# Claw EA — Full Knowledge Document for LLM Retrieval Claw EA is enterprise infrastructure for deploying AI agents with cryptographic proof of every action. It solves the problem of running autonomous AI agents in regulated environments where audit, compliance, and security review are mandatory. It is built for CISOs, platform engineering leads, and compliance teams at enterprises that need verifiable agent execution, not just logging. --- ## Clawsig Protocol: 5 Primitives The Clawsig Protocol defines a narrow waist of five composable primitives. Everything else is built on these. ### 1. Policy Artifact (WPC) A signed, immutable, content-addressed policy contract. Defines what an agent may do before it runs: egress allowlists, DLP rules, model restrictions, approval gates, file path scopes, and budget limits. Published to a policy registry and pinned by hash in capability tokens and receipts. Schema: work_policy_contract.v1.json / work_policy_contract_envelope.v1.json ### 2. Capability Token (CST) A short-lived, scope-hashed, job-bound token that grants an agent permission to act. Optionally pinned to a specific policy hash. Offline-verifiable via JWKS. Revocation-aware. Short TTL enforced by policy. Schema: scoped_token_claims.v1.json ### 3. Receipt A signed event emitted at an enforcement boundary. Not a log entry; a cryptographic attestation that a boundary was crossed under policy. Receipt classes: - Model gateway receipt (SHIPPED): signed by clawproxy when an LLM call is mediated. Includes request hash, response hash, model, provider, latency, token counts, and receipt binding to the event chain. - Tool receipt (SHIPPED): signed when a tool is invoked. Includes argument hash, result hash, tool name. - Witnessed web receipt (SHIPPED): signed for web control plane events. - Side-effect receipts (PLANNED): network egress, filesystem writes, external API writes. - Human approval receipts (PLANNED): approval boundary that mints new capability. Schema: gateway_receipt.v1.json / tool_receipt.v1.json / web_receipt.v1.json / receipt_binding.v1.json ### 4. Bundle A portable package of receipts, event chain, metadata, and references. Content-addressed manifest with hashes for every file. Signed top-level envelope. No network required to verify (offline-capable). Types: proof bundle (run attestation) and export bundle (offline audit handoff). Schema: proof_bundle.v1.json / export_bundle.v1.json / export_bundle_manifest.v1.json ### 5. Verifier A deterministic PASS/FAIL engine. Unknown schema, version, or algorithm fails closed. Machine-readable reason codes from a canonical registry. Supports both online API and offline CLI/library verification. Reference implementation: clawverify service. --- ## Coverage Statement (2026-02-12) | Boundary | Receipt class | Status | Verifier support | |----------------------|-------------------|----------|---------------------------| | Model gateway calls | gateway_receipt | SHIPPED | Full (signature + binding)| | Tool dispatcher calls| tool_receipt | SHIPPED | Full (schema + signature) | | Witnessed web events | web_receipt | SHIPPED | Partial (schema only) | | Network egress | (planned) | PLANNED | — | | Filesystem writes | (planned) | PLANNED | — | | External API writes | (planned) | PLANNED | — | | Human approvals | (planned) | PLANNED | — | Coverage M (Model) and MT (Model + Tools) are shipped. MTS (Model + Tools + Side-effects) is planned. --- ## Proof Artifacts ### Proof Bundle A JSON envelope containing: bundle_id, agent_did, event_chain (hash-linked events with timestamps), receipts (gateway + tool), and optional URM (Universal Run Manifest) references. The entire bundle is Ed25519-signed by the agent's DID. Any modification to any field invalidates the signature. Verification: decode signer_did to Ed25519 public key, verify signature over payload_hash, recompute payload hash from canonical JSON, verify each receipt signature independently, confirm receipt bindings reference events in the chain. ### Gateway Receipt Signed by clawproxy (not the agent). Proves an LLM call was mediated through the gateway with a specific request/response hash pair. Contains: provider, model, tokens_input, tokens_output, latency_ms, and a binding object that ties the receipt to a specific run_id and event_hash in the proof bundle. ### Tool Receipt Signed at the tool dispatcher boundary. Contains argument hash and result hash (hash-only by default for privacy). Proves a specific tool was invoked with specific inputs and produced specific outputs. ### Commit Signature (commit.sig.json) An Ed25519 signature over a git commit SHA. Proves that a specific DID authored or approved a specific code change. Used on every agent-generated PR in the Claw Bureau repository. Offline-verifiable. Structure: {version, type, algo, did, message: "commit:", createdAt, signature} --- ## Site