{"version":1,"name":"airoweb","description":"Notes on AI workflows, tools, and MCPs.","url":"https://airoweb.com","language":"en","sitemap":"https://airoweb.com/sitemap-index.xml","feed":"https://airoweb.com/rss.xml","editorialPolicy":"https://airoweb.com/editorial-policy/","entries":[{"type":"article","title":"An AI renewal is a workflow review, not a seat-count negotiation","description":"Seat utilization can inform a contract negotiation. It cannot show whether an AI-assisted workflow is useful, safe, supportable, or still worth renewing.","url":"https://airoweb.com/blog/ai-tool-renewal-workflow-review/","category":"Company adoption","tags":["adoption","procurement","vendor management","workflow review","governance"],"publishedAt":"2026-09-20T00:00:00.000Z","updatedAt":"2026-09-20T00:00:00.000Z"},{"type":"article","title":"Jev belongs in the decision layer, not the writing layer","description":"Jev is designed to make bounded judgments that software can consume, not to draft prose. These three workflow designs show where that distinction helps—and where deterministic rules and human review must remain.","url":"https://airoweb.com/blog/jev-decision-layer-use-cases/","category":"AI infrastructure","tags":["Jev","System One models","decision automation","AI workflows"],"publishedAt":"2026-09-20T00:00:00.000Z","updatedAt":"2026-09-20T00:00:00.000Z"},{"type":"article","title":"NotchFuel puts AI usage in the MacBook notch","description":"NotchFuel makes the MacBook camera notch useful by keeping Claude Code, Codex, and Grok CLI usage visible without another dashboard.","url":"https://airoweb.com/blog/notchfuel-ai-usage-in-macbook-notch/","category":"AI infrastructure","tags":["macOS","AI usage","developer tools","open source"],"publishedAt":"2026-08-31T00:00:00.000Z","updatedAt":"2026-08-31T00:00:00.000Z"},{"type":"article","title":"Put the AI pentester in a test cell","description":"Use AI to plan, correlate, and document a penetration test, while deterministic tools, external policy, and a human tester retain control of every risky action.","url":"https://airoweb.com/blog/ai-penetration-testing-agent-guardrails/","category":"AI infrastructure","tags":["penetration testing","AI agents","application security","SaaS"],"publishedAt":"2026-08-25T00:00:00.000Z","updatedAt":"2026-08-25T00:00:00.000Z"},{"type":"article","title":"Ask workers where the AI moved the work","description":"An AI rollout can remove drafting while adding review, exception handling, surveillance, and accountability. A work-delta review makes that transfer visible before launch.","url":"https://airoweb.com/blog/ask-workers-where-ai-moved-work/","category":"Company adoption","tags":["adoption","operating model","worker consultation","workflow design","governance"],"publishedAt":"2026-08-16T00:00:00.000Z","updatedAt":"2026-08-16T00:00:00.000Z"},{"type":"article","title":"The agent updated the record. The notification never left.","description":"Two ordinary writes create a crash gap between an agent's decision and its external effect. Commit the decision and an outbox event together, then let a conventional relay handle delivery.","url":"https://airoweb.com/blog/agent-transactional-outbox/","category":"AI infrastructure","tags":["AI infrastructure","agents","reliability","event-driven architecture"],"publishedAt":"2026-08-03T00:00:00.000Z","updatedAt":"2026-08-03T00:00:00.000Z"},{"type":"article","title":"AI governance needs decision rights, not another committee","description":"A steering committee cannot own the daily decisions inside every AI-assisted process. Define who owns the governance system, the workflow, the platform, specialist review, and residual risk.","url":"https://airoweb.com/blog/ai-governance-decision-rights/","category":"Company adoption","tags":["adoption","governance","operating model","accountability"],"publishedAt":"2026-08-02T00:00:00.000Z","updatedAt":"2026-08-02T00:00:00.000Z"},{"type":"article","title":"A running flag is not a lock for your agent queue","description":"A task marked running can stay stuck after a worker dies, then collide with a replacement if the old worker returns. Expiring leases make ownership recoverable; guarded writes keep stale workers from acting.","url":"https://airoweb.com/blog/agent-queue-leases/","category":"AI infrastructure","tags":["AI infrastructure","agents","queues","reliability"],"publishedAt":"2026-07-27T00:00:00.000Z","updatedAt":"2026-07-27T00:00:00.000Z"},{"type":"article","title":"Stop measuring AI literacy by course completion","description":"A completion record says someone received training. A useful AI literacy programme shows that they can recognize the limits, data boundaries, review duties, and escalation points of the AI-assisted work they actually perform.","url":"https://airoweb.com/blog/stop-measuring-ai-literacy-by-course-completion/","category":"Company