recovery path can be confirmed in a separate evaluator run.

## The Pointer evidence chain

Discovery is the starting line. Operational proof is the test.

1. **Discover:** locate the authoritative surface, identity, policies, and supported tasks.
2. **Execute — L1:** complete a bounded, non-destructive task against a declared contract.
3. **Govern — L2:** enforce identity, authority, consent, limits, audit, and human control.
4. **Recover — L3 gate:** deny, time out, revoke, and resolve partial failure within documented contract limits.
5. **Confirm — L3:** enable a separate evaluator run to repeat the task and confirm equivalent evidence.

A failure in a critical layer caps the outcome; strengths elsewhere cannot average it away.

The public ladder is cumulative: L1 Executable → L2 Governed → L3 Confirmed. L3 also requires every applicable recovery control to pass. A “separate evaluator” did not produce the original evidence, but may be operated by the same organization. Independent external confirmation is a different claim and must be evidenced separately.

## Evidence states

- **Confirmed:** repeated in a separate evaluator run.
- **Observed:** captured, not yet confirmed.
- **Claimed:** declared without sufficient proof.
- **Not evidenced:** required proof was absent.
- **Contradicted:** evidence conflicts with the claim.
- **Not applicable:** excluded with a documented reason.

The deliverable is a claim-by-claim evidence record containing, at minimum, the claim ID, subject and environment, scope, source URLs and content fingerprints, observation and expiry dates, positive and negative results, status, limitations, and supersession history.

Under the candidate method, a public checklist score is not treated as proof of operational readiness. The method defines hard-gate conditions including an advertised surface not observed live or authorization not enforced; fake success or deceptive soft-404s—error pages returned as HTTP success; failure or recovery outside documented limits; missing, unbound, or unverifiable audit evidence; and material claims a separate evaluator cannot confirm. Documentation can prove a representation defect. Availability, execution, and authorization require a request against the declared live surface or equivalent controlled runtime evidence. Consequential production writes require an authorized sandbox, canary, or attested runtime evidence.

## Test the engagement that matters

- **Revenue path:** Can an agent identify fit, obtain accurate commercial terms, submit a bounded inquiry, and receive a verifiable next step without losing attribution or consent?
- **Service path:** Can an agent choose the correct service, supply required context, respect data boundaries, and route the request to an accountable human or system?
- **Support path:** Can an agent retrieve authorized information, respect scope limits, recover safely, and preserve the audit trail through escalation?

## Assessment sequence

1. Define the business problem and bounded task.
2. Inventory the public surfaces, contracts, policies, and claims.
3. Challenge normal, denied, malformed, replay, and failure cases.
4. Confirm material claims with a separate evaluator run.
5. Prioritize fixes by engagement value, control risk, and effort.
6. Keep implementation and release explicitly human-gated.

The assessment does not change production state. If a consequential action cannot be challenged within an authorized sandbox or other safe boundary, it is marked not tested this round—not forced. Implementation always requires separate authorization.

Every eligible no-fee measurement must also be subject-runnable: it includes complete findings, failure reasons, exact acceptance tests, method version, scope, configuration, test vectors, result derivation, rerun instructions, and evidence digests. The assessed organization can fix the problem and rerun the same measurement without paying 3Dogs. Paid work may cover additional interpretation, prioritization, remediation, or implementation, but cannot be required to understand or self-fix the result. Payment cannot improve the result, waive a gate, or control publication or appeal.

## Useful baselines, harder questions

Public discovery scanners remain useful starting-point diagnostics. Pointer retains those checks and adds requirements for bounded execution, governance, recovery, and confirmation without making claims about another product's complete current feature set.

## 3Dogs current posture

Cloudflare's Agent Readiness web UI reported 100/100 and “Level 5 Agent-Native” for `https://3dogs.ai` in an artifact captured on August 5, 2026 at 23:46 PT; that artifact does not expose its collector version. Cloudflare's public MCP scanner, version 1.0.0, rechecked the same origin with profile `all` at `2026-08-08T21:08:51Z` and returned Level 5/5 Agent-Native. The current programmatic result does not return an overall 100-point number, so Pointer does not translate one label into the other.

Cloudflare's result covers public discoverability, content accessibility, bot controls, and capability discovery. It does not establish Pointer's authorization-declaration, honest-error, bounded-execution, governance, recovery, or confirmation requirements.

The decisive self-test was not another document review. The 100/100 result coexisted with an advertised root commerce API, MCP endpoint, and documentation route that live requests did not support. Multiple reviews initially read the declarations and misclassified the missing commerce surface as an authorization defect. Calling the declared endpoints corrected the diagnosis: the advertised surface was not observed. Pointer now treats that sequence as a foundational control—documents can prove what was represented; availability, execution, and authorization require appropriate runtime evidence.

**Pointer status: `NOT_RANKABLE`. Third-party discovery evidence: `DISCOVERY_ONLY`.**

Method `0.2.1-candidate` · human approval required.

**Summary issuance state:** `POINTER SUMMARY · 3DOGS.AI · NOT_SHAREABLE · NOT_RANKABLE · METHOD 0.2.1-CANDIDATE · REASON NO POINTER OPERATIONAL EVIDENCE BUNDLE ISSUED`

Discovery signals present. A third-party discovery scan reported 100/100; Pointer classifies that as insufficient evidence of anything operational. 3Dogs does not claim a self-awarded certification, a perfect operational score, or an ordinal company ranking.

A future shareable label must bind the evidence digest, limits, expiry, and named human release-decision reference. If any required field is missing, the label remains `NOT_SHAREABLE`.

## Next action

Give Pointer one job that matters. Choose one journey—a quote request, service request, or support case—and name the owner who can approve testing. The future no-fee measurement must return complete findings, exact acceptance tests, and everything needed to rerun after a self-fix.

**Current release state:** the subject-runnable measurement bundle is not yet released. Pointer will not issue a shareable result at any assurance level, publish a ranking, or sell remediation against method 0.2.1 until that bundle exists and the protocol-truth and soft-404 hard gates close on the live site. Internal diagnostics are not Pointer results. A qualified DEV pilot request identifies the business problem, bounded task, authorized actor, allowed inputs, prohibited actions, expected outcome, failure expectations, evidence requirements, human escalation, and evidence freshness window. No implementation or public release is automatic.

- [Read the machine-readable methodology](/pointer/methodology.json)
- [Join the DEV validation cohort](/enterprise/?intent=pointer-dev-pilot#briefing)
- [Review the historical scan artifact and its limits](/pointer/agent-readiness/)