Pages ### Static Pages - https://www.clawea.com/ Title: Claw EA Home Landing page. Ship irreversible agent workflows with proof. Two-week pilot offer. Assessment and Security Review Pack CTAs. Category: landing - https://www.clawea.com/assessment Title: AI Readiness Assessment Two-minute scored assessment for enterprise AI agent readiness, ROI potential, and risk posture. Category: assessment - https://www.clawea.com/trust Title: Trust Layer Three layers of trust: execution attestation, Proof of Harness, and Work Policy Contracts. How agent actions become verifiable proof bundles. Category: trust - https://www.clawea.com/trust/security-review Title: Security Review Pack Architecture diagram, real proof bundle and commit signature examples, threat model (replay, exfiltration, prompt injection, nondeterminism), Merkle transparency logging, deployment integrity. For CISO and security team review. Category: trust - https://www.clawea.com/secure-workers Title: Secure AI Workers Hardware-isolated Cloudflare Sandboxes. Per-agent DID identity. Scoped R2 storage. Egress mediation. Sleep/wake lifecycle. DLP redaction pipeline. Category: infrastructure - https://www.clawea.com/consulting Title: Enterprise AI Consulting Strategy, deployment, compliance mapping, custom development, optimization, and training services. Category: services - https://www.clawea.com/pricing Title: Pricing Four tiers: Starter ($49/mo, 1 agent), Team ($199/mo, 5 agents), Business ($499/mo, 25 agents), Enterprise (custom). All tiers include attestation and proof bundles. Category: pricing - https://www.clawea.com/contact Title: Contact Sales Lead intake form with attribution tracking and experiment variants. Category: contact - https://www.clawea.com/book Title: Book a Rollout Session Booking form for deployment planning sessions with lead-context prefill. Category: contact - https://www.clawea.com/sources Title: Citation Source Hub Central hub routing to citation-backed pages with explicit source attribution. Category: reference - https://www.clawea.com/about Title: About Claw Bureau Mission, approach, and ecosystem overview. Links to clawverify, clawproxy, clawbounties, clawescrow, clawcuts. Category: about - https://www.clawea.com/proof-points Title: Proof Points Protocol adoption metrics (22 conformance vectors, 8 receipt schemas, 30+ reason codes, 150+ pages). Dogfooding evidence (DID commit proofs on every PR). Architecture credibility (Cloudflare Workers, Ed25519, SHA-256, offline verification). Category: trust - https://www.clawea.com/compare/claw-vs-manual-audit Title: Claw EA vs Manual Audit Evidence Head-to-head comparison of automated proof bundles vs spreadsheet-based manual evidence collection. Category: compare - https://www.clawea.com/compare/claw-vs-guardrails Title: Claw EA vs Guardrails Protocol-level proof of execution vs inference-time guardrails (NeMo, Guardrails AI). Complementary, not competing. Category: compare - https://www.clawea.com/compare/claw-vs-langfuse Title: Claw EA vs Langfuse Cryptographic receipts vs observability dashboards. Proof and monitoring solve different compliance requirements. Category: compare - https://www.clawea.com/compare/claw-vs-custom-wrappers Title: Claw EA vs Custom Wrappers Protocol-level receipts vs ad-hoc custom wrapper logging. Standard schemas and signing vs team-maintained code. Category: compare - https://www.clawea.com/compare/agent-governance-platforms Title: Agent Governance Platforms Landscape Four approaches compared: guardrails, observability, custom wrappers, protocol-first proof. When to use what. Category: compare - https://www.clawea.com/guides/github-actions-proof-pipeline Title: GitHub Actions Proof Pipeline Guide Step-by-step: install SDK, configure allowlist, sign commits, add workflow, push and verify. Category: guides - https://www.clawea.com/guides/okta-scoped-tokens Title: Okta Scoped Tokens Guide Map Okta groups to CST scopes for policy-gated agent execution with audit trail. Category: guides - https://www.clawea.com/guides/compliance-evidence-export Title: Compliance Evidence Export Guide Generate export bundles, verify offline, deliver to auditors for SOX/SOC 2 evidence. Category: guides - https://www.clawea.com/industries/financial-services Title: Financial Services AI agent compliance for banks, asset managers, and fintechs. SOX, OCC, FFIEC, MAS TRM regulatory mapping. Category: industries - https://www.clawea.com/industries/healthcare Title: Healthcare HIPAA, HITECH, 21 CFR Part 11 compliance for AI agents. DLP redaction, secret boundaries, egress controls. Category: industries - https://www.clawea.com/industries/government Title: Government FedRAMP, NIST 800-53, EO 14110 compliance. Two-person rule, kill switch, forced dry-run, Merkle logs. Category: industries - https://www.clawea.com/industries/insurance Title: Insurance