[go: up one dir, main page]

Simon Willison’s Weblog

Subscribe
Atom feed for showboat

4 posts tagged “showboat”

Showboat is a tool that lets coding agents demonstrate their work.

2026

Given the threat of cognitive debt brought on by AI-accelerated software development leading to more projects and less deep understanding of how they work and what they actually do, it's interesting to consider artifacts that might be able to help.

Nathan Baschez on Twitter:

my current favorite trick for reducing "cognitive debt" (h/t @simonw ) is to ask the LLM to write two versions of the plan:

  1. The version for it (highly technical and detailed)
  2. The version for me (an entertaining essay designed to build my intuition)

Works great

This inspired me to try something new. I generated the diff between v0.5.0 and v0.6.0 of my Showboat project - which introduced the remote publishing feature - and dumped that into Nano Banana Pro with the prompt:

Create a webcomic that explains the new feature as clearly and entertainingly as possible

Here's what it produced:

A six-panel comic strip illustrating a tool called "Showboat" for live-streaming document building. Panel 1, titled "THE OLD WAY: Building docs was a lonely voyage. You finished it all before anyone saw it.", shows a sad bearded man on a wooden boat labeled "THE LOCALHOST" holding papers and saying "Almost done... then I have to export and email the HTML...". Panel 2, titled "THE UPGRADE: Just set the environment variable!", shows the same man excitedly plugging in a device with a speech bubble reading "ENV VAR: SHOWBOAT_REMOTE_URL" and the sound effect "*KA-CHUNK!*". Panel 3, titled "init establishes the uplink and generates a unique UUID beacon.", shows the man typing at a keyboard with a terminal reading "$ showboat init 'Live Demo'", a satellite dish transmitting to a floating label "UUID: 550e84...", and a monitor reading "WAITING FOR STREAM...". Panel 4, titled "Every note and exec is instantly beamed to the remote viewer!", shows the man coding with sound effects "*HAMMER!*", "ZAP!", "ZAP!", "BANG!" as red laser beams shoot from a satellite dish to a remote screen displaying "NOTE: Step 1..." and "SUCCESS". Panel 5, titled "Even image files are teleported in real-time!", shows a satellite dish firing a cyan beam with the sound effect "*FOOMP!*" toward a monitor displaying a bar chart. Panel 6, titled "You just build. The audience gets the show live.", shows the man happily working at his boat while a crowd of cheering people watches a projected screen reading "SHOWBOAT LIVE STREAM: Live Demo", with a label "UUID: 550e84..." and one person in the foreground eating popcorn.

Good enough to publish with the release notes? I don't think so. I'm sharing it here purely to demonstrate the idea. Creating assets like this as a personal tool for thinking about novel ways to explain a feature feels worth exploring further.

# 17th February 2026, 4:51 am / ai, generative-ai, llms, ai-assisted-programming, gemini, text-to-image, nano-banana, showboat, cognitive-debt

Two new Showboat tools: Chartroom and datasette-showboat

Visit Two new Showboat tools: Chartroom and datasette-showboat

I introduced Showboat a week ago—my CLI tool that helps coding agents create Markdown documents that demonstrate the code that they have created. I’ve been finding new ways to use it on a daily basis, and I’ve just released two new tools to help get the best out of the Showboat pattern. Chartroom is a CLI charting tool that works well with Showboat, and datasette-showboat lets Showboat’s new remote publishing feature incrementally push documents to a Datasette instance.

[... 1,756 words]

Skills in OpenAI API. OpenAI's adoption of Skills continues to gain ground. You can now use Skills directly in the OpenAI API with their shell tool. You can zip skills up and upload them first, but I think an even neater interface is the ability to send skills with the JSON request as inline base64-encoded zip data, as seen in this script:

r = OpenAI().responses.create(
    model="gpt-5.2",
    tools=[
      {
        "type": "shell",
        "environment": {
          "type": "container_auto",
          "skills": [
            {
              "type": "inline",
              "name": "wc",
              "description": "Count words in a file.",
              "source": {
                "type": "base64",
                "media_type": "application/zip",
                "data": b64_encoded_zip_file,
              },
            }
          ],
        },
      }
    ],
    input="Use the wc skill to count words in its own SKILL.md file.",
)
print(r.output_text)

I built that example script after first having Claude Code for web use Showboat to explore the API for me and create this report. My opening prompt for the research project was:

Run uvx showboat --help - you will use this tool later

Fetch https://developers.openai.com/cookbook/examples/skills_in_api.md to /tmp with curl, then read it

Use the OpenAI API key you have in your environment variables

Use showboat to build up a detailed demo of this, replaying the examples from the documents and then trying some experiments of your own

# 11th February 2026, 7:19 pm / ai, openai, generative-ai, llms, ai-assisted-programming, skills, showboat

Introducing Showboat and Rodney, so agents can demo what they’ve built

Visit Introducing Showboat and Rodney, so agents can demo what they’ve built

A key challenge working with coding agents is having them both test what they’ve built and demonstrate that software to you, their supervisor. This goes beyond automated tests—we need artifacts that show their progress and help us see exactly what the agent-produced software is able to do. I’ve just released two new tools aimed at this problem: Showboat and Rodney.

[... 2,023 words]