design-studio

Tiledesk's open-source visual, no-code designer where LLM/GPT AI meets a flexible 'graph' approach. Create conversations and automations effortlessly, a Voiceflow and Botpress alternative.

Runssource: GitHubhomepageTypeScriptMITcommit b72ebaa8c73a

TypeScript, MIT licensed. The project labels itself: automation tool, bot builder, botpress alternative, chatbot development, conversation designer, conversational ui, design studio and github project.

design-studio runs. An Argusic agent installed it in 25 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Tiledesk Design Studio Angular 14 project builds successfully via ng build (exit 0) and the test suite executes 334 tests (142 passing, 191 failing due to pre-existing spec configuration issues) using ChromeHeadless with puppeteer's bundled Chrome 121 in a sandboxless container.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.22 (measured)
recorded runs
1
last tested
stars
473
forks
98
open issues
5
watchers
7
size
19 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing design-studio, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Broken spec files with wrong component class names (17 files): toogle, advanced, cds-action-speech-form, cds-action-reply-button, cds-action-reply-voice-text, attributes-dialog, operand/operation/operator (v2), cds-action-email, cds-action-online-agents, cds-action-reply-v2, cds-action-reply-image, audio-upload, delay-text, element-from-url, webhook-service15 minutes
  • No Chrome browser installed in the container5 minutes
  • Missing @ionic/angular module in user-typing.component.spec.ts2 minutes
  • app.component.spec.ts tested non-existent title property1 minute
  • test.ts lacked require.context for spec discovery1 minute
  • 191 of 334 unit tests fail at runtime due to missing provider/pipe/module mocks in spec files (pre-existing test quality issues)
Install time
25 minutes
Cold machine to finish
28 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
npx ng build exited 0, dist/ directory populated; npx ng test reported TOTAL: 191 FAILED, 142 SUCCESS, 334 total, Chrome connected
Model tokens used
599,731
Exact commit tested
b72ebaa8c73a
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

/bin/sh -lc 'ls -la /work/repo/dist/ 2>/dev/null | head -5' in /work/repo
 succeeded in 0ms:
total 10524
drwxrwxr-x 3 runner runner    4096 Oct 20 11:01 .
drwxr-xr-x 9 runner runner    4096 Oct 20 11:01 ..
-rw-rw-r-- 1 runner runner   12826 Oct 20 11:01 238.bd939cb4c6723f0f.js
-rw-rw-r-- 1 runner runner   46894 Oct 20 11:01 278.e3b1ed49e21dc522.js
Build output exists in `dist/`. Let me compile the final report.
2026-10-20T11:02:20.924676Z ERROR codex_core::session: failed to record rollout items: thread 01a15…
tokens used
599,731
Build output exists in `dist/`. Let me compile the final report.

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 25 minutes.
  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.22

Topics (from GitHub)

automation-toolbot-builderbotpress-alternativechatbot-developmentconversation-designerconversational-uidesign-studiogithub-projectgithub-repositorygpt-aigraph-visualizationllmmultichannelno-codeopen-sourcevisual-designervoiceflow-alternative

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/design-studio.svg)](https://argusic.com/subject/design-studio)

Questions

Does design-studio run?
Yes. design-studio runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test design-studio?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b72ebaa8c73a. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test design-studio?
The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does design-studio take to install?
25 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does design-studio need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing design-studio?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for design-studio?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion