Home / use cases

Steal a workflow.
They're yours anyway.

Concrete recipes — each one lists the mode, the model type, and the moves. Every one of them works with the Wi-Fi off.

For the confidentiality professional

Work you could never upload.

RAG Tool

Interrogate a 200-page contract

Load the PDF into the RAG Tool and ask questions like "What are the termination clauses?" or "List every obligation with a deadline." The document is indexed on your disk; the analysis happens on your GPU. Client confidentiality survives contact with AI.

Mode: RAG Tool · Model: any strong text model
Moves: load PDF → ask → follow up → export answer to PDF
Vision · Generate

Analyze sensitive images

Scanned records, internal dashboards, evidence photos — upload the image in Generate mode with a vision model and get descriptions, transcriptions, or answers. Then click Generate > Chat to keep discussing it conversationally.

Mode: Generate → Chat bridge · Model: llava
Moves: + File → ask → Generate > Chat → follow-ups
For the homelabber

An agent that earns its rack space.

SSH Bot

Diagnose a sick server, hands-off

Connect the SSH Bot to the box and describe the symptom: "The web app is slow — find out why." It checks load, memory, disk, logs — reading each output and deciding the next command itself — then reports its findings. You watch the terminal live the entire time.

Mode: SSH Bot · Connect: your host, your credentials
Moves: connect → state the goal → supervise → done
Tools + Code exec

From "write a script" to "it ran"

Ask for a PowerShell script to, say, rename a season of media files. Review the generated code in the response — then execute it directly from the app. Python, PowerShell, or Batch, no copy-paste detour through an editor.

Mode: Chat or Generate · Feature: Code Block → Run
Moves: ask → read the script → Run
For the subscription-fatigued

The everyday stuff, minus the meter.

Chat · model switching

Draft cheap, polish smart

Brainstorm and outline with a fast small model — instant responses, zero cost. When the draft is ready, switch the dropdown to your biggest model mid-conversation. It inherits the whole thread and does the final pass. Two-tier quality, one chat, no tokens billed.

Mode: Chat · Models: 8B → biggest you can run
Moves: draft → switch model → "now refine this"
Vision · screenshots

"What is this error?" in two clicks

Hit the screenshot button, capture the cryptic dialog, and ask. No retyping stack traces, no cropping personal info before uploading to a cloud — because there is no uploading.

Mode: Generate · Model: llava
Moves: screenshot button → "explain this error"
Audio

Voice memos into meeting notes

Record directly in the app — or drop in an .mp3 — and have an audio-capable model turn rambling into structure: summary, decisions, action items. Recordings of your own meetings finally have somewhere private to go.

Mode: Generate · Model: gemma4
Moves: record → "summarize: decisions + action items"
LaTeX output

Study math with real notation

Ask for a derivation and get rendered formulas, not ASCII approximations. Combine with file reading — import a problem set as PDF and work through it — for a tutor that's always available and never metered.

Mode: Chat · Feature: formula rendering
Moves: import PDF → "walk me through problem 3"
For the builder

AI as a component, not a chat window.

JSON mode

Extract structured data from messy text

Paste invoices, emails, or logs and enforce a JSON response: {"vendor": …, "amount": …, "due": …}. Guaranteed parseable output makes the model a reliable pipeline stage — feed the results to whatever comes next.

Mode: Generate · Feature: JSON mode ON
Moves: paste text → describe schema → parse forever
Tools · Python

Give the model a calculator (and more)

With tools enabled, the model can call local Python when it needs real computation — crunch the numbers in your CSV instead of hallucinating them. Function calling, running on the same machine as everything else.

Mode: Chat · Feature: Tools ON
Moves: read file → ask the quantitative question
Image generation

Placeholder art without the queue

Generate concept images and placeholders locally with x/z-image-turbo or x/flux2-klein. Iterate as many times as you like — the only rate limit is your GPU fan.

Mode: Generate · Model: x/z-image-turbo
Moves: describe → generate → iterate freely
Parameters

Tune the model to the task

Deterministic extraction wants temperature near zero; brainstorming wants it high. Set system prompts and parameters per session and keep presets for the configurations you reuse — the dials the cloud never let you touch.

Mode: any · Feature: parameter panel
Moves: set system prompt → tune → save preset