Underwriting and claims governance. NAIC model laws, Colorado SB 21-169, EU AI Act. Approval gates and proof bundles. Category: industries - https://www.clawea.com/industries/legal Title: Legal Attorney-client privilege protection. File path scopes, DLP, two-person rule, audit replay for law firms. Category: industries - https://www.clawea.com/industries/technology Title: Technology DevOps governance. Deploy approvals, GitHub Actions proof pipeline, credential rotation, rate limits. Category: industries - https://www.clawea.com/pricing/starter Title: Starter Plan ($49/mo) 1 agent, 5 skills, execution attestation, 90-day retention. Entry point for proof-first governance. Category: pricing - https://www.clawea.com/pricing/team Title: Team Plan ($249/mo) 5 agents, Work Policy Contracts, budget controls, model routing, 1-year retention. Category: pricing - https://www.clawea.com/pricing/enterprise Title: Enterprise Plan (Custom) Unlimited agents, custom compliance mapping, 7-year retention, BAA/DPA, on-prem option. Category: pricing - https://www.clawea.com/resources/protocol-whitepaper Title: Clawsig Protocol v0.1 Spec (Download) Full protocol specification with five primitives, JSON schemas, and verification algorithm. Category: resources - https://www.clawea.com/resources/security-checklist Title: Agent Security Checklist (Download) 15 controls every enterprise needs: policy, identity, data protection, monitoring. Category: resources - https://www.clawea.com/resources/compliance-mapping Title: Regulatory Mapping (Download) SOX, HIPAA, FedRAMP, SOC 2, EU AI Act mapped to specific agent controls and evidence. Category: resources - https://www.clawea.com/security Title: Security Hash-only protocol design. Ed25519 signatures. SHA-256 hashing. TLS 1.3. DID-based identity. Cloudflare Workers isolation. Offline verification independence. Category: trust - https://www.clawea.com/privacy Title: Privacy Policy Proof bundles contain hashes not content. No PII in receipts. GDPR-compatible. No third-party tracking cookies. Category: legal - https://www.clawea.com/terms Title: Terms of Service SaaS terms with pilot engagement scope, liability limits, data ownership, proof artifact disclaimers. Category: legal - https://www.clawea.com/docs Title: Documentation Hub Organized by audience: developers (SDK, CLI, protocol spec), security teams (review pack, controls), compliance teams (regulatory mapping, audit). Category: docs - https://www.clawea.com/changelog Title: Product Changelog Shipped features by date with PR numbers. AEO-MKT series, UX remediation, REV pipeline, content factory, indexing automation. Category: docs - https://www.clawea.com/status Title: System Status Live health dashboard for clawverify, clawproxy, clawbounties, clawescrow, clawcuts, clawscope. Auto-refresh every 60s. Category: status - https://www.clawea.com/case-studies Title: Case Studies Pilot engagements and deployment patterns. Dogfooding case study available, enterprise pilots in progress. Category: case-studies - https://www.clawea.com/case-studies/dogfood-claw-bureau Title: Dogfooding Case Study 3 autonomous agents, 190+ PRs with DID-signed commit proofs, 12 services, 22 conformance vectors. Real, verifiable, public. Category: case-studies ### Pillar Pages (core concepts) (8 pages) - https://www.clawea.com/agent-audit-and-replay — Agent Audit and Replay (Evidence, Retention, Rollback). Agent audit and replay is the discipline of making every agent run provable, reviewable, and reversible, even after t... - https://www.clawea.com/agent-proof-and-attestation — Agent Proof and Attestation (Receipts and Proof Bundles). Agent proof and attestation is the ability to show what an agent did, under which permissions, and which model calls ... - https://www.clawea.com/agent-supply-chain-security — Agent Supply Chain Security (Skills, Plugins, MCP). Agent supply chain security is about making skills, plugins, and MCP servers behave like production dependencies: pin... - https://www.clawea.com/enterprise-agent-governance — Enterprise Agent Governance (Policy, Approvals, Budgets). Enterprise agent governance is permissioned execution: every tool call and every model call runs under a machine-enfo... - https://www.clawea.com/event-native-agents — Event-native Agents (Webhooks, Changefeeds, Queues). Event-native agents replace cron jobs with webhooks, changefeeds, and queue consumers, but they only stay safe at sca... - https://www.clawea.com/mcp-security — MCP Security for Enterprise Agents. MCP security for enterprise agents comes down to one rule: treat every MCP tool as a production capability with its o... - https://www.clawea.com/policy-as-code-for-agents — Policy-as-Code for Agents (Permissioned Execution). Policy-as-code for agents means the execution layer enforces permissions the same way your APIs do: