Exemplary AIEnterprise
For creatorsDemoBook a demo
Agents

Agents with real authority, and real boundaries.

They plan, call your tools and finish multi-step work — inside the permissions, guardrails and budgets you set. Deployed on your own infrastructure.

Talk to us
Six configuration surfacesGrounded by defaultRuns on-premise
Ask the agent to run a workflow…
Animated demo: an agent turns a prompt into a weekly sales report delivered to Slack.
Anatomy of an agent

Six decisions, not a prompt box.

Every agent in the platform is configured across the same six surfaces. Walk them in order and you have described precisely what the agent is, what it knows, and what it is permitted to do.

Agents/Compliance OfficerPrivate

On this page

Identity
Behaviour
Knowledge & Privacy
Tools & Integrations
Models
Limits & Budgets

Identity

E

Agent name

Compliance Officer

Description

Expert compliance assistant for ISO 27001:2022 ISMS and SOC 2 management.

Greeting message

I can help you manage your ISO 27001:2022 and SOC 2 compliance programme. Ask me about posture, gap analysis, policy drafting, or audit readiness.

Agent type

GeneralCreativeLegalMedicalEducation
Changes are saved when you click Save.Save changes

1. Identity — how it introduces itself

  1. Identity — how it introduces itself

    Name, avatar, description, and a domain template (general, creative, legal, medical, education) that seeds the agent's register. This is the part end-users actually meet.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Identity

    E

    Agent name

    Compliance Officer

    Description

    Expert compliance assistant for ISO 27001:2022 ISMS and SOC 2 management.

    Greeting message

    I can help you manage your ISO 27001:2022 and SOC 2 compliance programme. Ask me about posture, gap analysis, policy drafting, or audit readiness.

    Agent type

    GeneralCreativeLegalMedicalEducation
    Changes are saved when you click Save.Save changes
  2. Behaviour — instructions and skills

    The system prompt, the instruction modules layered on top of it, and the reusable skills the agent carries or loads on demand.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Behaviour

    System prompt

    ## Working method

    Prefer graph-aware tools over raw queries.

    Cite the control or clause behind every answer.

    Active instruction modules

    Knowledge GuardrailGeneral HeaderTool Usage Policy

    Skills

    Evidence assessmentAttached
    Policy exception reviewAttached
    Changes are saved when you click Save.Save changes
  3. Knowledge & Privacy — what it may read

    Which bases and datatables it can reach, whether it is confined to your files, and whether personal data is masked before it ever reaches a model.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Knowledge & Privacy

    Knowledge base guardrail

    Protected Mode · Secure

    Base & DataTable access

    Compliance ManagementViewer
    Control registerViewer

    Data protection

    PII Masking · BetaWorld Knowledge · off
    Changes are saved when you click Save.Save changes
  4. Tools & Integrations — what it may call

    Scoped tool permissions, MCP servers, assigned workflows, and chat-platform bots. Permission is granted per scope, not per agent.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Tools & Integrations

    Tool permissions

    base:*datatable:*data:*model:usecompliance:Readmore

    Tool loading

    Search FilesPreloaded
    Read File ContentPreloaded
    Search Text in FilePreloaded

    Integrations

    MCP serversWorkflowsSlack bot
    Changes are saved when you click Save.Save changes
  5. Models — and what happens when one is down

    An ordered stack rather than a single choice. The default answers first; the rest are tried in order behind it.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Models

    Model configuration

    1Gemini 3.1 ProDEFAULT
    2GPT-5.2
    3Gemma 4 (open weights)

    Models are tried in order. The default model is used for initial responses.

    Temperature

    Top P

    Changes are saved when you click Save.Save changes
  6. Limits & Budgets — the ceiling it works inside

    Step, tool-call and token caps, a soft timeout, and when context gets compacted. An agent that cannot run away is an agent you can leave running.

