Skip to content
QuorlyticTalk to a Data ExpertContact
Menu

Capability / AI agent development

AI Agent Development Services

AI agent development is the engineering of software that uses a language model to decide which tool to call next in order to complete a task. Quorlytic builds agents connected to internal company data that act with the requesting user's permissions, use a small set of scoped tools, require approval for irreversible actions and record every consequential step.

By QuorlyticUpdated

An agent that can call tools is a system with authority, so the authority is designed first. Start with a bounded task, the smallest useful set of tools and a clear rule for what needs a human's approval.

Request

  • Task from a userIdentity, role and purpose travel with it

Per-user permissions · step and cost limits

  • Planning modelChooses the next step
  • Scoped toolsSearch · read · draft · update

Action

  • ReversibleRead and draft: runs
  • IrreversibleSend, delete, pay: approval first
  • Audit trailTools, data read, approver
  • EvaluationStop, escalate and refuse cases
AI agent with controls: a request carries the user's identity into a planning model that calls scoped tools inside per-user permissions and step limits; reversible actions run, irreversible actions wait for approval, and every step is recorded and evaluated. A typical shape, not a client implementation.
01

The business problem

An agent earns its complexity only when the path through a task varies and cannot be scripted in advance. If the steps are known, a deterministic workflow is cheaper to run, easier to test and simpler to audit; if the task is answering questions, a search assistant with no write access is enough. Most first deployments should be read-only, with autonomy added where the measured benefit justifies the controls it needs.

02

What we build

The common thread is an agent working inside an organisation's own systems and data, under the same access rules people already have. Typical builds include agents that answer and act across internal documents and databases, agents that prepare work for a person to approve, and agents that query governed warehouse data through an agreed semantic layer rather than raw tables.

03

The outcome

A bounded agent in production with per-user access, approval gates and an audit trail

Agent run trace

One agent task, followed through every control.

A production agent is judged by what it did and on whose behalf. The trace follows a single task from request to record: identity, plan, tool calls, the action that needed approval and the audit entry it left behind.

Agent run trace
  • Service desk agent
  • Read and draft
  • Approval required to send
  1. RequestA support lead asks for a refund summary on an open ticketLogged with the user, role and purposeReceived
  2. IdentityTask runs with the support lead's permissionsNo shared service accountScoped
  3. Tool callRead ticket and order historyAllow-listed read tools onlyTwo records read
  4. DraftRefund summary and a proposed customer replySources attached to the draftDrafted
  5. Proposed actionSend the reply to the customerIrreversible, so approval is requiredAwaiting approval
  6. RecordInputs, tools, data read and approver loggedRetained for audit and reviewRecorded
The agent drafts and proposes; a person approves anything that cannot be undone.

What it answers

  • Whose permissions did the agent use?
  • Which actions did it take on its own?
  • Who approved what it sent?
Talk to a Data Expert about AI agents

When this is the right engagement

Symptoms that bring teams here.

These are the situations in which an AI agent is worth building, and the ones that usually mean a simpler tool will do.

  • People copy information between the same systems every day

    A bounded, repetitive task across known tools is where an agent with scoped access earns its place.

  • A pilot chatbot answers well but cannot do anything

    The next step is controlled action: scoped tools, approval gates and an audit trail.

  • The agent demo used an admin account

    In production it must act with each user's permissions, or it becomes the easiest way to leak data.

  • Nobody can say what the agent did yesterday

    Without a trace of tool calls, data read and approvals, an agent cannot be operated or trusted.

  • Every step of the process is already known

    A deterministic workflow will be cheaper and easier to test than an agent. Start there.

  • Security has blocked the AI project

    The objection is usually access and audit. Designing those first is what gets an agent approved.

Capability model

What a production agent needs.

A production agent is five engineered responsibilities around a model. Select one to see what it involves and what it produces.

01 — Task

Bound the job: who asks, what the agent may do, what success looks like and what failure costs.

What it produces

A written task definition with the actions the agent may and may not take.

AI agents: when autonomy works

What usually goes wrong

  • A general assistant with no defined task
  • No agreed definition of done
  • Autonomy chosen before the failure cost is known

Technologies in this stage

  • Task definition
  • Success criteria
  • Failure-cost review

Reference architecture

An agent inside its controls

The model sits in the middle, but most of the architecture is the control around it: identity carried into every call, scoped tools, a gate on irreversible actions and a record of everything consequential.

  1. Request with identity

    The user's identity and role travel with the task.

    • SSO
    • Role
    • Purpose
  2. Planning model

    Decides the next step within the task's limits.

    • Step limit
    • Cost limit
    • Task scope
  3. Scoped tools

    Purpose-built actions, never raw admin access.

