Product 02

InkIQ Agents

Agents that do the work, not ones that summarise it. They read the thread, parse the purchase order, open every attachment, match the product, apply your price tables and write the reply — then ask a human when they aren't sure, and remember the answer.

Underneath all of them is one model of how this industry actually works. We built a full ERP to learn it. Where your data lives is a deployment decision, not a limit on what they understand.

Deployment A

On the InkIQ ERP

The fastest route. Price tables, catalogue, equipment and customer history already sit where the agents expect them, so there is nothing to connect and nothing to map.

  • Requests become quotes and orders directly
  • Schedules production onto your real stations
  • Full audit trail on every action taken
  • Live in days, because the configuration is the product
Deployment B

On the systems you already run

You have an ERP, it works, and replacing it is not this year's project. Then it stays. We wire the brain into the stack you have and become the layer that understands the work — your systems keep being the system of record.

  • 01We map your stack — order system, mailbox, supplier feeds, artwork storage, accounting
  • 02Your pricing logic is mirrored into the model, charge for charge
  • 03Agents work your queue and write finished records back where they belong
  • 04Nothing migrates, and nothing about how your team works has to change

No two stacks are the same, so no two builds are. This one starts with a scoping engagement, not a signup.


The working loop

From "can you quote this?" to a quote.

This is the whole job, and the agents own all of it. Every step is something a person in your office is doing right now, between other things, at the wrong time of day.


Purchase orders

A PO is a document. It should arrive as data.

Contract work doesn't come as a friendly email. It comes as a purchase order — a PDF, a spreadsheet, a portal export, a scan of a printout — and somebody in your office retypes it into the system, line by line, at the busiest hour of the day.

The agents read it instead. Line items, SKUs, colourways, the size matrix, in-hands date, ship-to, billing terms and PO number come out as structured fields, matched against your catalogue and that account's pricing. Order entry becomes a review step: nine lines confirmed, one flagged, thirty seconds of your attention instead of twenty minutes of typing.

  • PDFs, spreadsheets, portal exports, scans and photographs of paperwork
  • Size-and-colour matrices read as a grid, not flattened into a total
  • Line items matched to your catalogue with that customer's contract pricing applied
  • Anything ambiguous is flagged for a human rather than guessed at
  • Revised POs reconcile against the original instead of creating a duplicate
PO-88214.pdf → order
PO number88214
In-hands14 Sep
Heavyweight tee · NavyMatched · contract price1,200
180
S
420
M
400
L
200
XL
Fleece hood · CharcoalTwo products match this descriptionReview
Lines read9 of 10 confirmed

Voice

It answers the phone.

The same agent, on the same brain, taking calls. It knows your products, your pricing and the customer on the line — so a call at 6:40pm becomes a request in the system instead of a voicemail somebody listens to tomorrow.

You decide when it picks up.

Nobody wants a robot answering every call. So the rules are yours: which hours it takes, whether it only catches overflow when the line is busy, which numbers it never answers, and who it hands off to.

  • 01Schedule. After hours, weekends, lunch cover — or never, until you say so.
  • 02Overflow. Picks up only when the call has rung out or everyone is already on a line.
  • 03Transfer numbers. Route by reason — new enquiries to sales, order status to the front desk, anything urgent to a mobile.
  • 04Warm handoff. When it transfers, the person picking up already has the caller, the account and what's been said.
  • 05Always a way out. A caller who asks for a person gets a person.

Every call is transcribed and filed against the customer and the order, the same as an email thread. If the caller describes a job, it comes out as the same structured request — quantities, sizes, decoration, dates — and joins the same queue, with the same chase-what's-missing behaviour.

Call · Tue 18:42 · 4m 11s
CallerMatched to account
ReasonNew enquiry

“We need about 150 hoodies for a staff event, left chest logo, need them the week of the 22nd.”

CapturedQty · decoration · date
Still neededSizes · artwork
Follow-upEmailed at 18:47
TranscriptFiled to account

Outside answering hours the same call would have gone to voicemail and been actioned on Wednesday.


Also on the agent

The work that happens after the quote.

Reading the enquiry is the visible half. These are the jobs it does once the order is real.

01

Mockups

Places the logo on the real garment at the real print size, using the supplier's own size chart. When somebody nudges it by hand, that correction becomes how it places the next one.

02

Machine scheduling

Puts the embellishment stage on a press that can actually run it, on a day with capacity, respecting colour limits and minimums. Override it whenever you like.