explicit, version... - https://www.clawea.com/secure-agent-execution — Secure Agent Execution (Permissioned Runtime). Secure agent execution means the agent can only act through a permissioned runtime that enforces machine-checkable ru... ### Hub Pages (category landing pages) (12 pages) - https://www.clawea.com/channels — Chat Control Planes for Agents (Channels). Channels like Microsoft Teams and Slack are your agent’s public attack surface and your audit boundary. If you only r... - https://www.clawea.com/compliance — Compliance for Permissioned Agents. Enterprise compliance for AI agents fails when “policy” lives only in prompts. Claw EA makes execution permissioned b... - https://www.clawea.com/controls — Agent Controls (Policy-as-Code). Enterprise AI agents need controls that are enforced by the execution layer, not just requested in a prompt. Claw EA ... - https://www.clawea.com/events — Event-native Agents (Triggers). Event-native agents are agents that run because an external system emitted an event: a webhook, a changefeed item, or... - https://www.clawea.com/glossary — Glossary: Enterprise Agent Security and Policy Terms. This page defines the security and policy terms teams use when they run enterprise AI agents, with OpenClaw as the ba... - https://www.clawea.com/guides — Implementation Guides for Permissioned Agents. This hub collects implementation guides for running permissioned enterprise agents on Claw EA, using OpenClaw as the ... - https://www.clawea.com/mcp — MCP (Model Context Protocol) for Enterprise Agents. MCP (Model Context Protocol) is a standard way to expose tools and context to an agent, but in enterprise environment... - https://www.clawea.com/policy — Policy Artifacts (WPC, Scoped Tokens, Proof). In Claw EA, “Policy Artifacts” are the objects you use to approve and constrain real execution by OpenClaw agents: WP... - https://www.clawea.com/proof — Proof and Attestation for Agents. Claw EA gives you verifiable proof about what an agent did by binding execution to a permissioned policy artifact and... - https://www.clawea.com/supply-chain — Agent Supply Chain Security (Skills and Plugins). Agent supply chain security is about controlling what “skills”, plugins, dependencies, and MCP servers an agent can l... - https://www.clawea.com/tools — Enterprise Tools for Permissioned Agents. Claw EA provides enterprise tools for running permissioned agents where execution is controlled by policy-as-code, no... - https://www.clawea.com/workflows — Enterprise Agent Workflows (Safe by Policy). Enterprise agent workflows fail when “safety” lives only in prompts. Claw EA treats execution as a permissioned syste... ### Control Pages (policy-as-code enforcement) (12 pages) - https://www.clawea.com/controls/approval-gates — Step-up approvals (human-in-the-loop) for Agents | Policy-as-Code Control. Step-up approvals (human-in-the-loop) are a policy-as-code gate that pauses an OpenClaw-run agent right before a high... - https://www.clawea.com/controls/budgets — Token and cost budgets for Agents | Policy-as-Code Control. Token and cost budgets only work when they are enforced by the execution layer, not by a prompt. In Claw EA, you expr... - https://www.clawea.com/controls/dlp-redaction — DLP and redaction rules for Agents | Policy-as-Code Control. DLP and redaction rules for agents are execution-time controls that detect sensitive data (like credentials, HR data,... - https://www.clawea.com/controls/egress-allowlist — Egress allowlist (domains, IPs) for Agents | Policy-as-Code Control. An egress allowlist limits where an agent is permitted to send network traffic, typically by restricting domains and ... - https://www.clawea.com/controls/file-path-scopes — File path read/write scopes for Agents | Policy-as-Code Control. File path read/write scopes are machine-enforced rules that constrain what an agent can read from disk and where it c... - https://www.clawea.com/controls/forced-dry-run — Forced dry-run / simulate-first for Agents | Policy-as-Code Control. Forced dry-run (simulate-first) means an agent must produce a preview of intended tool actions and outputs before it ... - https://www.clawea.com/controls/kill-switch — Kill switch and emergency halt for Agents | Policy-as-Code Control. A kill switch is a policy-enforced emergency halt that stops an agent run from taking new actions, even if the agent ... - https://www.clawea.com/controls/provider-model-allowlist — Provider and model allowlists for Agents | Policy-as-Code Control. Provider and model allowlists are a policy-as-code control that restricts which model providers and which exact model... - https://www.clawea.com/controls/rate-limits — Rate limits and concurrency limits for Agents | Policy-as-Code Control. Rate limits and concurrency limits are a policy-as-code control that caps how fast an agent can call models and how