Request-to-ECO & Quote Agent
Built on requestEvery change starts somewhere. It should end in a clean ECO and a quote.
Pick where your change starts
Agent 2
Agent 2
Request-to-ECO & Quote Agent
- AI reads the input, then coded rules (fixed logic, not AI) check what it found, with sources.
- Plans what each change needs, checks your files for it, drafts the ECO and prices the quote.Read-only: it never changes your files, and works within set limits.Cited: every finding names the file and row it came from.Reviewed: it goes over its own work before handing it to you.
- People review the draft and make and record every decision. Routed to Quality, Engineering, and others as appropriate.
- Switch on only the follow-up actions you need: emails, tasks, and updates in your other systems such as SAP, Oracle, Jira or Teams. Not in this demo: we’ll discuss your follow-up actions in a discovery call. Once switched on, nothing changes in your systems without your approval.
The steps above combine:AUTOMATIONAIHUMAN-IN-THE-LOOP
Automate any of 30+ follow-up actions
switch on what you needNot in this demo: we’ll discuss your follow-up actions in a discovery call.
ECO initiation
Design engineering
Document control
Manufacturing eng.
Purchasing & supply
QA/RA
Project leadership
Agent 2Built on request
Turn customer requests into ECO drafts and quotes, then automate 30+ actions
Let’s build this agent. Tell us about your current process and requirements.
About the Request-to-ECO & Quote Agent
What a custom AI agent could do with a customer's change request: turn it into a draft ECO and a quote, for your team to review.
We build custom AI agents around each client's own process. This page shows one we would build for contract manufacturers and the device makers they work with: an agent that takes a customer's change request, whether an email, a marked-up document or a change request form, and does the groundwork your team does by hand before it can answer. It is part of our Change Control Agent Suite. Its first agent, the BOM-to-ECO & Quote Agent, is live, and you can try it with sample files or your own.
See the approach working: try the live BOM-to-ECO & Quote Agent →
The manual work today
A customer asks for a change: a different part, a new label, a tighter tolerance, an updated test. The request often arrives in free text, sometimes with attachments that don't match each other. Before anyone can reply with a date and a price, someone has to work out what is actually being asked, which of the customer's products and your assemblies it touches, what stock and open orders are affected, what the change costs to make, and what it means for the device's documents and filings. That work typically spans Program Management, Engineering, Quality and Purchasing, and the customer is waiting on the answer.
Why it matters under the QMSR
ISO 13485:2016 §7.2.2 asks you to review requirements related to product before you commit to supply them, and, when those requirements change, to amend the relevant documents and make sure the right people know. Since FDA's Quality Management System Regulation took effect on 2 February 2026, 21 CFR Part 820 incorporates ISO 13485 by reference, so a customer's change is a regulated event at the contract manufacturer as well as at the device maker.
One nuance matters for contract manufacturers: some decisions belong to the legal manufacturer, not to you. Whether a change needs a new 510(k), a PMA supplement or a new UDI device identifier is your customer's call. An agent like this is designed to prepare the questions for them, not to answer them on their behalf.
What the agent would do
The same four steps as every agent in the suite, applied to a customer request:
AI reads · coded rules check
Read the request
AI pulls out what is being asked: the affected customer part numbers and documents, the change itself, the requested effective date or lot, and any reason given. Coded rules (fixed logic, not AI) then check what it found, and each item is designed to point back to where it came from in the request. Anything unclear or missing, such as an effective date or a drawing the email mentions but doesn't attach, is designed to be listed as a question back to the customer rather than filled in.
AI agent · plans, checks, drafts, prices
Draft the ECO and the quote
The AI agent plans what the change needs, checks your files and drafts:
- Where it's usedthe customer's products, your BOMs and assemblies in your files that the change touches.
- Stock and orderson hand, work in process and open orders affected, with a suggested disposition for each (use up, rework, scrap, return) and the quantity it rests on.
- Parts and supplierswhether any new part is already on your approved supplier list, with its lead time.
- Open changesother open ECOs on the same parts in your ECO log, to help keep two changes from colliding.