03

Chasing, on a timer

Drafts the follow-up when a customer goes quiet, reminds an approver at 48 hours, asks for a production sample photo before a long run ships, and builds the quote the moment a request hits 100%.


Control

You choose how much rope they get.

Nobody sensible hands a new hire the keys on day one, and an agent is no different. InkIQ runs at one of three levels, set per account and changeable at any time.

  • 01Manual. It prepares everything and sends nothing. A person reviews and clicks.
  • 02Hybrid. It handles the routine chases itself and escalates anything with a decision in it.
  • 03Autonomous. It works the queue end to end and messages you when it hits something it hasn't seen before.

Every outbound action is logged with what it did, why, and what it read to decide. Confirmation gates sit in front of anything that reaches a customer.

Request 8812 · Cedar Park Schools
ProductMatched · preferred vendor
Artwork3 files read
Colours4
SizesMissing
Ship-toMissing
Complete72%

Drafted follow-up: “Happy to get this priced today — could you confirm the size breakdown and the delivery address? The artwork you sent is print ready.”

ScheduledSend in 2 h

Learning

They get better because your people correct them.

Not by training on your data in a shared model. By writing down what happened in your account, for your account only.

?

When it doesn't know, it asks

In autonomous mode it messages the owner with the specific question and the context behind it. The answer becomes a rule it applies from then on.

When you fix it, it notices

Move a logo, rewrite a draft, change a price on a quote it built — the difference between what it proposed and what shipped is captured automatically.

Nobody else sees your business

Rules learned in your account apply only in your account. The work improves the system's judgement over time, but your artwork, pricing and customer data are never shown to another company or reproduced outside your account.


The obvious question

What happens when it gets something wrong?

It will. Any shop owner evaluating this is really asking one thing: what does a mistake cost me, and how would I even know? Straight answers.

Can it send a wrong price to a customer?

Only if you let it. Out of the box the agent prepares and a person sends. Even at the most autonomous setting, anything that reaches a customer can sit behind a confirmation, and pricing isn't invented — it's your table, applied. If the table doesn't cover a case, it escalates rather than improvising a number.

What if it reads the artwork wrong?

Colour counts and stitch estimates are shown as findings you can see and change, next to the file they came from, before anything is quoted. Where it isn't confident — a gradient that may or may not be halftones, small text that may not hold — it says so in the finding instead of committing to a number. It also tells you when a customer's own description disagrees with the file, which catches more errors than it causes.

What if it picks the wrong product?

When two catalogue products plausibly match a description, it flags both instead of choosing. "Two products match this description" is a normal outcome, not a failure — the aim is a system that hands you the ambiguous 10% rather than one that quietly guesses on all of it.

How would I know a mistake happened?

Every action is logged with what it did, when, on whose behalf, and what it read to decide. If a customer asks why they received something, you can answer precisely rather than reconstructing it. Requests that escalate appear as work waiting for a human, not as silent failures.

Does it get better, or does it make the same mistake forever?

Corrections are captured. When someone rewrites a draft, moves a logo or changes a price on something the agent built, the difference between what it proposed and what shipped is recorded and applied next time — in your account only. Answers you give it when it escalates become rules it follows from then on.

What does it do when it genuinely doesn't know?

It asks, and it says what it's unsure about rather than producing a confident-sounding guess. In autonomous mode that's a message to the owner with the specific question and the context behind it. A system that stops is worth considerably more than one that's right most of the time and never tells you which times.


The assistant

Ask them about your own shop.

The same agents sit in a panel beside whatever you're working on. They know how the software works and can query your actual data, so the answers are about your business rather than a help article.

“How many black heavyweight tees in size small did we embroider with a left-chest logo last quarter, and what was the average margin?”

It can also do things: create a task, draft a follow-up, build a quote, start a mockup — each behind a confirmation, each written to the audit log. Send it a screenshot when something looks wrong and it will tell you what it's looking at.

Assistant · this morning

Daily brief · 07:00

Four jobs are due to ship today and one is short 24 pieces in XL — the supplier confirmed a Thursday restock, which misses the in-hands date. Two approvals have been sitting with customers for more than 48 hours. Cash collected last week was ahead of the four-week average; two invoices crossed 60 days.

4
Ship today
2
Approvals late
1
At risk
38.1%
Wk margin

Watch it do the job.

Send us one real enquiry — the email, the purchase order, the artwork, the messy bits — and we'll run it through the agents in the first ten minutes of the call. That's a faster argument than anything we could write here.