    Agents/Compliance OfficerPrivate

    On this page

    Identity
    Behaviour
    Knowledge & Privacy
    Tools & Integrations
    Models
    Limits & Budgets

    Limits & Budgets

    Budget preset

    StandardExtendedCustom

    Effective values

    Max steps per turn20
    Max tool calls per turn25
    Max duplicate identical calls3
    Max resource scope per query3
    Max subagent depth3
    Soft timeout5 minutes
    Changes are saved when you click Save.Save changes

Agent settings: one surface at a time, in the order the console lists them

Mode & delegation

Some agents answer people. Some answer other agents.

An agent's mode decides who is allowed to call it and what it does with work it cannot finish alone. Pick a mode to see the shape it creates.

Standalone — Operates directly with end-users and tools.

In standalone mode a support engineer messages the runbook assistant directly, and the agent calls its own file tools. Nothing sits in between.

messagescalls
End userSupport engineer
AgentRunbook assistant
Toolfile:*
  1. End userSupport engineer
    messages
    AgentRunbook assistant
    then
  2. AgentRunbook assistant
    calls
    Toolfile:*

Mode is a per-agent setting, not a plan tier. The same agent can be promoted from standalone to hybrid the moment an orchestrator has a reason to call it.

Behaviour

Instructions that don't drift.

An agent's system prompt is the part everyone edits and nobody reviews. The platform layers it: your instructions sit on top of modules the workspace enforces, so the guardrails cannot be prompted away.

Knowledge Guardrail

Confines answers to your indexed files and requires a citation for each one.

General Header

Workspace-wide framing every agent inherits, so register stays consistent.

Tool Usage Policy

How and when to reach for a tool — and when to ask a human instead.

Active instruction modules are applied by the workspace, above whatever the agent's own prompt says.

skill_guidelines.md

# How to write a 10x skill

1. Define exact boundaries

Bad: “Be helpful.”

Good: “Never modify the production database unless explicitly requested.”

2. Specify the output format

Bad: “Give me the results.”

Good: “Output the results as a JSON array of objects.”

Same input, same answer, twice
Instructions

Write constraints, not encouragement.

Agents perform best when they know exactly what they may not do. Vague warmth produces vague behaviour; explicit boundaries and named output shapes produce the same answer twice.

  • Define the exact output structure you expect
  • State the negative constraints, not just the goals
  • Give one worked example over three paragraphs of tone
Reusable expertise

Write the playbook once. Attach it everywhere.

A skill packages instructions, and optionally the tools they need, into something an agent can carry in every prompt or load on demand from its skill index. Author it once and every agent that should follow it, does.

A skill is three parts: a human name and an immutable slug, a when-to-use rule the model reads to decide whether the skill applies, and a Markdown body holding the method.

1. Author it once

Skill library/New skill
Draft

Create a skill

Reusable instructions for agents.

Name

Incident response brief

Slug

incident-response-brief

When should an agent load this skill?

Use when the request concerns an active security incident, incident triage, or an executive response update.

Category

Security operations

Activated tools

2 approved tools
Ready to publish to the shared libraryCreate skill
InstructionsMarkdown

# Incident response brief

 

## When to use

Use for security incidents, triage updates, or requests for an executive brief.

 

## Working method

1. Establish scope and severity from the available evidence.

2. State facts separately from assumptions.

3. Surface the next accountable action and owner.

Approved tools

2. Attach it per agent

Agents/Operations copilot

Agent setup

Identity
Behaviour
Skills
Knowledge & Privacy
Tools & Integrations
Models
Limits & Budgets

Skills

Attach reusable guidance this agent can load as requests require it.

Attach skill
Library skillStatus
Incident response briefSecurity incident or executive update
2Loaded
Evidence assessmentAssess source reliability or gaps
1Available
Policy exception reviewReview a request against policy
2Available
The agent loads a matching skill only when its rule applies.

Give every agent a focused skill set.

Attach published skills from the shared library to compose a specialist without rewriting its system instructions — and without every agent carrying every instruction.

  • Attach a published skill to one agent or a repeatable role
  • Update shared guidance once, not per agent
  • Pair expertise with only the tools it is allowed to use

Agents inherit the workspace's default language and answer in 120+ others when the conversation calls for it.

