IndustriesServices

Every case is read, sorted, and answered by hand.

Calls, messages, and complaints arrive faster than the team can read them, and each client's rules for the answer are different. We build small language models that read and sort every case, and agents that prepare the answer for the team lead who signs.

Start with a Decision BlueprintTalk to the engineer
FIG. 1 · Routed complaintIllustrative
Client B (retail) · complaintLate delivery

Agent · facts from the client's systems

  • DeliveryPromised date passed by 12 daysAPI

SLM · client B's policy and reply

  • ClauseDelay over 10 days → voucher per the matrixclient policy §3
  • ProposedVoucher within the matrix, from the calculator
  • ReplyDraft in client B's tone
  • SLM
  • Agent

Why a person decidesNot a template case, so the drafted reply goes to the team lead.

DecidesTeam lead

From the use case: Outsourced complaints desk

Use cases in this sector

The desks we build for here.

  • SLMsAgentic AI

    Contact-center speech: quality and compliance on every call

    TodayEvery call is recorded, quality hears two in a hundred, and off-the-shelf speech-to-text mangles your product names.

    With the systemEvery call checked for quality and compliance; the coaching point in context.

    Team lead decides

  • SLMsAgentic AI

    Agent assist

    TodayNew call-center agents take months to be productive and put customers on hold to search the knowledge base.

    With the systemAnswers drafted while the customer is on the line.

    Call-center agent decides

  • SLMsAgentic AI

    Outsourced complaints desk

    TodayOne team answers written complaints for several clients, each with its own rules, tone, and deadlines.

    With the systemEach reply drafted in the client's own rules and tone.

    Team lead decides

These use cases describe systems we build, written from how these desks work. They are not past client projects: no client names, no results.

The sector

What is different here

The way of working stays the same. These four things change with the sector.

Data
Call recordings, chat and email, complaint histories, and each client's own policies and reply templates.
Who signs
The team lead, the call-center agent on the call, or the desk supervisor. Replies outside a client's approved templates wait for a team lead, and a quality score is advisory.
Where it runs
On your servers or your cloud account; audio stays in your environment.
Rules you work under
  • Each client's own policy, reply deadlines, and compensation matrix
  • One model per client where the desk serves several; no client's data trains another's
  • A recording notice and a lawful basis for every call; no voiceprints
  • Staff scoring that is transparent to the people scored

Where it runs, what it connects to, and who can reach it

Kinds of AI

The three kinds of AI here

Each works on its own; they stack where the decision needs more.

  • Estimate

    Machine-learning models

    Machine-learning models fit where a number decides, such as forecasting volume; the desks on this page start without one.

    How it works

  • Understand

    Small language models (SLMs)

    Small language models read and sort every message, and a speech recognition (ASR) model turns each call into text for review.

    How it works

  • Prepare and act

    Agentic AI systems

    Agents check each case against the client's rules and prepare the reply for the team lead.

    How it works

Equalize the gap.

Bring one decision. Leave knowing the first step.

A short description of the decision is enough; no confidential records.

Start with a Decision BlueprintTalk to the engineer

https://eqlx.ai/industries/service-industries · Printed copy; the website is the current version.