- Regulatory questionsthe same seven checks as our live agent (significance, FDA filing, risk, testing, process / labeling / device ID, documents and training), framed as questions for your customer where the decision is theirs.
- Cost and quotematerial, rework or scrap, engineering and one-time costs, rolled into a quote for the customer with an effective date.
People · review, decide, send
People review, decide and send
The draft goes to your program, engineering and quality leads. Your team makes and records every decision and decides what goes back to the customer; the agent prepares the work and decides nothing.
Automation · optional
Follow-up actions, if you want them
The reply to the customer, tasks and updates in systems such as SAP, Oracle, Jira or Teams, each switched on separately and designed so nothing changes in your systems without your approval.
Each finding is designed to name the file and row it came from, and a check whose file wasn't provided shows as Not checked, not as a clean result. The output is only as complete as the request and files it is given, and AI can misread a request, which is why people review every draft.
The checks, and where they come from
| Check | Requirement |
|---|---|
| Review the changed requirement; amend documents; inform the people affected | ISO 13485 §7.2.2 (via 21 CFR 820.10) |
| Communicate with the customer about the change | ISO 13485 §7.2.3 |
| Does the change reach the device design? | ISO 13485 §7.3.9 |
| New parts from approved suppliers only | ISO 13485 §7.4.1 |
| New 510(k), PMA supplement or new UDI device identifier? (the legal manufacturer's decision) | 21 CFR 807.81(a)(3); 21 CFR 814.39; 21 CFR 830.50 |
| Labeling and packaging affected? | 21 CFR 820.45 |
Each requirement, with its source, is on our QMSR mapping page. The agent raises these questions and shows its working. The decisions stay with your team and, where they are the legal manufacturer's, with your customer.
What your team would get
- A draft ECO: the affected products, assemblies and parts found in your files, the findings, and the open questions, for your team to check and complete.
- A quote for the customer: the cost of the change, any one-time costs and the proposed effective date.
- A list of questions for the customer, where the request is unclear or the decision is theirs.
- A record of the requirement review: what changed, what it affects, and who decided.
How we'd build yours
Every contract manufacturer handles customer changes its own way: how requests arrive, how quotes are built, how ECOs are numbered and routed, what each customer's quality agreement requires. So we don't sell this agent off the shelf. We start from your process:
- 01
Discovery
we map how customer requests are handled today, with the people who handle them.
- 02
Proof of concept
a working version on a few of your real requests and files, so you can judge the output for yourself.
- 03
Build and integration
connected to the systems you choose, such as your ERP, PLM, quoting tool or document control, and tested against your cases.
- 04
Go-live and tuning
your team trained, results monitored, rules adjusted as your process changes.
The live BOM-to-ECO & Quote Agent shows the approach working today, on the same engine this agent would use.
Questions buyers ask
Is this a product we can buy?
Not off the shelf. We build it for you, around your process, your customers' requirements and your systems (ERP, PLM, quality). The best way to start is with a 2-week pilot around your needs. Book a Discovery Call →
Can it handle different customers' formats?
It can be built to read requests in the forms your customers use, and to follow each customer's quality agreement where they differ. We'd settle the list in discovery.
What if a request is vague?
The agent is designed to list what's unclear and draft the questions back to the customer, rather than guess what they meant.
Who decides on filings?
The legal manufacturer. The agent is designed to prepare those questions for your customer, with the information they'll need, and to leave the decision with them.
Is it validated?
Not out of the box. If your team uses an agent like this as part of your quality system, ISO 13485 §4.1.6 asks you to validate that software for its intended use, in proportion to the risk. We design our builds with that in mind and can talk through what your validation would need.
Talk to us about an agent built to your process.
Book a Discovery CallDisclaimer: This page describes an example of an agent we would build to a client's process: how it is designed to work, not a product or a guaranteed result. Any agent we build is advisory and not a validated system. AI can make mistakes, results depend on the data it is given, and the regulatory checks raise questions without deciding them. Your team reviews the output and makes and records every decision. Time figures are estimates, not measurements. Nothing on this page is legal or regulatory advice.