Tools & permissions

Capability is granted by scope, and paid for in context.

Every tool an agent can call is a permission you granted and a slice of its context window. The platform separates the two decisions: what it may do, and what it should carry with it.

Tool loading

Preloaded tools are always available to the agent. Discoverable tools are found on-demand via search, reducing initial context size.

DATA

FILES

MODEL

Context window at start of chat

7 of 12 tools preloaded

Tool definitionsRoom for the conversation
InstructionsTool definitionsRoom for the conversationProportions illustrative

Every preloaded tool spends context before the user has said anything. Discoverable tools cost nothing until they are needed.

Enabled scopes

base:*datatable:*data:*model:usecompliance:Readfile:*folder:*

Wildcards grant a family; an explicit verb like compliance:Read grants exactly one. Anything not listed is denied — there is no implicit access.

MCP integrations

Reach external services through MCP servers you connect — 170+ available, plus any server you host yourself.

Workflow assignments

Assign workflows users can trigger from this agent's chat, surfaced as a Run a workflow button.

Chat platform bots

Connect the same agent to Slack so it answers in the channel where the work already happens.

Rich output

Let the agent render inline charts, KPI cards and tables in chat. Off by default — when disabled, no extra tool or instructions load, so the agent stays lean.

Browse the tools they can call
Past the first agent

The tenth agent is a configuration, not a project.

Every agent here is the same six decisions, drawn from one skill library and one set of scopes. The second one starts from a working configuration, not a blank page. The tenth can be the one the ninth calls. Work that could never justify a system of its own becomes work you can hand over.

Guidance you write once is carried by every agent that should follow it, and you change it in one place.

An agent that cannot run away is an agent you can leave running.

Work that runs while nobody is watching still ends at a person, because the orchestrator holds the result until someone approves it.

Knowledge & privacy

An agent that cannot invent is an agent you can audit.

Grounding is not a prompt instruction here — it is a mode. Protected Mode confines the agent to what you gave it and makes every answer carry its source.

QuestionFrom the user
Your indexed filesProtected Mode
AnswerWith a citation
Model's own knowledgeBlocked by default

Protected Mode

Secure
  • Only responds with information from uploaded files
  • Provides mandatory source citations
  • Ensures accurate, verifiable responses
  • File and folder tools are automatically enabled

Allow Web Search Citations

An explicit opt-in. When enabled the agent may search the web and show web citations alongside your file references — never instead of them.

Base & DataTable access

Grant an agent structured data the same way you grant a person: per resource, with a role.

Compliance Management

Base · All datatables

Viewer

Control register

DataTable · Read only

Viewer

The agent can use tools on these resources, but they never appear in the user's sidebar — access to an agent is not access to your data.

PII Masking

Beta

Mask sensitive values — tax IDs, government numbers and other personal data — before anything is sent to the model.

Tax ID → ●●●●Government number → ●●●●Contact detail → ●●●●

World Knowledge

Off by default

When enabled, the agent may use the model's own knowledge or visual judgment, but only for knowledge-graph tasks you annotate, and always with a caveat shown to the user.

It is layered on top of the knowledge guardrail. It never turns the guardrail off.

  • Runs in your own infrastructure
  • No data leaves for inference
  • Air-gapped deployment supported
  • Full audit trail per answer

Grounded, masked, cited — and none of it leaves your network.

SOC 2 Type IIAICPA
HIPAACompliant
GDPRReady
ISO 27001Certified
Ground them on your own graph
Models & budgets

One agent, an ordered stack of models.

Choosing a model is a decision you will want to change. So it is a list, not a field — and the ceilings the agent works inside are set in the same place.

Model configuration

  1. 1

    Gemini 3.1 Pro

    Highest reasoning quality

    DEFAULT
  2. 2

    GPT-5.2

    Balanced quality and speed

  3. 3

    Gemma 4 (open weights)

    Runs local — the air-gapped floor

Models are tried in order. The default model is used for initial responses.