    • Search
    • Read record
    • Draft
    • Update
  4. Company data

    Read with the user's permissions, enforced at source.

    • Documents
    • Warehouse
    • CRM
    • Ticketing
  5. Approval gate

    Irreversible actions wait for a named approver with the evidence.

    • Send
    • Delete
    • Pay
    • Publish
  6. Audit and monitoring

    Every consequential action recorded and watched.

    • Tool calls
    • Data read
    • Approvals
    • Cost

Across every step

  • Per-user permissions
  • Evaluation set
  • Step and cost limits
  • Exercised rollback
Reference architecture: a user request carries identity to a planning model, which calls scoped tools over company data; reversible actions run, irreversible ones wait for approval, and every step is evaluated and recorded. It shows a typical shape for discussion, not a prescribed stack or a client implementation.

The approach

  1. 01

    When a task needs an agent, and when it does not

    An agent earns its complexity only when the path through a task varies and cannot be scripted in advance. If the steps are known, a deterministic workflow is cheaper to run, easier to test and simpler to audit; if the task is answering questions, a search assistant with no write access is enough. Most first deployments should be read-only, with autonomy added where the measured benefit justifies the controls it needs.

    The interaction patterns are compared in depth in AI agents: when autonomy works.

  2. 02

    Agents we build on company data

    The common thread is an agent working inside an organisation's own systems and data, under the same access rules people already have. Typical builds include agents that answer and act across internal documents and databases, agents that prepare work for a person to approve, and agents that query governed warehouse data through an agreed semantic layer rather than raw tables.

    • Internal-knowledge agents combining retrieval with scoped actions
    • Workflow agents that draft, check and route work for approval
    • Data agents that query governed models through a semantic layer
    • Agents connected to CRM, ERP, ticketing and document systems through allow-listed tools
  3. 03

    Access is enforced per user, not per agent

    An agent acting on someone's behalf must never see or do more than that person can. Each request carries the user's identity into every tool call and data query, so permissions are enforced by the source systems rather than by instructions in a prompt. A shared service account with broad access is the most common way an agent leaks data, and it is designed out from the start.

  4. 04

    Approval gates for anything irreversible

    Read actions and reversible drafts can run automatically; sending, deleting, paying, publishing and changing records of consequence go through an explicit approval step with the evidence the agent used. Steps, tool calls and spend are capped per task, so a confused agent stops rather than loops.

    • Irreversible actions require a named approver
    • Step, tool-call and cost limits set per task
    • A defined fallback when the agent cannot complete the task
  5. 05

    Evaluation before autonomy

    An agent is tested on a task set drawn from real work, including cases where the right action is to stop, escalate or refuse, and cases where a user lacks permission. Tool selection, task completion, unsafe-action attempts, latency and cost are measured separately, and the set is re-run before every change to the model, prompts or tools.

    Retrieval quality is scored with the methods in evaluating RAG systems, because an agent that reads the wrong document acts on the wrong facts.

  6. 06

    Audit, monitoring and rollback

    Every consequential action is logged with its inputs, the tools called, the data read, who it acted for and who approved it. After launch the agent is monitored for task success, escalation and refusal rates, unusual tool use and cost, with an owner for each signal and a rollback to the previous configuration that has been exercised.

    The controls are set out as a framework in the AI agent governance guide.

  7. 07

    What drives the cost of an AI agent

    Cost is driven less by the model than by the systems the agent must reach and the controls around them: the number of tool integrations and their authentication, the condition of the data the agent reads, the strictness of the evaluation standard, the approval workflow, and the expected volume of tasks, which sets running cost. A first agent is scoped as a bounded pilot on one task, priced as a fixed scope agreed in writing.

  8. 08

    An agent is only as reliable as the data it reads

    Agents fail quietly when the documents are stale, the metrics are undefined or the permissions are wrong. That is why agent work at Quorlytic starts from the data foundation: governed models, documented definitions and tested access. The published case studies describe that foundation work for manufacturing and healthcare clients; agent engagements build on the same practice.

Delivery model

How the work is sequenced.

Four phases. Autonomy is added only where the evaluation shows it is safe.

