The Platform

One governed runtime. Every app inherits it.

Frontline isn't a chatbot builder. It's a fixed, governed runtime — knowledge grounding, policy enforcement, human approval, and signed Trust Receipts. The Architect only writes configuration; the runtime does the rest, safely.

Fail-closed by default Approved-knowledge grounding Signed Trust Receipts
Governed runtimegoverning
Visitor asks

Governed pipeline
  • Intent detected
  • Grounded in approved knowledge
  • Policy: pricing → human review
  • Human approval
  • Grounded answer sent
  • Trust Receipt minted
Grounded answer
Trust Receipt
8 governed modules
compose into any vertical app
Fail-closed
risky actions can't run un-approved
One audit trail
every run, source, and tool call

Two planes

The Architect builds it. The runtime governs it.

A clean split: describe-time generates configuration; run-time enforces it. The moat isn't the generator — it's the fixed, governed runtime everything runs on.

01
Build plane

The Architect

Turns a plain-English workflow into configuration — data model, agents, policies, and workflows. It never writes arbitrary server code, so nothing it ships can escape the runtime.

Plain-English → compiled manifest
Generates config, not code
Cheap to run — configuration, not a per-app build
Describe the workflow

“A refund desk that answers from our refund policy and escalates big refunds.”

Compiled — configuration, not code
  • Data model
  • Governed agents
  • Policies & approvals
  • Workflow
02
Run plane

The governed runtime

Executes that configuration under enforcement — grounding answers, gating risk to humans, and signing a Trust Receipt for every action.

Grounding, policy & approval enforced
Signed receipt per action
Row-level access available per tenant
Running — governed by default
Answers only from approved knowledge
High-risk action → held for a human
Signed Trust Receipt per action

Runtime modules

Eight modules. Composed into every vertical.

Not features you wire up per app — the fixed foundation the Architect configures. Grounding and governed chat run today; workflows, tool calling, and channels are available per tenant.

Agent Runtime
Specialized agents — intent, knowledge answering, capture, validation, summarization, and tool execution. Each with its own prompt, tools, and policies.
Per-agent prompts and tools · Confidence thresholds · Fallback and handoff rules
Agentic Workflows
Bounded, resumable multi-step execution with retries, durable state, branching, approval gates, and per-step checkpointing.
Durable state machines · Approval gates between steps · Crash-safe checkpointing
Knowledge Engine
Hybrid retrieval + rerank over approved-only sources. Versioned, scoped per app, refreshed on demand.
Document, FAQ, and policy collections · Per-app knowledge scopes · Source attribution on every answer
Policy Engine
Configurable guardrails: block, escalate, or require approval per topic, intent, or action — fail-closed by design.
Topic and intent guardrails · Action-level approval policies · Risk categorization
Human Approval
Route low-confidence answers and high-risk actions to human reviewers with full context before anything irreversible runs.
Approval inbox per role · Inline source preview · SLA tracking
Trust Receipts & Audit
Every AI run emits a signed, independently verifiable receipt — sources, prompts, model versions, policy triggers, and tool calls.
Per-message evidence trail · Signed & verifiable · Exportable audit log
Tool & MCP Connectors
Governed tool calling into CRMs, email, WhatsApp, calendars, sheets, ERPs, webhooks, and MCP servers — every call logged.
Webhook + REST connectors · MCP server support · Scoped, logged tool calls
App Configuration
Each app declares its data model, intents, capture fields, workflows, policies, and UI — as configuration, never a fork.
Per-app schema & entities · Templated agent sets · Reusable across customers
Governed by construction

Safety isn't a setting you can forget to turn on.

Because apps are configuration on a fixed runtime — not arbitrary code — grounding, policy, approval, and audit apply to every app by default. There's no path around them.

Config, not code
Generated apps can't bypass the runtime — there's no server code to escape into.
Enforced, not advised
Policies and approvals are checked at the write boundary, fail-closed.
Provable, not claimed
Every action leaves a signed receipt you can verify independently.