AI agent platform

Agents with a narrow job and a hard boundary

Nine business agent blueprints. Each one has an explicit tool allow-list, approved knowledge, escalation rules and a complete execution history. High-impact actions have no automated path at all.

Never available to an agent

  • Moving money or issuing refunds
  • Deleting records
  • Changing payroll
  • Signing contracts
  • Making employment decisions
  • Shell, database or unrestricted internet access

These capabilities do not exist in the runtime. A prompt cannot grant them.

Blueprints

Pick a role, then restrict it further

Blueprints are starting points with sensible defaults. You can narrow the tool list, tighten the prompt and add approval gates — never widen beyond the registry.

AI Receptionist

receptionist

Cover inbound enquiries 24/7, capture lead details and book appointments without hiring a front desk.

Granted tools
knowledge.searchleads.createapproval.requestemail.draft
Prohibited
  • Making commitments on pricing discounts
  • Booking outside published availability

Escalation: Urgent or complaint language is escalated to a human within the same conversation.

AI Sales Agent

sales

Respond to inbound interest in minutes, qualify against your criteria and hand a briefed lead to sales.

Granted tools
knowledge.searchleads.createleads.lookupleads.update_stageemail.draftapproval.request
Prohibited
  • Negotiating discounts or contract terms
  • Issuing quotes not approved by sales

Escalation: Deals above your approval threshold are routed to a human rep.

AI Customer Support Agent

support

Deflect repetitive tickets, categorise issues and draft replies your team can approve.

Granted tools
knowledge.searchtickets.lookuptickets.replytickets.createapproval.request
Prohibited
  • Issuing refunds
  • Changing billing details

Escalation: Unresolved, angry or account-security issues are escalated to a human immediately.

AI Administrative Assistant

admin

Remove inbox and paperwork overhead from operations teams.

Granted tools
knowledge.searchapproval.requestemail.draft
Prohibited
  • Deleting records
  • Sending email without approval

Escalation: Anything legally sensitive or involving personnel decisions goes to a human.

AI Finance Assistant

finance

Cut invoice processing time while keeping every payment human-approved.

Granted tools
knowledge.searchapproval.request
Prohibited
  • Initiating payments or transfers
  • Issuing refunds

Escalation: Every payment action requires explicit human approval; discrepancies are flagged.

AI HR Assistant

hr

Automate HR paperwork while keeping employment decisions human.

Granted tools
knowledge.searchtickets.createapproval.request
Prohibited
  • Ranking or rejecting candidates
  • Employment decisions

Escalation: Any hiring, discipline or termination question is routed to a human with no AI recommendation.

AI Marketing Operations Assistant

marketing

Automate marketing operations and reporting, not social media management.

Granted tools
knowledge.searchusage.reademail.draftapproval.request
Prohibited
  • Sending campaigns without consent checks
  • Purchasing ad spend

Escalation: Any audience without documented consent is escalated before any draft is produced.

AI Document Processing Agent

documents

Turn unstructured documents into validated structured records.

Granted tools
knowledge.searchapproval.requesttickets.create
Prohibited
  • Approving invoices
  • Deleting source documents

Escalation: Low-confidence extractions are routed to a human with the source reference.

AI Business Intelligence Agent

bi

Give operators a weekly read on where time and money leak.

Granted tools
usage.readknowledge.searchapproval.request
Prohibited
  • Modifying source data
  • Presenting projections as measured results

Escalation: Data quality gaps are reported rather than filled with estimates.

Tool registry

The complete tool surface

Anything not on this list cannot be invoked by any agent, regardless of what a model asks for.

ToolWhat it doesScopeImpact
knowledge.searchSearch the agent's approved knowledge base.agent.knowledgeReversible
leads.createCreate a lead record in the workspace CRM.crm.writeReversible
leads.lookupFind a lead by email inside this workspace.crm.readReversible
leads.update_stageMove a lead between pipeline stages.crm.writeReversible
tickets.createOpen a ticket and optionally escalate.support.writeReversible
tickets.lookupFind tickets for the current customer.support.readReversible
tickets.replyDraft a reply for a human to send.support.writeReversible
usage.readRead this workspace's metered usage.billing.readReversible
approval.requestAsk a teammate to approve a high-impact action.approval.requestReversible
email.draftProduce a draft only — never sends it.comms.draftReversible

Third-party writes (CRM, telephony, payments) are mediated by the workspace's own connection, encrypted at rest, and every call is logged with its arguments and outcome.

Prompt injection is treated as a data problem

Documents, emails and web pages are wrapped in an untrusted-data block with an explicit instruction that they are data, not instructions. Known injection patterns are flagged on the message and recorded in the execution log.

The real defence is that the dangerous capability does not exist. Even a successful jailbreak cannot call a tool that was never registered.

Approval with detail, not a rubber stamp

An approval request contains the account, amount, destination and consequence, plus the conversation that produced it. The approver can decide without reconstructing context.

Decisions record who approved, when, and any comment — and the run resumes from exactly that point.

See an agent work on your process

Start a workspace, install an agent blueprint and run it in simulation mode. Configure a provider key when you want real model output.

AI agents · Sonai