SOLUTIONS

Records and checks for AI work

We're building software that holds project records and gives AI agents a fixed way to read and draft them. The aim is to spend less effort recreating forms and more on the questions that need thought.

01 · Software

What moves into software

Table 1 · What moves into software
PartWhat it holdsWhat the AI agent no longer has to reinvent
SchemaFields, units and allowed valuesThe shape of the form
ChecksRequired sources and missing-field checksWhether a required field exists
StateDraft, review, released and closedWhere the work stands
OutputA repeatable report layoutFormatting on every run
StoreOne versioned home for each recordWhich scattered file to use

A person chooses the forms and checks. Code is not a substitute for reviewing the answer.

The first build

The first build links FMEA and a control plan on an engineering project. The same records-and-checks pattern is meant for the rest of the business: a customer case, an inventory count, a purchase order or a month-end close.

We're starting with AI agents that keep working and remembering between conversations, because that is the behavior this build is meant to support.

The record store connects through MCP, a standard way for an AI agent to use outside software. People decide what the program does and check it. The AI agents doing daily work use those connections; they do not get permission to rewrite the program.

03 · The field

What the field has found

These are reports from other authors, not Advance Now performance results. The numerical finding belongs to the cited research, not to this build.

Table 2 · What the field has found
What the field foundSourceThe older tool that already does it
Add a check between steps, so a failed step stops the chain.“Building Effective Agents” (2024)Stage gates; ladder logic
Constrain the input: fixed choices, allowed ranges, required steps.Agent poka-yoke write-ups; Thoughtworks RadarPoka-yoke
Keep notes in files outside the conversation, and read them back.Guide to context engineering (2025)Travelers, setup sheets, batch records
Spread a task over a conversation and performance drops an average of 39%.Laban and others (ICLR 2026)State programming: one mode at a time
Have a person approve actions that are sensitive or can't be undone.A practical guide to building agents (2025)Interlocks; sign-off before release
Run the same task many times, and count it as reliable only if it passes every time.Sierra, τ-bench (ICLR 2025)Commissioning and capability studies

Full citations are in the Notes. Structure sets the size of the job compares the main ways to build an AI agent.

What you can try today

List the decisions your AI agent repeats that never change. Put one into a fixed template or a script. Check its output independently. Keep the prompt focused on what requires judgment. Record failures and compare against the previous version before giving it more responsibility. A well-shaped record can still be wrong, so the responsible person checks the evidence and decides.

Public experiments and references

A.N. Creation Office keeps the public AI agents and examples. hotbotspot documents business tools and illustrative records.