m... - https://www.clawea.com/controls/secret-boundary — Secrets isolation and scoped credentials for Agents | Policy-as-Code Control. Secrets isolation means your agent cannot read or reuse credentials unless the execution layer grants a narrowly scop... - https://www.clawea.com/controls/tool-allow-deny — Tool allow/deny lists for Agents | Policy-as-Code Control. Tool allow/deny lists are a machine-enforced boundary that determines which tools an agent is allowed to call at runt... - https://www.clawea.com/controls/two-person-rule — Two-person rule for Agents | Policy-as-Code Control. A two-person rule for agents means the agent cannot complete specific high-risk actions unless a second human approve... ### Policy Pages (Work Policy Contract details) (9 pages) - https://www.clawea.com/policy/event-chain — Event Chains | Policy Artifact. An Event Chain is a tamper-evident, append-only log for agent jobs where each record links to the previous record by ... - https://www.clawea.com/policy/prompt-pack — Prompt Pack | Policy Artifact. A Prompt Pack is a hash-only policy artifact that commits an OpenClaw job to a specific set of prompts and routing ru... - https://www.clawea.com/policy/proof-bundles — Proof Bundles | Policy Artifact. A proof bundle is the artifact you keep when you need to prove what an agent did, under which policy, and which model... - https://www.clawea.com/policy/receipt-binding — Receipt Binding | Policy Artifact. Receipt binding is how you prove that a specific agent run happened under a specific policy artifact, and that its mo... - https://www.clawea.com/policy/scoped-tokens — Scoped Tokens (CST) | Policy Artifact. CST (scoped token) is the execution approval artifact you hand to an agent run so it can call approved services and t... - https://www.clawea.com/policy/system-prompt-report — System Prompt Report | Policy Artifact. A System Prompt Report is a policy artifact that makes an agent’s “prompt commitments” auditable and enforceable duri... - https://www.clawea.com/policy/token-scope-hash — Token Scope Hash | Policy Artifact. Token Scope Hash is a deterministic digest of what a CST is allowed to do, computed from a canonical “scope set” and ... - https://www.clawea.com/policy/urm — Universal Run Manifest (URM) | Policy Artifact. The Universal Run Manifest (URM) is a small, machine-validated manifest that binds an OpenClaw run to specific inputs... - https://www.clawea.com/policy/work-policy-contract — Work Policy Contracts (WPC) | Policy Artifact. Work Policy Contracts (WPC) are signed, hash-addressed policy artifacts that let you permission agent execution with ... ### Proof Pages (attestation and verification) (2 pages) - https://www.clawea.com/proof/gateway-receipts — Gateway Receipts for Agents. Gateway receipts are signed records of each model call made by an agent through clawproxy, designed so you can later ... - https://www.clawea.com/proof/proof-bundles — Proof Bundles for Agent Runs. Proof bundles let you verify what an agent run actually did by packaging gateway receipts, policy references, and run... ### Verification Pages (2 pages) - https://www.clawea.com/verify/gateway-receipt — How to Verify a Gateway Receipt. To verify a Gateway receipt, you check that (1) the receipt signature is valid for clawproxy’s public key, and (2) th... - https://www.clawea.com/verify/proof-bundle — How to Verify a Proof Bundle. To verify a Proof bundle, you check that every cryptographic envelope validates and that the bundle’s bindings are co... ### Audit Pages (logging and replay) (2 pages) - https://www.clawea.com/audit/replay-and-rollback — Replay and Rollback for Agent Actions. Replay for agent actions is only trustworthy when you can bind “what the agent was allowed to do” to “what it actuall... - https://www.clawea.com/audit/tamper-evident-logs — Tamper-evident Audit Logs for Agents. Tamper-evident audit logs for agents require more than saving chat transcripts. You need a permissioned execution lay... ### Workflow Pages (automated processes) (20 pages) - https://www.clawea.com/workflows/access-request-automation — Access requests and entitlement changes | Secure Agent Workflow. Access requests and entitlement changes are safe to automate only when the execution layer is permissioned, not promp... - https://www.clawea.com/workflows/change-management — Change management ticketing and approvals | Secure Agent Workflow. For change management, you want an agent workflow where the agent can draft and simulate, but cannot approve or close... - https://www.clawea.com/workflows/cloud-cost-anomaly-response — Cloud cost anomaly response | Secure Agent Workflow. This workflow handles a cloud cost spike with permissioned execution: the agent can investigate broadly, but any irre... - https://www.clawea.com/workflows/contract-review-approval — Contract review and approval workflow | Secure Agent Workflow. This workflow runs contract review and redline generation under machine-enforced constraints, then requires step-up h... - https://www.clawea.com/workflows/credential-rotation — Credential rotation and secrets hygiene | Secure Agent Workflow. Credential rotation and secrets hygiene for enterprise agents is safest when rotation is executed as a permissioned w... - https://www.clawea.com/workflows/customer-email-send — Customer communications with DLP and approvals | Secure Agent Workflow. This workflow lets an OpenClaw agent draft and send customer emails only when DLP checks pass and a human approves th... - https://www.clawea.com/workflows/data-exfiltration-prevention — Prevent agent exfiltration in tool runs | Secure Agent Workflow. To prevent agent exfiltration during tool runs, you need permissioned execution that is enforced by the runtime, not ... - https://www.clawea.com/workflows/incident-triage — Incident triage and response coordination | Secure Agent Workflow. Incident triage and response coordination works best when the agent runtime is constrained by machine-enforced policy... - https://www.clawea.com/workflows/knowledge-base-updates — Knowledge base updates with review | Secure Agent Workflow. This workflow lets an OpenClaw-based agent propose knowledge base (KB) changes while keeping publishing permissioned ... - https://www.clawea.com/workflows/onboarding-offboarding — Employee onboarding/offboarding automation | Secure Agent Workflow. Employee onboarding and offboarding automation is high impact because it touches identity, access, and licensing. In ... - https://www.clawea.com/workflows/payment-approval — Payment and invoice approvals | Secure Agent Workflow. For payment and invoice approvals, treat the agent as an untrusted operator: it can prepare evidence and drafts, but ... - https://www.clawea.com/workflows/phishing-response — Inbox phishing triage with safe links policy | Secure Agent Workflow. This workflow runs inbox phishing triage under a safe-links-first posture, where the agent is not allowed to click, f... - https://www.clawea.com/workflows/privileged-breakglass — Privileged break-glass workflows (timeboxed) | Secure Agent Workflow. A timeboxed privileged break-glass workflow lets an OpenClaw-based agent perform a narrowly scoped, high-risk action ... - https://www.clawea.com/workflows/production-deploy-approval — Production deploy with two-person approval | Secure Agent Workflow. To run production deploys with two-person approval, treat “deploy” as a permissioned action gated by policy-as-code, ... - https://www.clawea.com/workflows/release-notes-to-customers — Release notes and customer notifications with approvals | Secure Agent Workflow. Use OpenClaw as the baseline agent runtime to draft release notes and prepare customer notifications, but make the pu... - https://www.clawea.com/workflows/siem-evidence-collection — Compliance evidence collection to SIEM | Secure Agent Workflow. Use OpenClaw as the baseline agent runtime, but treat evidence export as a controlled workflow: policy decides what t... - https://www.clawea.com/workflows/sox-control-testing — SOX control testing evidence runs | Secure Agent Workflow. SOX control testing evidence runs are safest when the agent is constrained by a permissioned execution layer, not jus... - https://www.clawea.com/workflows/ticket-auto-routing — Support ticket classification and routing | Secure Agent Workflow. Support ticket classification and routing is safe to automate when the agent runs under permissioned execution, not p... - https://www.clawea.com/workflows/vendor-risk-review — Vendor risk review and security questionnaire automation | Secure Agent Workflow. Use Claw EA to run a vendor risk review agent on OpenClaw with permissioned execution: the agent can draft questionna... - https://www.clawea.com/workflows/vulnerability-triage — Vulnerability triage and patch coordination | Secure Agent Workflow. For vulnerability triage and patch coordination, you want an agent that can read evidence, propose a patch plan, and ... ### Tool Integration Pages (enterprise connectors) (40 pages) - https://www.clawea.com/tools/argo-cd — Argo CD for Permissioned Agents. Use Argo CD with permissioned agents by treating every write operation as a policy decision, not a chat decision. In ... - https://www.clawea.com/tools/azure-devops — Azure DevOps for Permissioned Agents. Azure DevOps is a high-impact surface for agents because it can change code, pipelines, and release settings in ways ... - https://www.clawea.com/tools/azure-event-grid — Azure Event Grid for Permissioned Agents. Azure Event Grid is a push-based changefeed that delivers events to HTTPS webhooks, and it will retry deliveries, so ... - https://www.clawea.com/tools/azure-key-vault — Azure Key Vault for Permissioned