CClarivyAI Decision Visibility

AI Agent Integrations

Agent consumption contract · Last updated 2026-06-23

Direct answer. Clarivy is designed so AI agents can ingest an audit, verify every recommendation against raw JSON evidence, and create downstream work without inventing context. Enterprise Monitor includes dedicated deliverables for enterprise AI agent employees, not just human summaries.

What Clarivy gives an AI agent

FilePurposeAgent rule
agent-bundle/manifest.jsonMachine-readable inventory, action graph, evidence map, verification plan, adapter notes, memory delta, and handoff notes.Use this as the entry point.
ai-employee-brief.mdStructured Markdown with stable finding_id, evidence_id, and action_id.Summarize by ID; do not paraphrase unsupported claims.
raw-data-index.mdIndex of every endpoint-query datapoint and linked raw JSON.Verify evidence before recommending edits.
Raw JSON evidencePrompt, endpoint, sampled_at, model metadata, response text, citations, and error state where applicable.Treat current-run raw JSON as the evidence source.
/llms.txtPublic facts about Clarivy's current product status, pricing, endpoint count, and limits.Use it when describing Clarivy itself.
/agent-feed/Machine-readable merchant profile, evidence policy, offer boundaries, and agent-safe comparison rules.Use it before routing an agent to scope review or a commercial handoff.

Enterprise Monitor agent package

Enterprise Monitor adds a stricter operational package for enterprise AI agent employees. These files are designed for planning, verification, and handoff; they do not remove human approval gates.

FilePurposeApproval boundary
agent-action-backlog.jsonPrioritized action records with owner hints, risk level, due window, finding IDs, and evidence IDs.Actions can be drafted by an agent, but high-risk records keep approval_required: true.
agent-bundle/evidence-map.jsonMachine-readable mapping from findings and actions to raw evidence files.Agents must verify current-run evidence before editing customer systems.
agent-bundle/verification-plan.jsonChecklist of raw JSON files and uncertainty flags to inspect before action.Low-confidence or missing evidence must remain visible in handoff notes.
agent-bundle/memory-delta.jsonChange summary versus prior Clarivy runs for the same customer subject.Memory is context only; current-run claims require current-run evidence.

See the Enterprise Monitor sample package for a public mock of the monthly report, weekly pulse memo, agent manifest, and agent action backlog. When Monthly Improvement Plan is scoped, the same backlog is curated into owner-ready work packages for human owners and enterprise AI agent employees; it remains evidence-bound and does not guarantee rankings, traffic, revenue, or answer share.

Native ecosystem compatibility

These are compatibility notes for file-based agent workflows. They are not vendor certifications or marketplace approvals.

Agent ecosystemStatusBest-fit Clarivy handoff
Claude CodeFile-compatibleRead the Markdown brief and manifest, then use raw-data-index links to verify evidence before editing content or docs.
CodexFile-compatibleUse stable action IDs as implementation tasks, commit scoped fixes, and cite raw JSON evidence in handoff notes.
OpenCodeCompatible patternUse the same manifest and Markdown brief workflow; adapter-specific examples still need manual verification.
WorkBuddyNative ecosystem priorityTarget workflow is business-ops task assignment from action_id plus evidence verification from raw-data-index.
HermesNative ecosystem priorityTarget workflow is reading the manifest, extracting work packages, and preserving evidence links during handoff.
Pi and conversational assistantsReader-compatibleUse the human report plus AI-readable brief for explanation and stakeholder summarization, not autonomous edits.
Chinese agent workflowsReader-compatibleUse zh/llms.txt, Chinese FAQ/methodology summaries, and the same evidence files; English remains canonical for product facts.

Agent workflow

  1. Load scope. Read the manifest first and identify audit subject, product tier, prompt set, and file inventory.
  2. Read findings. Use the Markdown brief to map findings to action IDs and evidence IDs.
  3. Verify evidence. Open the raw-data index and linked raw JSON before changing customer content.
  4. Plan work. Turn action IDs into scoped tasks; keep evidence IDs attached to each task.
  5. Respect privacy. Do not move contact details, billing data, raw responses, or raw JSON into long-lived memory unless the customer explicitly authorizes that storage.
  6. Report uncertainty. If an endpoint errored, a response is missing, or a finding is low confidence, preserve that status instead of smoothing it away.

Privacy boundary for agents

Repeat-audit memory is designed for continuity, not surveillance. It may include prior run summaries, prior GEO scores, recurring findings, previous actions, and open loops for the same customer subject. It excludes email, contact names, addresses, billing data, tax ids, raw response text, and raw JSON payloads. Customers can opt out or request deletion.

What agents must not infer

FAQ

Can AI agents consume Clarivy audit output directly?

Yes. Clarivy audits include an AI-readable Markdown brief, raw-data index, raw JSON evidence, and Agent Bundle Manifest. Agents should verify recommendations against raw JSON before taking action.

Does Clarivy store raw responses in repeat-audit memory?

No. Repeat-audit memory excludes raw response text, raw JSON payloads, contact details, billing data, tax ids, and addresses. It stores sanitized historical summaries for same-customer continuity only.