Sampling

Advanced settings

Temperature

Controls randomness. Lower is more deterministic.

Top P

Controls diversity via nucleus sampling.

Both are per-agent, and both are the reason a compliance agent and a drafting agent should never share a configuration.

Limits & budgets

Budget here means work, not money: how many steps, tool calls and tokens one chat turn may consume before the agent has to stop and report back.

Standard — Chat, Q&A and single-document tasks. Inherits the tenant defaults — right for most agents.

Max steps per turn
20
Max tool calls per turn
25
Max duplicate identical calls
3
Max resource scope per query
3
Max subagent depth
3
Soft timeout
5 minutes
Compaction buffer
20,000 tokens
Auto-compact at
85% of context
Per-chat token cap
Set per workspace

Every value is a per-agent override, not a product ceiling, so a drafting agent and a compliance agent never share a budget.

Built, not theorised

The agents we already run.

The six surfaces above are not a spec sheet. They are how we configured these, and each one runs in production on the customer's own infrastructure.

Most deployed

Medical OCR & document intelligence

Clinical documents, prescriptions, lab reports and insurance forms turned into structured, coded data — with medical named-entity recognition and EHR/FHIR mapping behind it.

  • 99.2% extraction accuracy on clinical documents
  • Medical NER and entity linking, not generic OCR
  • EHR / FHIR mapping and pre-built connectors
  • HIPAA-aligned, deployed inside the hospital network
One lab report, extractedIllustrative

Lab report · PDF

Structured · FHIR

Patient
Masked
Diagnosis code
ICD-10 · E11.9
Specimen date
2026-03-11
Result
6.4 mmol/L

Compliance Officer

Runs an ISO 27001:2022 ISMS and SOC 2 programme: gap assessments, risk analysis, policy drafting, evidence review, audit preparation. It reads a typed compliance graph rather than guessing from documents.

Media & content intelligence

Transcription, translation and drafting across 120+ languages with speaker diarization — built for newsrooms and broadcast feeds where speed to publish is the metric.

Same six surfaces

Build your own

Nothing above used a private API. Same six surfaces, same guardrails, same on-premise deployment — pointed at your domain instead of ours.

Every one of these started as an empty agent and six decisions. That is the whole product.

See the same six surfaces pointed at three other domains
From empty to in production

How an agent actually ships.

Creating the agent is the quick part. What makes it safe to hand to three hundred people is everything after it.

  1. 01

    Create

    Name it, give it a description and a domain template, and point it at a filestore. It exists, and it can do nothing yet.

  2. 02

    Configure

    Work the six surfaces: instructions and skills, what it may read, which scopes it may call, its model stack, its budget.

  3. 03

    Grant access

    A private agent is invisible until a group is granted it. Access is a deliberate act, per group — never a default.

  4. 04

    Share as a package

    Bundle the agent with the bases, skills and tools it depends on, so the same working configuration lands in another workspace intact.

  5. 05

    Watch it, then tighten it

    Usage, latency and cost per agent come back as telemetry. Raise the budget where it earns it and cut the tools it never called.

See Exemplary AI in action

Book a demo and we'll show you purpose-built agents grounded in your own knowledge — deployed on your infrastructure.

Book a demo
Exemplary AIEnterprise

Agentic AI for the enterprise — installed inside your network.

  • Sovereign deployment
  • Purpose-agnostic agents
Book a demo

Build

  • Agents
  • Model Hub
  • Knowledge Graph
  • File store

Connect

  • Integrations
  • Chatbots
  • Browser Extension

Govern

  • Management
  • Groups
  • Analytics

Company

  • About Us
  • Exemplary for creators
  • Book a demo

Use cases

By industry
  • Healthcare
  • Government
  • Financial services
  • Legal
  • Media
By department
  • Customer Support
  • IT & Engineering
  • Human Resources
  • Finance & Procurement
  • Compliance & Risk

© 2026 Exemplary AI. All rights reserved.

  • SOC 2 Type II
  • HIPAA
  • GDPR-ready
  • ISO 27001