Notes from finance, operations, and applied AI work.

26 posts found

• Corporate SecretarialProfessional Practice

  SG Corpsec Knowledge Library

  24 Sept 2026 · 18 min read

  Six guides for fictional training and human-reviewed drafting: intake, annual compliance, director appointments, templates, records and official sources. Version 1.0; professional legal approval pending.

• AI GovernanceProfessional Practice

  When AI doesn't comply

  15 Sept 2026 · 10 min read

  Your firm can authorise the work without controlling every rule governing its AI. Two payment workflows reveal why accountants, CSPs and firm owners need to distinguish capability, permission and continuity.

• Professional PracticeAI JudgmentHuman–AI Collaboration

  AI Is Doing More Than Drafting. Our Review Practices Need to Catch Up.

  10 Sept 2026 · 8 min read

  What real human–AI work reveals about professional judgment, evidence, approval and the limits of passing checks. An anonymised report for accountants, corporate service providers and firm owners.

• AI AccessWeb PublishingAnalytics

  Can AI Find Your Work—and Would You Know?

  05 Sept 2026 · 8 min read

  Make your work readable to AI clients, observe when recognized agents request it, and distinguish access from influence. An article followed by the practical Netlify method.

• Agent ArchitectureProfessional Practice

  The Agent Was a Folder

  24 Aug 2026 · 10 min read

  Two accounting case studies show how filesystem-defined agents, an interactive workbench and deterministic controls fit together—and when a VPS still matters.

• AI AgentsAgent ArchitectureMulti-Agent Systems

  From One Agent to an Agent System

  21 Aug 2026 · 8 min read

  A progressive guide to building one competent purpose-specific agent before adding infrastructure, specialist roles, orchestration, and multi-agent workflows.

• LinkedInContent OperationsAI Agents

  Build an Evidence-Led LinkedIn Agent

  19 Aug 2026 · 6 min read

  A documentation-first system for researching, drafting, and reviewing LinkedIn content while a human retains control of every public action.

• Second BrainCodexMarkdown

  Build a Markdown Second Brain as a Codex Project

  19 Aug 2026 · 7 min read

  A Markdown-first Codex workflow with an optional graph-retrieval upgrade: preserve evidence, connect sourced knowledge, test what the wiki can answer, and publish selected synthesis.

• PayNowXeroPayments

  Set Up Invoice-Specific PayNow QR Payments for Xero

  11 Aug 2026 · 6 min read

  A Codex runbook for building a controlled Xero payment page from a provider-issued PayNow QR, with field validation, tests, deployment checks, and real banking-app verification.

• Self-HostingDocuSealDocker

  Self-Host DocuSeal for Production

  09 Aug 2026 · 7 min read

  A production-oriented DocuSeal baseline covering pinned releases, PostgreSQL, private networking, HTTPS, durable secrets, backups, upgrades, monitoring, and email evidence.

• Codex PluginsDocuSealMCP

  Install a Review-Gated DocuSeal Plugin in Codex

  09 Aug 2026 · 7 min read

  A bounded Codex plugin pattern for preparing DocuSeal signing workflows while server-side review gates and explicit human approval retain send authority.

• Human-Agent CollaborationAI FluencyWorkflow Design

  DUO Framework: Discover, Understand, Output

  31 Jul 2026 · 6 min read

  A human-agent collaboration loop that separates rapid context discovery, human judgement, and governed production.

• Agentic WorkflowsDocument SigningHuman-in-the-Loop

  Agentic Document Signing with Human Approval

  26 Jul 2026 · 7 min read

  A system pattern in which agents prepare and validate signing packs while humans retain authority over template approval and legally significant sends.

• AccountingGroup ConsolidationAI Agents

  Build a Controlled Group Consolidation Worksheet with AI

  25 Jul 2026 · 7 min read

  A controlled workbook architecture for using AI to prepare consolidation workflows while keeping inputs, exceptions, approvals, and professional judgement visible.

• Agent ArchitectureCodexEve

  Adopt Vercel Eve Architecture in a Codex Workspace

  22 Jul 2026 · 7 min read

  A dependency-free build manual for preparing a repository around Eve's filesystem architecture, security boundaries, and evaluation strategy before installing a runtime.

• API DesignAgent Architecture

  Repository Agent Brief: Plan How to Open an API

  18 Jul 2026 · 14 min read

  A complete, copy-ready planning brief for inspecting an existing repository and designing a supported API, with evidence, authorization and staged delivery.

• Agentic WorkflowsAPI DesignTechnical Build Notes

  API-to-Agentification Workflow

  18 Jul 2026 · 6 min read

  A staged workflow for turning an existing application into a safely agent-operable system, starting with its real interfaces, permissions, and business operations.

• Agentic WorkflowsBusiness OperationsWorkflow Design

  Plan Non-Technical Work Loops with AI Agents

  15 Jul 2026 · 6 min read

  A practical method for turning business and knowledge-work processes into bounded, evidence-driven feedback loops without giving agents implied authority.

• Loop EngineeringCodexAgents

  Loop Engineering with gstack in the Codex App

  08 Jul 2026 · 7 min read

  A practical playbook for designing repeatable AI engineering loops in the Codex App, using gstack as a reference architecture for goals, repository rules, review, QA, and shipping discipline.

• AI VisibilityTechnical SEOPlaybook

  AI Visibility Playbook

  05 Jul 2026 · 6 min read

  A practical checklist for making a website easier for AI-assisted search systems to find, understand, and cite.

• AI AutomationAgentic WorkflowsTechnical Build Notes

  Agentify Any App

  04 Jul 2026 · 7 min read

  A practical pattern for turning existing software into agent-operable workflows through typed APIs, stable URIs, permissions, confirmations, and audit logs.

• AI AutomationFinance OperationsAgentic Workflows

  From Ledgers to LLMs: Why Finance Teams Need AI Operators

  20 Feb 2026 · 6 min read

  A practical argument for treating AI as an operating layer in finance, not a side experiment.

• AccountingComplianceSME Operations

  Why Bank Statements Alone Are Not Bookkeeping

  08 Feb 2026 · 4 min read

  A simple explanation of why SME owners need clean source records, not just bank transactions.

• AI AutomationSME OperationsWorkflow

  From Prompts to Workflows: How SMEs Should Really Use AI

  18 Jan 2026 · 5 min read

  AI becomes useful when teams move beyond one-off prompts into repeatable workflows with review points.

• AI GovernanceRiskOperations

  AI Risk Is Mostly a Process Problem

  07 Dec 2025 · 5 min read

  Risk in AI adoption usually comes from unclear handoffs and weak review points, not model capability alone.

• Founder ReflectionsAI AutomationSystems

  Practical Beats Flashy in AI Adoption

  21 Nov 2025 · 4 min read

  The most valuable AI systems often look boring because they are embedded in real operational routines.