== PRODUCT TOUR ==
== 01 MODEL BACKENDS ==SEC 01/07

Connect the models you already use

Register a model backend - Anthropic, OpenAI, or any OpenAI-compatible endpoint such as Ollama or vLLM. Farna Control health-checks each backend and routes around a failed provider, and individual nodes choose the backend they run on.

FIG 01Product UI / model backends
Model Backends admin page listing two configured backends with provider, model ID and credential status
== 02 SCHEMA BROWSER ==SEC 02/07

Define the shape of a handoff

Bind a versioned schema to each node's input and output. A step whose output does not match its schema fails before the next node runs, so a malformed agent response never reaches the tool behind it. A schema change creates a new version and leaves the old one in place.

FIG 02Product UI / schema browser
Schemas page listing each schema with its description and status, with folders and Browse, Editor and Infer tabs
== 03 PIPELINE EDITOR ==SEC 03/07

Compose the pipeline as a graph

Place agents, connectors, gates, and human steps as nodes on a canvas and connect them with edges. The editor validates the graph before it saves - missing bindings, incompatible schemas, and unreachable nodes are rejected at save time, before anything runs.

FIG 03Product UI / pipeline editor
Pipeline editor canvas with three agent nodes connected by edges and a toolbar with Save and Run Pipeline
== 04 GATE REVIEW ==SEC 04/07

Put a human where the risk is

Mark a step human-only and the run pauses in Awaiting Human. The agents wait for a named role: a reviewer claims the gate, reads the run context and the upstream output, and approves or sends it back. The decision, the reviewer, and the timestamp are recorded.

The gate review screen has no capture yet.

== 05 RUN DETAIL ==SEC 05/07

Dispatch the agents you already run

Farna Control does not supply agents. It dispatches work to the runtime you already use - Claude Code, Cursor, Copilot, or your own harness - and writes the prompt, output, cost, and exit status to the run record.

FIG 05Product UI / run detail
Completed run detail showing the run status, total cost, a chip for each node and the execution trace
== 06 AUDIT LOG ==SEC 06/07

Prove what happened

Significant governance events - run start, agent dispatch, human decision, and gate outcome - land in a hash-chained, append-only audit log inside your instance. The run record separately captures the immutable snapshot and reported output for run-level inspection. Team adds chain verification and audit export, including a signed evidence pack for offline verification.

FIG 06Product UI / audit log
Audit log with append-only events and Verify Chain button visible
== 07 RUN IT YOURSELF ==SEC 07/07

Run it yourself

Farna Control is self-hosted software. Clone it, bring your own model backend and agents, and keep every prompt and every record inside your own network. There is no hosted trial.