Core Concepts

A quick map of the vocabulary used across Nexrall's docs.

Agent

An agent is a loop that reasons, calls tools (read/write files, run commands, call APIs), observes the result, and repeats until the task is done or it needs your input. Nexrall runs this loop in a few different shapes:

• The coding agent (Fullstack Agent Coding, Nexrall Code, Nexrall CLI) — reads/writes a file tree, runs commands, tests its own work.
• A workflow sub-agent — a narrower agent scoped to only the tools a workflow node grants it.
• The Canvas agent — writes a single self-contained document/artifact (report, deck, chart) rather than a full app.

Session

A session is one continuous conversation with an agent — the chat history, any files or artifacts it produced, and its progress ledger (see below). Sessions persist so you can close the tab and come back later without losing context.

Progress ledger

Long-running agent work is prone to "context rot" — summarizing a summary until the original goal gets fuzzy. Nexrall's agents maintain a progress ledger: a structured, machine-tracked record of what's been touched (files edited, tests run and their pass/fail result) that survives context compaction, pinned next to the original task description. This is what lets an agent work through dozens of turns without drifting or "forgetting" a failed test.

Workflow

A workflow is a graph of steps — a trigger, then nodes like HTTP calls, conditions, transforms, or sub-agents — built by describing it in chat to the Agent Builder. Workflows run on a deterministic execution engine, not an LLM improvising each time: the same graph produces the same behavior every run, and you can dry-run it before it goes live.

Trigger

A workflow starts from a trigger — manual (you run it), a webhook (an external system calls a unique URL), or a schedule (cron-based, runs automatically).

Tools & connectors

Agents act through tools — file edits, shell commands, HTTP requests — and connectors, which are pre-built integrations (Slack, GitHub, Google Sheets, Discord, and more) a workflow node or agent can call without you wiring authentication by hand.

Agent Workspace

The Agent Workspace is the control surface: an Activity Bar (Overview, Tasks, Canvas, Workflows, Runs, Agents) with a contextual sidebar and a context-aware chat — one screen to see and manage everything every agent is doing, rather than separate dashboards per feature.

Model tiers

Every agent in Nexrall can run on one of three model tiers:

Tier	Best for
Turbo	Fast, default — everyday coding and chat.
Pro	Most capable reasoning for complex, multi-step work.
Ultra	Maximum power, adaptive deep thinking for the hardest problems.

See Model tiers for details on context window and when to reach for each one.