Settled in software.
Open the current record, enforce fields and allowed states, check the return, and save a version that can be read back.
METHODOLOGY
Your business already has ways to plan, review and approve work, and most functions have a well-understood way to do it right. We start there. We don't invent a new process: ordinary software holds the forms and checks, AI drafts, compares and helps make some of the decisions, and the people with the authority sign off.
We look up what normal looks like for the function, compare it with how you run today, and automate that. If your people came out of sales, purchasing, planning, accounting or engineering, they will recognize every row.
| Familiar tool | What stays settled | What AI can prepare | What people decide |
|---|---|---|---|
| MRP and capacity planning (CRP) | Bills of material, calendars, stock and units | Initial shortage and overload analysis | Schedule, overtime and capacity changes |
| Purchasing and supply chain | Order fields, dates, approval limits and supplier records | Late-order comparisons and expedite drafts | Supplier changes and spending |
| Inventory management | Locations, counts and reorder points | Stock-out and excess analysis against demand | Reorders, write-offs and transfers |
| Project tracking | Milestones, owners and status | Slip analysis and the open-items list | Priorities, resources and dates |
| Stage gates | Required evidence and gate status | Missing-evidence list and review packet | Go, hold or drop |
| SWOT and risk analysis | Factors, scoring scale and source links | Initial analysis by AI, with evidence for each item | Strategy and which risks are accepted |
| Sales pipeline and CRM | Stages, required fields and account ownership | Research and follow-up drafts | Pricing, commitments and stage changes |
| Budgets and forecasts | Accounts, periods and calculation rules | Variance analysis with source references | Explanations, adjustments and the close |
| FMEA and APQP | Required fields and source links | Candidate risks and unanswered questions | Accepted risks and release |
| Control plans | Check method, frequency and reaction fields | Missing-check review | Process changes and response |
| Lean, Six Sigma, 5 whys and A3 | Steps, owners and evidence fields | Comparisons and possible causes | Which cause is supported and what to change |
| Standard work and checklists | Current version and completion fields | Draft instructions and exceptions | Approval of the next version |
Explore the tools in hotbotspot. The public AI agents run as open experiments at A.N. Creation Office.
Open the current record, enforce fields and allowed states, check the return, and save a version that can be read back.
Read the task's instruction, compare the supplied evidence, draft the result and mark missing facts. A rejected record returns for correction.
Review the substance, approve or reject the action, and decide when the work is ready to move. Anything that can't be undone waits for a yes.
Anything that can't be undone waits for a yes.
Looking for the molding example? Read Manufacturing
Illustrative: Paper Lantern Distribution is a made-up company. A supplier moves a confirmed date by two weeks. The buyer supplies the PO, stock balance and customer-order dates. Software keeps the original promise date and records the new one separately. AI identifies the customer orders that may be affected, marks missing alternate-source prices, and drafts a follow-up. It offers partial delivery and a schedule change as options, without treating either as agreed. The buyer checks stock with the warehouse and chooses a partial-delivery request. The draft stays unsent until the buyer approves it. The reply and the decision return to the order record.
Illustrative: Cedar Desk Services is a made-up company. The controller supplies the ledger export and approved budget for one period. Software aligns the accounts and computes the differences. AI drafts a note separating the recorded difference from possible explanations. A travel increase has invoices; an outside-services increase has no supporting detail, so its cause stays open. The controller rejects the unsupported explanation and asks the account owner for evidence. No journal is posted. The accepted note and unresolved question are saved with their sources.
Illustrative: Harbor Lane Goods is a made-up company. A customer reports the wrong item in a shipment. Software opens a case using the order number and return-policy version. AI compares the message with the shipment record and drafts a reply asking for the missing item label. It cannot infer damage or promise a replacement from the complaint alone. A service lead reviews the reply and approves sending it. When the label arrives, the lead decides whether the policy covers a replacement. Any refund or shipment requires separate approval. The case retains the evidence and the decision.
Give them the current system, the rules and the limits. Check the first work closely. Give them more responsibility as they earn it, with test results and a record. Train the people who will review it, handle exceptions and change the instructions when the business changes.
Deeper in the work, four kinds of files help: principles state the shared rules; playbooks describe a job's stages and gates; skills describe one task; records hold facts, decisions and evidence. These are a flat set of working materials. Each task instruction states its purpose, inputs, boundaries, method, output, reviewer and what must be saved. Read the notes.
A fixed form can still contain a wrong answer. Instructions alone do not enforce permissions. Not every task justifies custom software. Test with your own data and model, including missing sources, conflicting records and denied approvals. Test again after a change. Solutions explains what has and has not been tried.