# What does it cost to change an AI workflow six months later?

Changing an AI workflow six months later lands in one of four buckets: a settings change, a small code change, a large code change, or a rebuild. A system built for change puts most requests in the first two. A glued workflow puts them in the last two, because its logic lives only in the connections.

Kicker: Six months later
Checked: 2026-09-27

## A change request lands in one of four buckets

- **A settings change**: What it means, A value already exists for this: a threshold, a key, a cap, a window, which provider runs first; What it costs, Minutes. No new code, no review, no risk to anything else
- **A small code change**: What it means, A new rule sits beside the existing ones, with a test that checks it; What it costs, Hours to a day. One place to edit, one thing that can break
- **A large code change**: What it means, Something connected crosses a boundary. A new channel, a new system it has to talk to, a change in what it hands back; What it costs, Days to weeks, and it should be quoted as such before the work starts
- **A rebuild**: What it means, The assumption under the data changed; What it costs, Start again on that part, and anyone honest says so up front

## This is the question nobody answers

Ask a shop what happens when your needs change in six months and the answer is usually a posture: flexible, modular, built to grow. None of that survives a specific request.

The useful version is plain: name the four buckets, then say which one a given change falls into and why. Every system has all four. What separates a good one is where the line sits, and a team that runs its own systems can draw that line without stopping to think.

## What lives in each bucket, from systems that are running

These are OCTYN's own, written down before anyone asks, which is the point.

- A settings change on Mooney: which key is active, the daily caps per plan, which provider goes first. Upgrading a key's plan changes no code, because the system already sends work to whichever one has room.
- A small code change on Mooney: a new expense field, a new category, another spoken language, one more backup step. The server-side pieces update on their own, so a change reaches every phone that has the app without a store review. That is why the line sits there.
- A large code change on Mooney: anything that changes what the system hands back, because the instructions, the checker and the expense logic are tied together. Also anything touching the widget, since running two processes at once is structural.
- A rebuild on Mooney: shared team accounts, because storage today is a single file with no structure and no migration path. That fits one person and not a shared team, and OCTYN would say so before taking the work.
- A settings change on the craft retailer's outreach system: the target list is a file per company, and daily volume, the split between markets, inbox limits, send windows and follow-up timing are all values a person can set. Another company already runs on the same system with a completely different target list, which is the proof the split holds.
- A rebuild on the retailer's system: sending at a much higher volume than today, because the research step is deliberately slow and built for care over speed.

## Why a glued workflow lands higher up the list

Not because the workflow is a bad choice. Because of where its logic sits.

In a built system, the rule that decides something is a named piece of code, next to a test that fails when it is wrong, with a note saying why it was written. Six months later, someone can find it by searching for what it does, change it, and know from the test whether anything broke.

In a glued workflow, the rule is the shape of the connections. There is no name to search for, no note saying why it was drawn that way, and the only way to know whether a change broke something is to run it and watch. That is fine at three steps. At thirty, a small change becomes an afternoon of clicking, and whoever built it has often moved on.

This compounds with the person more than with the workflow itself. Most of it gets built by whoever needed it that week, in whatever window was open, and the reason lives in their head. A rebuild six months later is often not a technical call. It is that nobody left can say what the thing was supposed to do.

## Ask for the four buckets before you sign

Take the three changes you are most likely to want in six months. Not hypotheticals: the ones already half-discussed. Ask which bucket each one lands in and why.

The answer tells you two things: whether they have thought about change at all, and whether they will give you the expensive answer when it is the true one. Anyone who puts all three in the settings bucket is either selling, or has not built it yet.

## Dated record

- A new provider takes an afternoon, a new expense field takes a day, and shared team accounts means rewriting how data is stored. Written down before anyone asked (recorded 2026-09-14, [Mooney](https://octyn.co/casestudies/mooney))
- The target list for each company on this outreach system is one file of sources, weights, thresholds and market, so another company already runs on the same system with a completely different list (recorded 2026-09-27)
- Which model the assistant uses, whether the built-in assistant is even on, and where updates come from are all settings the team can change with no new release (recorded 2026-07-14)
- Letting more than one person read Brain at once is a rebuild, not a setting, because the whole design assumes a single reader with a single context at a time (recorded 2026-09-14)

## Terms used here

- [Orchestration](https://octyn.co/glossary/orchestration)
- [Rollback](https://octyn.co/glossary/rollback)
- [Total cost of ownership](https://octyn.co/glossary/total-cost-of-ownership)
- [Baseline measurement](https://octyn.co/glossary/baseline-measurement)
- [System architecture](https://octyn.co/glossary/system-architecture)

## Bears on

- [Company Brain](https://octyn.co/systems/company-brain)
- [Agency Ops](https://octyn.co/systems/agency-ops)

## Related

- [A glued workflow versus a built system at 10,000 runs a month](https://octyn.co/compare/glued-workflow-vs-built-system)
- [Build around your workflow, or bend it to a product](https://octyn.co/compare/built-around-your-workflow-vs-tool-you-bend-to)
- [Company Brain](https://octyn.co/systems/company-brain)

Canonical: https://octyn.co/compare/cost-to-change-ai-workflow-six-months