<?xml version='1.0' encoding='utf-8'?>
<rss version="2.0"><channel><item><title>The ERP Review Packet Is the Manager’s New Work Surface</title><link>https://melverick.com/blog/erp-review-packet-manager-work-surface/</link><guid isPermaLink="true">https://melverick.com/blog/erp-review-packet-manager-work-surface/</guid><description>When an AI agent proposes an ERP write, managers need a decision-ready review packet with evidence, impact, exceptions, exposure, and a reversal path.</description><pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Your AI Agent Needs a Job Description, Not a Personality</title><link>https://melverick.com/blog/ai-agent-job-description-not-personality/</link><guid isPermaLink="true">https://melverick.com/blog/ai-agent-job-description-not-personality/</guid><description>Before a persistent AI agent gets access to your ERP, CRM, email, or documents, define its owner, outcomes, decision rights, evidence, stop conditions, and review cadence.</description><pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Skills Need a Registry Before They Become Organisational Infrastructure</title><link>https://melverick.com/blog/skills-need-a-registry-before-organisational-infrastructure/</link><guid isPermaLink="true">https://melverick.com/blog/skills-need-a-registry-before-organisational-infrastructure/</guid><description>A practical skill-register framework for SMEs turning repeatable AI instructions into governed organisational infrastructure.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>A Digital Coworker Needs a Job Description, Not Just a Prompt</title><link>https://melverick.com/blog/digital-coworker-managed-identity-job-description/</link><guid isPermaLink="true">https://melverick.com/blog/digital-coworker-managed-identity-job-description/</guid><description>Before giving an AI agent access to business systems, define its job, permissions, evidence requirements, cost ceiling, escalation path, and stop conditions.</description><pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Before Your AI Agent Acts, Add a Policy Checkpoint</title><link>https://melverick.com/blog/policy-checkpoint-between-ai-reasoning-and-execution/</link><guid isPermaLink="true">https://melverick.com/blog/policy-checkpoint-between-ai-reasoning-and-execution/</guid><description>A practical permission model for deciding what AI agents may read, recommend, write, transact, approve and reverse inside SME workflows.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>The Enterprise AI Stack Is Not One Model</title><link>https://melverick.com/blog/enterprise-ai-stack-context-orchestration-skills-controls/</link><guid isPermaLink="true">https://melverick.com/blog/enterprise-ai-stack-context-orchestration-skills-controls/</guid><description>A practical five-part blueprint for moving AI from chat to governed execution: trusted context, orchestration, reusable skills, controls, and recovery.</description><pubDate>Wed, 23 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><item><title>Your Meeting Agent Is Not Finished Until the CRM Changes</title><link>https://melverick.com/blog/meeting-agent-not-finished-until-crm-changes/</link><guid isPermaLink="true">https://melverick.com/blog/meeting-agent-not-finished-until-crm-changes/</guid><description>A practical five-step operating pattern for turning AI meeting notes into governed CRM updates, qualified next actions, and an auditable sales workflow.</description><pubDate>Tue, 22 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><item><title>A Safe Prompt Cannot Fix an Unsafe Agent Environment</title><link>https://melverick.com/blog/safe-prompt-cannot-fix-unsafe-agent-environment/</link><guid isPermaLink="true">https://melverick.com/blog/safe-prompt-cannot-fix-unsafe-agent-environment/</guid><description>Why SME agent safety starts with containment, least privilege, approval gates, evidence, and a tested stop procedure—not another instruction in the prompt.</description><pubDate>Mon, 21 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><item><title>Before Your AI Agent Can Pay, Give It an Agent Passport</title><link>https://melverick.com/blog/before-ai-agent-can-pay-agent-passport/</link><guid isPermaLink="true">https://melverick.com/blog/before-ai-agent-can-pay-agent-passport/</guid><description>A practical agent-passport template for controlling identity, delegated authority, spending limits, approvals and revocation in SME payment and procurement workflows.</description><pubDate>Sun, 20 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><item><title>A Sandbox Label Will Not Contain Your AI Agent</title><link>https://melverick.com/blog/ai-agent-sandbox-is-not-a-security-boundary/</link><guid isPermaLink="true">https://melverick.com/blog/ai-agent-sandbox-is-not-a-security-boundary/</guid><description>A practical containment-test framework for SME leaders deploying AI agents with access to networks, credentials, CRM, ERP, finance, or production systems.</description><pubDate>Sat, 19 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><item><title>Before You Pay for AI Agents, Define an Approved Unit of Work</title><link>https://melverick.com/blog/define-approved-unit-of-work-before-paying-for-ai-agents/</link><guid isPermaLink="true">https://melverick.com/blog/define-approved-unit-of-work-before-paying-for-ai-agents/</guid><description>A practical framework for defining completed, approved and auditable agentic work before choosing a platform or negotiating outcome-based pricing.</description><pubDate>Fri, 18 Sep 2026 00:00:00 +0000</pubDate><category>Workflow Ownership</category></item><title>Melverick Ng — Field Notes</title><description>Practical field notes on Digital Coworkers, AI workflow ownership, and reliable execution.</description><link>https://melverick.com/</link><item><title>Your AI Dashboard Should Measure Changed Work, Not AI Usage</title><link>https://melverick.com/blog/your-ai-dashboard-should-measure-changed-work-not-ai-usage/</link><guid isPermaLink="true">https://melverick.com/blog/your-ai-dashboard-should-measure-changed-work-not-ai-usage/</guid><description>A practical scorecard for measuring whether AI improves a business workflow, including cycle time, review burden, exceptions, outcomes, and total cost.</description><pubDate>Thu, 17 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>What Happens When Your AI Agent Crashes After Step Six?</title><link>https://melverick.com/blog/ai-agent-failure-contract-recovery/</link><guid isPermaLink="true">https://melverick.com/blog/ai-agent-failure-contract-recovery/</guid><description>A practical failure contract for long-running AI agents: checkpoints, bounded retries, duplicate guards, rollback ownership, exception queues, and proof of completion.</description><pubDate>Tue, 15 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Small AI Wins When It Closes One Real Business Loop</title><link>https://melverick.com/blog/small-ai-wins-when-it-closes-one-real-business-loop/</link><guid isPermaLink="true">https://melverick.com/blog/small-ai-wins-when-it-closes-one-real-business-loop/</guid><description>A practical four-part test for SME AI projects: one decision, the right data, a domain expert, and a measurable business outcome.</description><pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>The Next ERP Is the Control Plane Above Your Systems</title><link>https://melverick.com/blog/the-next-erp-is-the-control-plane-above-your-systems/</link><guid isPermaLink="true">https://melverick.com/blog/the-next-erp-is-the-control-plane-above-your-systems/</guid><description>ERP and CRM remain systems of record. The next operational advantage is a governed control plane that coordinates context, agents, permissions, actions, evidence, and cost across them.</description><pubDate>Sun, 13 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Stop Building One Omniscient Agent. Build Governed Business Actions.</title><link>https://melverick.com/blog/stop-building-one-omniscient-agent-build-governed-business-actions/</link><guid isPermaLink="true">https://melverick.com/blog/stop-building-one-omniscient-agent-build-governed-business-actions/</guid><description>A practical framework for replacing broad, over-permissioned AI agents with narrow, reusable business actions grounded in trusted context, explicit controls, evidence, and human escalation.</description><pubDate>Sat, 12 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>The Best AI Agent Workflow Is a Closed Loop, Not a Chatbot</title><link>https://melverick.com/blog/best-ai-agent-workflow-closed-loop-not-chatbot/</link><guid isPermaLink="true">https://melverick.com/blog/best-ai-agent-workflow-closed-loop-not-chatbot/</guid><description>A practical six-stage operating model for moving AI from recommendations to governed execution across ERP, CRM, finance, and service workflows.</description><pubDate>Wed, 09 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Put AI Above the Workflow, Not Inside Every Control</title><link>https://melverick.com/blog/put-ai-above-the-workflow-not-inside-every-control/</link><guid isPermaLink="true">https://melverick.com/blog/put-ai-above-the-workflow-not-inside-every-control/</guid><description>A practical operating model for letting AI interpret work while tested systems keep permissions, approvals, execution and auditability under control.</description><pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Do Not Hire a Digital Coworker You Cannot Review</title><link>https://melverick.com/blog/do-not-hire-a-digital-coworker-you-cannot-review/</link><guid isPermaLink="true">https://melverick.com/blog/do-not-hire-a-digital-coworker-you-cannot-review/</guid><description>A practical five-part control card for SME leaders deploying AI agents across ERP, CRM and operational workflows.