adoption","tags":["adoption","AI literacy","governance","training"],"publishedAt":"2026-07-26T00:00:00.000Z","updatedAt":"2026-07-26T00:00:00.000Z"},{"type":"article","title":"Valid JSON is not permission to act","description":"A schema can make an agent's output parseable without making the requested action correct or permitted. Put a conventional policy-enforcement layer between model proposals and production writes.","url":"https://airoweb.com/blog/valid-json-is-not-permission-to-act/","category":"AI infrastructure","tags":["AI infrastructure","agents","structured outputs","security","workflow"],"publishedAt":"2026-07-20T00:00:00.000Z","updatedAt":"2026-07-20T00:00:00.000Z"},{"type":"article","title":"Measure the AI workflow, not how often people open the tool","description":"License activation and prompt activity show that an AI product is being used. A workflow scorecard shows whether the work is better, where costs moved, and whether the risk remains acceptable.","url":"https://airoweb.com/blog/measure-ai-workflow-not-tool-usage/","category":"Company adoption","tags":["adoption","measurement","operations","governance"],"publishedAt":"2026-07-19T00:00:00.000Z","updatedAt":"2026-07-19T00:00:00.000Z"},{"type":"article","title":"Give your agent a key, not the keyring","description":"An agent that needs to pull one report should not be handed a credential that can also move money. Scope the secret to the run, keep it out of the model's view, and treat anything it touched as already leaked.","url":"https://airoweb.com/blog/scope-agent-credentials-to-the-run/","category":"AI infrastructure","tags":["AI infrastructure","security","secrets management","agents"],"publishedAt":"2026-07-13T00:00:00.000Z","updatedAt":"2026-07-13T00:00:00.000Z"},{"type":"article","title":"Design the AI workflow's off switch before you need it","description":"AI programs design the intake, the pilot, and the rollout, then never plan the shutdown. Here is how to turn an AI workflow off — planned retirement and emergency stop — with owners, triggers, and fallbacks set in advance.","url":"https://airoweb.com/blog/design-the-ai-workflow-off-switch/","category":"Company adoption","tags":["operating model","governance","rollout","lifecycle","risk"],"publishedAt":"2026-07-12T00:00:00.000Z","updatedAt":"2026-07-12T00:00:00.000Z"},{"type":"article","title":"Assume your agent will run the workflow twice","description":"The reliability question for connected agent workflows is not whether a step runs, but whether running it a second time is safe. Design acting steps to be repeatable with idempotency keys, server-side dedup, and retries that back off.","url":"https://airoweb.com/blog/assume-agent-runs-workflow-twice/","category":"AI infrastructure","tags":["AI infrastructure","agents","workflow","reliability"],"publishedAt":"2026-07-10T00:00:00.000Z","updatedAt":"2026-07-10T00:00:00.000Z"},{"type":"article","title":"Your agent logs are a mirror: a self-audit from AI session history","description":"Your AI session logs are an unperformed record of how you actually work. A coding agent can turn them into an honest audit — if you run it locally, redact on read, and reject any confident-but-unsupported insight.","url":"https://airoweb.com/blog/agent-logs-are-a-mirror/","category":"AI workflow","tags":["coding agents","self-audit","privacy","prompts","workflow"],"publishedAt":"2026-07-08T00:00:00.000Z","updatedAt":"2026-07-09T00:00:00.000Z"},{"type":"article","title":"Give coding agents a workbench, not a workstation","description":"Coding agents should start inside a bounded workbench: scoped files, controlled network, no ambient secrets, explicit command approval, and a pull request as the first durable output.","url":"https://airoweb.com/blog/coding-agent-workbench-boundary/","category":"AI infrastructure","tags":["coding agents","AI infrastructure","security","developer tools"],"publishedAt":"2026-07-06T00:00:00.000Z","updatedAt":"2026-07-06T00:00:00.000Z"},{"type":"article","title":"Do not send every AI request through the same approval queue","description":"A single AI approval queue either blocks harmless work or rubber-stamps risky work. Intake lanes help teams route requests by data, impact, reversibility, and review need.","url":"https://airoweb.com/blog/ai-governance-intake-lanes/","category":"Company adoption","tags":["adoption","governance","operations"],"publishedAt":"2026-07-05T00:00:00.000Z","updatedAt":"2026-07-05T00:00:00.000Z"},{"type":"article","title":"Agent workflows need an evidence trail before they need more autonomy","description":"Before an AI agent can safely act across company systems, teams need a durable record of what it saw, what it decided, which tools it called, and who approved the result.","url":"https://airoweb.com/blog/agent-workflow-evidence-trail/","category":"AI infrastructure","tags":["agents","AI