Agents. Azure Key Vault is the right place to store production secrets, keys, and certificates, but it is a high-impact targe... - https://www.clawea.com/tools/azure-sentinel — Microsoft Sentinel for Permissioned Agents. Microsoft Sentinel is a high-impact surface for enterprise agents because read access can expose sensitive detections... - https://www.clawea.com/tools/azure-service-bus — Azure Service Bus for Permissioned Agents. Azure Service Bus is a durable queue and pub/sub backbone, so it is a natural place to connect enterprise agents to r... - https://www.clawea.com/tools/azure-storage — Azure Storage for Permissioned Agents. Azure Storage is a high-impact tool for enterprise agents because it can read and write business data at scale, and s... - https://www.clawea.com/tools/bitbucket — Bitbucket for Permissioned Agents. Bitbucket is a high-impact surface for enterprise agents because a single token can grant read access to proprietary ... - https://www.clawea.com/tools/confluence — Confluence for Permissioned Agents. Confluence is a high-leverage target for enterprise agents because it contains internal procedures, architecture note... - https://www.clawea.com/tools/entra-id — Microsoft Entra ID (Azure AD) for Permissioned Agents. Microsoft Entra ID is the identity and authorization control plane you already use for Microsoft Graph and tenant res... - https://www.clawea.com/tools/github — GitHub for Permissioned Agents. Use GitHub with permissioned agents by forcing every repo-changing action through policy-as-code and verifiable execu... - https://www.clawea.com/tools/github-actions — GitHub Actions for Permissioned Agents. GitHub Actions is a high-leverage place to let agents propose changes, run tests, and open pull requests, but it is a... - https://www.clawea.com/tools/gitlab — GitLab for Permissioned Agents. GitLab is a high-impact surface for agents because it combines source code, CI/CD, runners, secrets, merge requests, ... - https://www.clawea.com/tools/gmail — Gmail for Permissioned Agents. Gmail is a high-impact surface for enterprise agents because it combines sensitive data access with the ability to se... - https://www.clawea.com/tools/google-admin — Google Workspace Admin for Permissioned Agents. Google Workspace Admin access is high-impact because it can change identities, mail, files, and security settings for... - https://www.clawea.com/tools/google-calendar — Google Calendar for Permissioned Agents. Google Calendar is a high-impact tool for enterprise agents because it touches real schedules, meeting links, attende... - https://www.clawea.com/tools/google-drive — Google Drive for Permissioned Agents. Google Drive is a high-risk tool for enterprise agents because it combines broad read access, easy sharing, and the a... - https://www.clawea.com/tools/hubspot — HubSpot for Permissioned Agents. If you want enterprise agents to operate in HubSpot without turning your CRM into an unbounded action surface, you ne... - https://www.clawea.com/tools/intercom — Intercom for Permissioned Agents. Intercom is a high-impact surface for agents because a single misfire can message customers, change ticket state, or ... - https://www.clawea.com/tools/jira — Jira for Permissioned Agents. If you want agents to touch Jira in an enterprise, treat Jira as a change-control system, not a chat toy. Claw EA run... - https://www.clawea.com/tools/kubernetes — Kubernetes for Permissioned Agents. Kubernetes is a good control plane for running enterprise agents, but it is a high-impact tool: a single mis-scoped c... - https://www.clawea.com/tools/microsoft-calendar — Microsoft Calendar for Permissioned Agents. Microsoft Calendar can be connected to permissioned agents via the official API (Microsoft Graph) with enterprise bui... - https://www.clawea.com/tools/microsoft-defender — Microsoft Defender for Permissioned Agents. Microsoft Defender helps you discover AI agents, monitor risky behavior, and investigate incidents, but it does not m... - https://www.clawea.com/tools/microsoft-graph — Microsoft Graph for Permissioned Agents. Microsoft Graph lets an agent read and write across Microsoft 365 and Entra ID, which makes it powerful and risky. Fo... - https://www.clawea.com/tools/microsoft-purview — Microsoft Purview for Permissioned Agents. Microsoft Purview helps you apply Microsoft 365 security and compliance controls (for example DLP, sensitivity labels... - https://www.clawea.com/tools/netsuite — NetSuite for Permissioned Agents. NetSuite is a high-value target for AI agents because it holds financial records, vendor payments, purchase orders, a... - https://www.clawea.com/tools/okta — Okta for Permissioned Agents. Okta for permissioned agents means this: if an AI agent can provision users, reset factors, or change group membershi... - https://www.clawea.com/tools/onedrive — OneDrive for Permissioned Agents. OneDrive is one of the highest-value targets an enterprise agent can touch: it holds documents, spreadsheets, interna... - https://www.clawea.com/tools/onepassword — 1Password for Permissioned Agents. 