Report · marked 10 Oct 2026
rohitg00/ai-engineering-from-scratch
An agent can work here, but it will waste turns finding its footing.
Python · 66,427 stars · 6,885 files · branch main
65
/100
B
Instructions
24/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on readme as an entry point.Setup
9/20Whether an agent can install the project and get it running without a human. Losing marks on deterministic install and environment config.Verification loop
12/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on test command is discoverable and lint and format rules.Context economy
13/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability
8/10How quickly anything new can orient itself. Losing marks on written documentation.
Higher is better. Accent marks what is costing you most.
Fix these first
01
Test command is discoverable
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
02
File sizes fit in context
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
03
Environment config
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.
The full marking
Every deduction below names the file or setting it came from.
Instructions 24/27 A
Whether the repo tells an agent how to behave before it starts guessing.
✓Agent instruction file
12/12
AGENTS.md is present, which is the format the most tools read.
✓Instruction quality
12/12
Specific enough that an agent can act on it.
14,618 characters, a workable length
names the actual commands to run
uses headings, so an agent can skim it
includes copyable code blocks
✗README as an entry point
0/3
No README. This is the first file anything reads, human or machine.
Give the README an Install and a Usage heading with real commands under each. Agents pattern-match on those headings.
Setup 9/20 C
Whether an agent can install the project and get it running without a human.
✗Deterministic install
3/6
Only requirements.txt, which pins loosely at best.
Commit the lockfile your package manager generates. Without it, an agent's install and your install are different builds, and 'works on my machine' becomes unfalsifiable.
✓Discoverable commands
6/6
Commands are declared where an agent will look for them.
scripts/ directory
✗Environment config
0/4
Nothing documents the environment this needs. An agent will get a runtime error it can't diagnose.
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.
✗Pinned runtime version
0/2
No pinned runtime version.
Add a .nvmrc, .python-version, or equivalent so the agent's toolchain matches yours.
✗Reproducible environment
0/2
No container or devcontainer definition.
A Dockerfile or devcontainer removes an entire class of 'it won't install' failures.
Verification loop 12/25 C+
Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.
✓Tests exist
8/8
600 test files against 2310 source files.
e.g. certifications/claude/lessons/00-certification-strategy/code/tests/test_main.py, certifications/claude/lessons/01-claude-product-and-model-landscape/code/tests/test_main.py, certifications/claude/lessons/02-model-selection-and-token-economics/code/tests/test_main.py
✗Test command is discoverable
0/7
There's no obvious way to run the tests. Even if tests exist, an agent won't reliably find the entry point.
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
✓Continuous integration
4/4
5 GitHub Actions workflows define what "passing" means.
✗Lint and format rules
0/3
No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.
A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.
✗Static type checking
0/3
No static type checking.
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
Context economy 13/20 B
Whether the repo fits in a context window, or fights it.
✓No committed build output
6/6
No generated directories committed.
✓.gitignore hygiene
3/3
.gitignore covers 91 patterns.
✗File sizes fit in context
0/6
5 source files are over 100KB.
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
site/data.js — 1004KB
scripts/readme_translations.py — 292KB
site/test_build_artifacts.js — 112KB
✗Repository weight
4/5
About 104.7MB checked out, which is comfortable.
Here is your AGENTS.md
Drafted from what is actually in this repository: the install
command from your lockfile, the commands you already declare, your real directory layout. Anything
marked TODO needs a person. Save it at the root as AGENTS.md.
# AGENTS.md Learn it. Build it. Ship it for others. ## Setup ``` pip install -r requirements.txt ``` ## Commands ``` # TODO: nothing declares a build or test command, so an agent has to guess. # This is the single most valuable section of this file. Fill it in. ``` ## Layout - `projects/` 985 source files - `phases/` 822 source files - `site/` 186 source files - `certifications/` 170 source files - `manuals/` 89 source files - `scripts/` 40 source files ## Conventions - Tests live alongside the code they cover, following `certifications/claude/lessons/00-certification-strategy/code/tests/test_main.py`. - CI defines what passing means. See `.github/workflows/build-book.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - `site/data.js` is 1004KB. It will not fit comfortably in context, so read it in parts. - No lockfile is committed, so an install here may not match what CI produced. --- Drafted by agentreadme.com from what is in this repository. Everything marked TODO needs a human. Check it in as AGENTS.md at the root.
Open the raw markdown
or
curl -o AGENTS.md agentreadme.com/draft/rohitg00/ai-engineering-from-scratch.md
A draft gets the commands right and stops at the things only a maintainer knows. What a good Python AGENTS.md looks like covers what to add by hand, and what AGENTS.md is explains the format itself.
Show the mark
The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.
[](https://agentreadme.com/rohitg00/ai-engineering-from-scratch)Other Python repositories, marked
Think this mark is wrong?
Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.