infrastructure","security","operations"],"publishedAt":"2026-07-03T00:00:00.000Z","updatedAt":"2026-07-03T00:00:00.000Z"},{"type":"article","title":"Review AI workflows again when the workflow changes","description":"Calendar reviews are useful, but approved AI workflows need a fresh review whenever the model, data, vendor, users, output, or legal setting changes.","url":"https://airoweb.com/blog/ai-workflow-change-review/","category":"Company adoption","tags":["adoption","governance","workflow"],"publishedAt":"2026-07-03T00:00:00.000Z","updatedAt":"2026-07-03T00:00:00.000Z"},{"type":"article","title":"Keep SOUL.md out of the agent junk drawer","description":"A useful SOUL.md is not a place to store every instruction. It should define durable identity, voice, values, and hard boundaries, while project rules and repeatable workflows live in more specific files.","url":"https://airoweb.com/blog/keep-soul-md-out-of-the-junk-drawer/","category":"AI infrastructure","tags":["agents","SOUL.md","Hermes","context engineering"],"publishedAt":"2026-07-02T00:00:00.000Z","updatedAt":"2026-07-02T00:00:00.000Z"},{"type":"article","title":"Treat MCP servers like production APIs","description":"An MCP server that reaches company systems needs the same operational discipline as an internal API: ownership, versioning, access control, telemetry, and retirement criteria.","url":"https://airoweb.com/blog/mcp-servers-production-apis/","category":"AI infrastructure","tags":["MCP","AI infrastructure","security","platform engineering"],"publishedAt":"2026-07-02T00:00:00.000Z","updatedAt":"2026-07-02T00:00:00.000Z"},{"type":"article","title":"Treat Multica skills as operating knowledge, not prompt storage","description":"Multica skills are most useful when they encode reviewed operating knowledge for repeatable agent work, not when they become a dumping ground for every prompt fragment.","url":"https://airoweb.com/blog/multica-skills-operating-knowledge/","category":"AI infrastructure","tags":["Multica","skills","agents","workflow"],"publishedAt":"2026-07-02T00:00:00.000Z","updatedAt":"2026-07-02T00:00:00.000Z"},{"type":"article","title":"Decide which agent tool calls need human approval","description":"Before connecting an agent to tools, classify each action by data access, reversibility, business impact, and the approval step required before it runs.","url":"https://airoweb.com/blog/agent-tool-approval-matrix/","category":"AI infrastructure","tags":["agents","MCP","security","workflow"],"publishedAt":"2026-07-01T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"Review AI pilots before they become business process","description":"A simple pilot review helps teams decide which AI experiments deserve support, which need limits, and which should stop.","url":"https://airoweb.com/blog/ai-pilot-to-process-review/","category":"Company adoption","tags":["adoption","governance","workflow"],"publishedAt":"2026-07-01T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"Fable 5 is back. Do not build as if access is permanent.","description":"Fable 5's launch, suspension, and capped return show why teams should route frontier models through fallback, review, access, and budget controls.","url":"https://airoweb.com/blog/claude-fable-5-limited-availability/","category":"AI infrastructure","tags":["frontier models","AI adoption","security","workflow"],"publishedAt":"2026-07-01T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"A better prompt for building an Obsidian vault as agent memory","description":"A durable agent-memory vault needs source inventory, staged approval, provenance, validation, and a smaller first deliverable than most ambitious prompts ask for.","url":"https://airoweb.com/blog/obsidian-vault-prompt-for-agent-memory/","category":"AI infrastructure","tags":["memory","Obsidian","agents","context engineering"],"publishedAt":"2026-07-01T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"Before buying AI tools, write the operating model","description":"A simple operating model helps teams avoid disconnected AI tools, unclear ownership, invisible review gaps, and untracked data movement.","url":"https://airoweb.com/blog/ai-adoption-operating-model/","category":"Company adoption","tags":["adoption","governance","operations"],"publishedAt":"2026-06-30T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"A quick review checklist for recurring AI workflows","description":"Use this before a team starts repeating an AI-assisted workflow, trusting the output, and treating it as normal work.","url":"https://airoweb.com/blog/ai-workflow-review-checklist/","category":"Workflow review","tags":["workflow","review","risk"],"publishedAt":"2026-06-30T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"article","title":"MCP catalogs can wait. The workflow cannot.","description":"MCP content should start with the workflow, data boundary, available