Get Started
← Own your AI · Mission 7 of 31

Put AI in your terminal: summarise files, logs and web pages with one command

Copy any error message, type one short command, and get the cause and the fix in plain English. LLM sends any text to the AI on your own laptop, so your notes, errors and logs never leave your machine.

22 minBeginnerTools: FreeStep 1 free
Tested 9 Oct 2026 · LLM 0.36, llm-ollama 0.17.1, Ollama 0.40.1, Gemma 4 e2b, Windows 11 (16GB, no graphics card)
Copy any error, run one short command, get the cause and the fix in plain English
One command that summarises any text file, from meeting notes to a 300-line log
Saved prompts you can reuse with two words, and a searchable history of every answer
  • The one setting that stops big files being silently cut short, and a filter trick that gets answers in seconds
Before you start
  • Ollama with gemma4:e2b downloaded. Not done that yet? Do Run a ChatGPT-style AI on your own laptop first (15 minutes). Gemma 4 needs Ollama 0.20.7 or newer: check with ollama --version.
  • About 45MB of free disk space for LLM itself
  • Windows PowerShell, or Terminal on a Mac
01/06Check your local AI is ready0 done
STEP 01 of 06~3 min

Check your local AI is ready

LLM is only the messenger. Ollama is the engine that actually runs the AI on your machine.

  1. This mission uses the same free model as Run a ChatGPT-style AI on your own laptop: Google's Gemma 4 (gemma4:e2b) running in Ollama. If you've done that lesson, skip straight to the check.

    Windows (skip if you've done it)
    winget install --id Ollama.Ollama -e
ollama pull gemma4:e2b

  2. On a Mac, install Ollama from ollama.com/download ↗, then run ollama pull gemma4:e2b. The model is a 4.6GB download, so give it a few minutes. Then make sure it's there:

    Terminal
    ollama list
    Output
    NAME          ID              SIZE      MODIFIED
gemma4:e2b    b37049369adf    4.6 GB    Less than a second ago
✓
Checkpointollama list shows gemma4:e2b.
If it breaks'ollama' is not recognised + 1 more
'ollama' is not recognised
Close the terminal and open a new one. If it still fails, follow the install step in the Ollama lesson.
'could not connect to a running Ollama instance'
Ollama isn't running in the background. Open Ollama from the Start menu (or Applications on a Mac) and try again.
Still stuck? Ask the community
Next mission · Own your AITurn any Word, Excel, PowerPoint or PDF into text your AI can actually read
→