Delivery phases: what happens, what gets decided, and the artifact each phase leaves behind
PhaseActivitiesDecisions made hereWhat you keep
Bound the taskDecide what the agent is for and what it may do.
  • Define the task, the users and success criteria
  • List the actions and classify each as reversible or not
  • Compare against a workflow or search-only alternative
  • Agent, workflow or search
  • Which actions need approval
Task definition and action policy
Scope tools & accessConnect the agent safely to company systems.
  • Build purpose-built tools over the needed systems
  • Carry the user's identity into every call
  • Set step, tool-call and cost limits
  • The tool set
  • The permission model
Tool inventory and permission model
Evaluate behaviourProve it behaves on real work.
  • Build an evaluation set from real tasks
  • Include stop, escalate, refuse and permission-denied cases
  • Measure tool choice, completion, cost and latency
  • Whether the release gate is met
  • Where human review stays
Evaluation results and release gate
Deploy & monitorRun it with an owner and a way back.
  • Release to a bounded user group
  • Monitor success, escalation, refusals and cost
  • Exercise the rollback to the previous configuration
  • Expansion criteria
  • Incident ownership
Production agent with audit trail and runbook

Technology fit

What each technology is here to do.

What is involved, by role. Models and frameworks are chosen against the task's evaluation set, not the other way round.

  • Models

    • Hosted frontier models
    • Open-weight models
    • Model gateways

    Chosen on quality, latency, cost and data-residency for the specific task.

  • Orchestration

    • Agent frameworks
    • Tool calling
    • Workflow engines

    Holds the plan, the limits and the state of a run, and makes each step inspectable.

  • Data and tools

    • Enterprise search
    • Warehouse semantic layer
    • Business APIs

    What the agent reads and acts on, under the same access rules people already have.

    Platform detail
  • Control

    • Identity provider
    • Approval workflow
    • Audit log
    • Evaluation set

    The part that makes an agent safe to run in production and possible to approve.

Technology marks belong to their respective owners. No partnership, certification or endorsement is implied.

Engineering concerns

What has to be answered before it is trusted.

What has to be true before an agent is given real work.

Least privilege
The agent never sees or does more than the person it acts for, enforced by the source systems.
Prompt injection
Retrieved text is treated as untrusted input, and no instruction inside a document can widen the agent's permissions.
Irreversible actions
Sending, deleting, paying and publishing go through a named approver with the evidence the agent used.
Runaway cost
Step, tool-call and spend limits per task, so a confused agent stops rather than loops.
Explainability
Every consequential action can be traced to its inputs, tools, data read and approver.
Data residency
Where prompts, documents and logs are processed and retained is decided before the model is chosen.

Search, workflow or agent: which pattern fits the task

Search assistant, deterministic workflow, workflow with approval and bounded agent compared by who decides the next step, authority, best fit and main risk
DimensionSearch assistant (RAG)Deterministic workflowWorkflow with approvalBounded agent
Who decides the next stepThe user; the system only answersFixed code pathsFixed code paths, with a person approving the final actionThe model, within the tools it is given
Authority it holdsRead-only, within the user's permissionsWhatever the workflow is coded to doProposes; a person commitsCalls scoped tools, with approval for irreversible actions
Best fitAnswering questions from permitted documentsKnown, repeatable stepsKnown steps with a consequential end actionTasks whose path varies and cannot be fully scripted
Main riskUnsupported or wrongly cited answersBrittleness when inputs changeApproval fatigueWrong tool calls and runaway loops

Questions

Questions worth asking.

What do AI agent development services include?

Defining a bounded task, designing the tools and the permission model, connecting the agent to internal systems with the user's identity, building approval gates for irreversible actions, creating an evaluation set from real work, and deploying with monitoring, cost limits, an audit trail and a rollback path.

Has Quorlytic built AI agents for clients?

Yes. Quorlytic has built AI agents for client teams. Client details are not published without each client's approval; the engineering approach is set out on this page and in the agent governance guide, and specific work can be discussed directly.

How much does it cost to develop an AI agent?

It depends on the number of systems the agent must reach, the condition of the data it reads, the evaluation standard, the approval workflow and the expected task volume, which drives running cost. A first agent is a bounded pilot on one task, priced as a fixed scope agreed in writing; tell us the task and the systems involved and we will give you a range.

Can an AI agent use our internal data safely?

Yes, if it acts with the requesting user's identity rather than a shared account, uses only allow-listed tools, needs approval for irreversible actions and logs what it did. Permissions are then enforced by your source systems, not by instructions in a prompt.

Do we need an agent, or would a workflow do?

If the steps are known in advance, a workflow is cheaper and easier to test. Choose an agent only when the path genuinely varies and cannot be scripted, and keep a person approving any action that cannot be undone.

Which models and frameworks do you use?

The ones that meet the task's quality, latency and cost envelope on your own evaluation set, deployed where your data-residency and security requirements allow. Quorlytic holds no partner status, reseller agreement or certification with any model or platform vendor, so the recommendation follows the task.

Next step

Discuss your first AI agent.

Describe the task, the systems the agent would need to reach and who would approve its actions. That is enough to scope a first agent.

Discuss your first AI agent