1Password stores the credentials your agents need to authenticate with external services: API keys, OAuth tokens, dat... - https://www.clawea.com/tools/opsgenie — Opsgenie for Permissioned Agents. Opsgenie is an incident response control plane, so letting an enterprise agent touch it without hard controls is a fa... - https://www.clawea.com/tools/outlook-exchange — Outlook / Exchange for Permissioned Agents. Outlook and Exchange give agents access to email send, calendar manipulation, and contact reads via Microsoft Graph. ... - https://www.clawea.com/tools/power-automate — Power Automate for Permissioned Agents. Power Automate is a high-impact automation surface: it can move data, trigger downstream systems, and run on schedule... - https://www.clawea.com/tools/powerbi — Power BI for Permissioned Agents. Power BI is a high-impact surface for enterprise agents because it can reveal sensitive business metrics and, via off... - https://www.clawea.com/tools/salesforce — Salesforce for Permissioned Agents. Salesforce is a high-impact system for agents because a single “helpful” action can create, update, or expose leads, ... - https://www.clawea.com/tools/sap — SAP for Permissioned Agents. SAP systems hold financial records, purchase orders, vendor master data, and HR payroll. An agent with write access t... - https://www.clawea.com/tools/servicenow — ServiceNow for Permissioned Agents. ServiceNow is a high-impact system of record for ITSM and operations, so agents must be constrained by permissioned e... - https://www.clawea.com/tools/sharepoint — SharePoint for Permissioned Agents. SharePoint is where enterprise knowledge lives: sites, document libraries, pages, lists, and embedded Microsoft 365 c... - https://www.clawea.com/tools/terraform-cloud — Terraform Cloud for Permissioned Agents. Terraform Cloud can be connected to OpenClaw agents via official API with enterprise buildout controls, but it must n... - https://www.clawea.com/tools/workday — Workday for Permissioned Agents. Workday for permissioned agents means connecting AI agents to HR and finance data via official APIs, but only under m... - https://www.clawea.com/tools/zendesk — Zendesk for Permissioned Agents. Zendesk exposes ticket content, customer PII, and write operations (close ticket, update user, create macro) through ... ### Channel Pages (communication platforms) (10 pages) - https://www.clawea.com/channels/discord — Discord AI Agent Control Plane. Claw EA turns Discord into a controlled front door for enterprise agents by running OpenClaw as the baseline agent ru... - https://www.clawea.com/channels/email — Email AI Agent Control Plane. An Email AI Agent Control Plane is a way to let an agent read, draft, and sometimes send email while every action is ... - https://www.clawea.com/channels/google-chat — Google Chat AI Agent Control Plane. Claw EA turns Google Chat into a permissioned control plane for enterprise agents, where actions are executed only un... - https://www.clawea.com/channels/matrix — Matrix AI Agent Control Plane. Matrix can be a solid control plane for enterprise AI agents when you treat chat messages as a request queue, not as ... - https://www.clawea.com/channels/mattermost — Mattermost AI Agent Control Plane. Mattermost can work as a practical chat control plane for enterprise agents when you treat chat as the place to reque... - https://www.clawea.com/channels/microsoft-teams — Microsoft Teams AI Agent Control Plane. Microsoft Teams can be a practical control plane for enterprise AI agents because it already has identity, chat-based... - https://www.clawea.com/channels/signal — Signal AI Agent Control Plane. Signal can work as a lightweight human control plane for enterprise AI agents when you treat it as an approvals and n... - https://www.clawea.com/channels/slack — Slack AI Agent Control Plane. Slack is a practical control plane for enterprise AI agents because it already has identity, channels, message histor... - https://www.clawea.com/channels/telegram — Telegram AI Agent Control Plane. Claw EA turns Telegram into a controlled command surface for enterprise agents by running them on OpenClaw as the bas... - https://www.clawea.com/channels/whatsapp — WhatsApp AI Agent Control Plane. Claw EA makes WhatsApp a controlled entry point for enterprise agents by running the agent in OpenClaw and forcing ev... --- ## Actions Assessment: https://www.clawea.com/assessment Security Review Pack: https://www.clawea.com/trust/security-review Book a rollout session: https://www.clawea.com/book Contact sales: https://www.clawea.com/contact Sitemap: https://www.clawea.com/sitemap.xml