action, and operator before becoming a catalog.","url":"https://airoweb.com/blog/using-mcps-internal-workflows/","category":"AI infrastructure","tags":["MCP","workflows","automation"],"publishedAt":"2026-06-30T00:00:00.000Z","updatedAt":"2026-07-01T00:00:00.000Z"},{"type":"skill","title":"SOP Gap Audit","description":"This skill helps Operations Managers audit SOPs for missing steps, unclear handoffs, exception paths, controls, metrics, and rollout risk.","url":"https://airoweb.com/skills/sop-gap-audit/","category":"Operations Manager","tags":["operations","sop","process-improvement","knowledge-ops"],"publishedAt":"2026-08-10T00:00:00.000Z","updatedAt":"2026-08-10T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/sop-gap-audit/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/sop-gap-audit/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Incident Triage Brief","description":"This skill helps Technical Analysts convert scattered incident evidence into a triage package with impact, timeline, hypotheses, gaps, and next checks.","url":"https://airoweb.com/skills/incident-triage-brief/","category":"Technical Analyst","tags":["technical-analysis","incident-response","sre","observability"],"publishedAt":"2026-08-01T00:00:00.000Z","updatedAt":"2026-08-01T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/incident-triage-brief/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/incident-triage-brief/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Renewal Risk Brief","description":"This skill helps Sales / Account Managers turn account-health fragments into a concise renewal risk brief, stakeholder plan, and save motion.","url":"https://airoweb.com/skills/renewal-risk-brief/","category":"Sales / Account Manager","tags":["sales","account-management","renewals","customer-success"],"publishedAt":"2026-07-25T00:00:00.000Z","updatedAt":"2026-07-25T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/renewal-risk-brief/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/renewal-risk-brief/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Campaign Optimization Brief","description":"This skill helps Marketing Managers translate campaign data into practical optimization decisions without overstating attribution certainty or hiding data-quality caveats.","url":"https://airoweb.com/skills/campaign-optimization-brief/","category":"Marketing Manager","tags":["marketing","campaign-optimization","performance-marketing","reporting"],"publishedAt":"2026-07-18T00:00:00.000Z","updatedAt":"2026-07-18T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/campaign-optimization-brief/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/campaign-optimization-brief/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Requirements Traceability Matrix","description":"This skill helps Business Analysts turn messy discovery inputs into a requirements traceability matrix that links objectives, requirements, validation coverage, gaps, and sign-off readiness.","url":"https://airoweb.com/skills/requirements-traceability-matrix/","category":"Business Analyst","tags":["business-analysis","requirements","traceability","quality-assurance"],"publishedAt":"2026-07-11T00:00:00.000Z","updatedAt":"2026-07-11T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/requirements-traceability-matrix/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/requirements-traceability-matrix/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Daily Project Status Digest","description":"This skill helps technology Project Managers turn scattered implementation inputs into a paste-ready governance digest with risks, blockers, decisions, and owner follow-ups.","url":"https://airoweb.com/skills/daily-project-status-digest/","category":"Project Manager","tags":["project-management","status-reporting","sap-activate","risk-management"],"publishedAt":"2026-07-04T00:00:00.000Z","updatedAt":"2026-07-05T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/daily-project-status-digest/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/daily-project-status-digest/evals/evals.json","kind":"eval"}]},{"type":"skill","title":"Support Escalation Brief","description":"This skill helps Support and Customer Success teams turn scattered issue and account context into an escalation package that product, engineering, and leadership can act on quickly.","url":"https://airoweb.com/skills/support-escalation-brief/","category":"Support / Customer Success","tags":["customer-success","support","escalations"],"publishedAt":"2026-07-04T00:00:00.000Z","updatedAt":"2026-07-04T00:00:00.000Z","artifacts":[{"label":"Download SKILL.md","url":"https://airoweb.com/downloads/skills/support-escalation-brief/SKILL.md","kind":"skill"},{"label":"Download evals.json","url":"https://airoweb.com/downloads/skills/support-escalation-brief/evals/evals.json","kind":"eval"}]}]}