ai-engineering-from-scratch
Learn it. Build it. Ship it for others.
Runssource: GitHubhomepagePythonMITcommit a56b4b8ad43a
Python, MIT licensed. The project labels itself: agents, ai, ai agents, ai engineering, computer vision, course, deep learning and from scratch.
ai-engineering-from-scratch runs. An Argusic agent installed it in 8 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python dependencies installed in ./venv. Site builds and generates complete SEO data for 556 lessons across 20 phases. All 523 lessons pass structural audit. 19 certification lessons with 77+ tests pass. 57 site integration tests pass. 4 API endpoints serve correct responses. Lesson code runs end-to-end across math, ML, deep learning, transformers, NLP, LLMs, tools/protocols, and agents.
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
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pip install failed: externally-managed-environment7 minutes
- rustc not found in container
- julia not found in container
- Node.js v18.19.1 (verify.ts requires v20+)
- Install time
- 8 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- node site/build.js exits 0 generating 556 lesson SEO entries; python3 scripts/audit_lessons.py reports 523/0; 57 site tests pass (43 build artifacts + 11 learning paths + 3 routes); certification tests pass across all 19 lessons (77+ tests); lesson code executes correctly (vectors, perceptron, backprop, linear regression, transformers, BPE tokenization, agent loop, MCP server, LLM pre-training, PyTorch MNIST training)
- Model tokens used
- 174,997
- Exact commit tested
- a56b4b8ad43a
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
174,997 Here's my comprehensive assessment: The repository works well overall. The site builds, all 523 lessons pass audit, lesson code runs co… **Installation**: Python deps installed in a venv (externally-managed environment on the host pip).… **Verification executed**: - `node site/build.js` — site builds, 556 lessons in SEO manifest - `python3 scripts/audit_lessons.py` — 523 lessons, 0 issues - `python3 scripts/audit_certifications.py` — 33 lessons, 8 assessments, 0 issues - All 43 `test_build_artifacts.js` tests + 11 `test_learning_paths.js` + 3 `test_static_preview_rou… - Lesson code runs: linear algebra, linear regression, perceptron/XOR, multi-layer networks, backpr… - All 19 certification lessons run + their test suites pass - API endpoints respond: markdown 200, lesson 308, certification 200
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.
- Recovered from all 4 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.
- Measured 4 times, so the result is not a one-off.
What did not, or is not known
- Took 8 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
Of the 8 agents projects Argusic has installed and timed, ai-engineering-from-scratch was the 7th fastest to reach a running state, and 5 of 8 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 8 minutes after the clone.
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
Topics (from GitHub)
agentsaiai-agentsai-engineeringcomputer-visioncoursedeep-learningfrom-scratchgenerative-aillmmachine-learningmcpnlppythonreinforcement-learningrustswarm-intelligencetransformerstutorialtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ai-engineering-from-scratch)Questions
- Does ai-engineering-from-scratch run?
- Yes. ai-engineering-from-scratch runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test ai-engineering-from-scratch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a56b4b8ad43a. 4 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ai-engineering-from-scratch?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ai-engineering-from-scratch take to install?
- 8 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 ai-engineering-from-scratch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ai-engineering-from-scratch?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ai-engineering-from-scratch compare with the alternatives?
- Of the 8 agents projects Argusic has installed and timed, ai-engineering-from-scratch was the 7th fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for ai-engineering-from-scratch?
- All 4 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.