Advanced projects

A flow defines how an agent behaves on a call (or web/text session). Nairon has two project types built on two flow types:

• Simple project — a guided setup: an industry or use-case template plus skills you switch on and off (business information, knowledge Q&A, callback, and more). No branching logic or hooks. See Simple projects.
• Advanced project (Graph Flow) — a node-and-edge conversation graph with full control over branching, tool calls, and a growing set of Professional/Enterprise capabilities (code snippets and more node types coming soon — see Pro-flow nodes below). The rest of this page describes the graph flow editor’s model. See the practical guide.

Note

When you create a project, a project-type picker lets you choose between a Simple project and an Advanced project — both are available in v1.3, so a new project can be created as either.

Editor stages

The graph flow editor is organized into stages, navigated via tabs:

Stage	Content
Setup	Flow identity (who the agent is / its role) and the attached agent profile.
Before	The pre-hook tree — logic that runs before the conversation graph starts.
During	The conversation graph itself (nodes/edges) plus global tools.
After	The post-hook tree and the end-of-call survey toggle.
Test	Test-call launcher and simulation batch launcher/results for this flow.

Variables

A flow has variables — named slots that hold data for the duration of a call: values captured from the caller, values looked up from an integration, or values computed in a hook. Alongside user-created variables, the editor exposes a read-only set of system variables always available to reference in node text and hook logic: call_start_time, current_time, caller_phone_number, and invocation_type (isPhoneCall / isTextSession / isVoiceSession). Variables are referenced in node text with {variable_name} interpolation.

Pre-hooks and post-hooks

Hooks are small trees of nodes that run before the conversation graph starts (pre-hook) or after it ends (post-hook) — the place to do lookups, set variables from external data, or write results back out, without cluttering the conversation graph itself.

Each hook node has exactly one action:

• Integration lookup (pre-hook) — crm_lookup_phone, crm_lookup_email, calendar_check_availability, calendar_get_slots, or knowledge_query against a connected integration, storing the result into a variable.
• Integration write (post-hook) — crm_store_transcript, crm_store_note, calendar_schedule_meeting, calendar_cancel_booking.
• Set variable — assign a literal or computed value.
• Condition — branch on an expression, with separate true/false transitions.
• Webhook — call an arbitrary HTTP endpoint (method, headers, body template, and optionally store the response into a variable).
• Code snippet (Professional/Enterprise, coming soon) — a short snippet with read/write access to named variables. See Code snippets for the full picture.

A pre-hook tree terminates either by continuing into another hook node or by entering the conversation graph at a chosen start node (letting different lookup outcomes route into different opening nodes). A post-hook tree terminates at the end of the call handling.

Global tools

Global tools are flow-level capabilities available as dynamic tools on every conversation node (except any explicitly excluded): a callback routine (offer to call the user back, backed by a calendar integration), forward + callback fallback (transfer to a human, falling back to a callback offer if unavailable — the live transfer itself is coming soon, see Call forwarding), and a global menu.

Pro-flow nodes

Professional and Enterprise projects get extra capability on the same graph flow type — there’s no separate “pro flow” flow type, just additional node kinds gated to those plans:

• Code snippet (see Pre-hooks and post-hooks above and Code snippets) is coming soon, both as a hook step and as a conversation-graph node. Flows that already contain a snippet keep it.
• Evaluation, logic, and abstract node types are built into the editor’s data model and coming soon: they aren’t offered in the node picker yet, so a flow can’t add one today.
• The Authentication node (see Authentication node) gates a step of the graph behind an identity check against an Auth Directory — a “critical section” that can’t be reached without passing the check first. It’s in preview; see that page for details.

Survey

A flow can enable an end-of-call survey: a rating question and free-text feedback, asked at hangup, before post-hooks run (so a post-hook can read the resulting rating/feedback into an integration write). Survey results appear per-call in call history and are aggregated in analytics.

Versions and publishing

Every save creates a flow version; exactly one version is active at a time. Activating a version is what a running number’s calls will use — the compiled flow goes live whenever a version is activated, typically within a few seconds.