</description><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>A Chatbot That Opens a Ticket Is Not a Digital Coworker</title><link>https://melverick.com/blog/chatbot-ticket-digital-coworker/</link><guid isPermaLink="true">https://melverick.com/blog/chatbot-ticket-digital-coworker/</guid><description>A practical framework for moving SME customer service from AI answers to governed execution across CRM, billing and finance systems.</description><pubDate>Mon, 31 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Build the Readiness Gate Before the Agent</title><link>https://melverick.com/blog/build-the-readiness-gate-before-the-agent/</link><guid isPermaLink="true">https://melverick.com/blog/build-the-readiness-gate-before-the-agent/</guid><description>A practical seven-part readiness gate for SMEs moving AI agents from impressive demos into dependable ERP, CRM and operations workflows.</description><pubDate>Sun, 30 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Your AI Agent Needs a Job Description, Manager, Access Card and Audit Trail</title><link>https://melverick.com/blog/ai-agent-job-description-manager-access-card-audit-trail/</link><guid isPermaLink="true">https://melverick.com/blog/ai-agent-job-description-manager-access-card-audit-trail/</guid><description>A practical six-part framework for turning AI assistants into governed digital coworkers that can execute bounded ERP and CRM work safely.</description><pubDate>Sat, 29 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Your First AI Digital Worker Should Improve the Data Before It Automates the Work</title><link>https://melverick.com/blog/ai-digital-workers-data-readiness-governed-execution/</link><guid isPermaLink="true">https://melverick.com/blog/ai-digital-workers-data-readiness-governed-execution/</guid><description>A practical four-stage model for SMEs to use governed digital workers to expose data problems, support human decisions, and automate only stable operational paths.</description><pubDate>Fri, 28 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>When AI Becomes the Interface, Your Operating Rules Become the Product</title><link>https://melverick.com/blog/when-ai-becomes-the-interface-operating-rules-become-the-product/</link><guid isPermaLink="true">https://melverick.com/blog/when-ai-becomes-the-interface-operating-rules-become-the-product/</guid><description>Claudeforce signals a shift from clicking through CRM screens to acting through AI. For SMEs, the real readiness work is making data, permissions, action limits, and exceptions explicit.</description><pubDate>Thu, 27 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Stop Buying Finance Chatbots. Design One Governed Finance Job.</title><link>https://melverick.com/blog/design-one-governed-finance-job/</link><guid isPermaLink="true">https://melverick.com/blog/design-one-governed-finance-job/</guid><description>A practical SME blueprint for turning agentic AI into one bounded finance workflow with evidence, deterministic checks, and maker-checker approval.</description><pubDate>Wed, 26 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Your AI Moat May Be the People Who Can Grade the Answer</title><link>https://melverick.com/blog/your-ai-moat-may-be-the-people-who-can-grade-the-answer/</link><guid isPermaLink="true">https://melverick.com/blog/your-ai-moat-may-be-the-people-who-can-grade-the-answer/</guid><description>Before an SME debates building or buying AI, turn ten difficult past cases into a grading set that domain experts can defend.</description><pubDate>Tue, 25 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>Production AI Is a Harness Problem, Not a Model Problem</title><link>https://melverick.com/blog/production-ai-is-a-harness-problem/</link><guid isPermaLink="true">https://melverick.com/blog/production-ai-is-a-harness-problem/</guid><description>A practical guide for SME leaders: why reliable digital coworkers depend on orchestration, context, permissions, controls, monitoring, and human accountability—not just a capable AI model.</description><pubDate>Sun, 23 Aug 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item><item><title>The AI Workflow Ownership Test</title><link>https://melverick.com/blog/ai-workflow-ownership-test/</link><guid isPermaLink="true">https://melverick.com/blog/ai-workflow-ownership-test/</guid><description>Seven questions an SME should answer before allowing an AI agent or Digital Coworker to execute real business work.</description><pubDate>Mon, 27 Jul 2026 00:00:00 GMT</pubDate><category>Workflow Ownership</category></item></channel></rss>