Agent Platform

Build agents that ship.

A visual builder for the ops team and an SDK for the platform team — same runtime, same shared skills, same governance. Ship an agent in an afternoon; harden it for production in a week.

Anatomy

Every agent is eleven decisions.

Change any one and behaviour changes — no rebuild, no redeploy. Every setting is versioned, evaluated, and rolled forward through the same control plane.

Identity
Identity

Its own name, email, and account. Every action attributable back to it.

Identity
Instructions

The system prompt that shapes voice, scope, and refusal behaviour.

Identity
Models

The reasoning model. Bring your own or use the platform default.

Context
Knowledge

The corpora it reads from. Grounded, cited, and refresh-aware.

Context
Memory

What it remembers across sessions — user, thread, or workspace scope.

Capability
Skills

Reusable capabilities. One skill can serve many agents.

Capability
Tools

APIs, MCP servers, and enterprise systems it can call.

Capability
Workflows

Multi-step procedures with branching, approvals, retries.

Boundary
Permissions

Scoped access — never more than the human it's acting for.

Boundary
Policies

Risk tiers that decide when a human must approve.

Boundary
Evaluation

Continuous accuracy, cost, latency, and hallucination scoring.

Two paths · one runtime

Ops teams click. Developers ship.

Both paths produce the same artefact — an agent versioned in the registry, running under the same governance model. Move between them freely as your team grows.

Visual builder

No-code for the operator

Name the agent, pick its knowledge, toggle its tools, wire its policies. Draft → test → deploy in one console. No PR, no CI wait.

  • Skill and tool toggles per agent
  • Approval-mode picker per action
  • Test on a sample thread before promoting
  • One click to publish a version
Developer SDK

Code-first for the platform team

Define agents in TypeScript. Version in git. CI runs your evals. MCP servers expose your internal tools. The runtime is the same one the visual builder targets.

  • SDK · API · CLI · MCP
  • Agents-as-code in your repo
  • Golden-set evals in CI
  • Progressive rollout by percent or cohort
Shared skills

Skills are reusable, not agent-specific.

A skill is a self-contained capability with its own instructions, tools, knowledge, inputs, outputs, permissions, and guardrails. Build once. Every agent that needs it can call it.

  • One skill · many agents · one implementation
  • Guardrails travel with the skill, not the caller
  • Skills call other skills — no reinvention
  • Versioned and rolled out on their own cadence
Search DocumentationCreate Jira TicketUpdate SalesforceSend Slack MessageProvision Okta UserReset PasswordProcess InvoiceAnalyze ContractGenerate ReportApprove AccessSchedule MeetingPost to ConfluenceQuery WarehouseSend EmailCreate GitHub IssueUpdate HubSpot
Marketplace

Install an agent. Customise it in a day.

Pre-built agents for every department. Every one is a starting point — swap knowledge, retune instructions, adjust tool access. You inherit the shape; you own the behaviour.

IT

IT Helpdesk Agent

Access requests, password resets, onboarding cascades.

Support

Customer Support Agent

Ticket triage, cited answers, refund routing.

Sales

Sales Research Agent

Account briefs, lead qualification, CRM hygiene.

HR

HR Onboarding Agent

New-hire cascades, policy answers, leave workflows.

Finance

Finance AP Agent

Invoice processing, expense review, payment routing.

Security

Security Ops Agent

Alert triage, containment, out-of-band notification.

Agent-to-agent

Agents delegate to each other.

Sales asks Engineering for a technical answer. IT asks Security for an access review. Every hop is a first-class call — logged, evaluated, and permission-checked on its own.

Human-in-the-loop

Sensitive writes wait for a human.

Policy tiers decide the gate. Low-risk reads run on autopilot. Reversible writes route to a manager. Destructive writes add step-up MFA on the reviewer.

Developer platform

Ship agents like you ship code.

Define, test, and roll out agents from a repo. Golden-set evaluations run in CI. Progressive rollout by percent or cohort. Same primitives, no glue code.

SDK
TypeScript-first, typed schemas
API
REST + streaming, OpenAPI
CLI
Test, deploy, tail logs
MCP
Serve tools to any MCP client
Enterprise-ready by default

The controls your security team is going to ask about

SOC 2 Type II
audited annually
GDPR
EU data residency
SSO / SAML
Okta · Entra · Google
SCIM 2.0
auto-provision
Agent Identity
own account, own audit trail
Approval Policies
low / medium / high tiers
Audit Log
every action, immutable
Zero training
your data stays yours
Bring your model
Anthropic · OpenAI · self-host
Bring your key
AES-256-GCM at rest
Rollback
every write reversible
99.9% uptime
SLA on Enterprise

Start with one agent. Grow to a workforce.

Book a demo and see the builder plus the SDK on your own systems. First agent live in an afternoon.