Find the Broken Step Before Your Users Do

For teams that own a docs quickstart. 1stRun runs every command, not only the links, and proves each fix in a fresh container.

Try

Proven in a clean container

dbt guide: 3 steps fixed, 9 of 9 pass

Two were docs bugs: jafgen --years 6 at step 10, and a guide that never says it needs Python 3.12. Step 1 only needed git. The rerun made no model calls.
See the run in Doc-test
Priced before you scale

$5.35 a month for 300 runs, projected

Basis: 300 runs at $0.0178, the mean model cost of 88 real runs, at list price. The Team plan caps a run at $0.047.
See a sample receipt
Assigned to who knows the code
1. 1Write a page for workspaceHaider wrote 13 of its 22 changes
2Altimate Base hosted modelfor anandgupta42

3YOLO mode on ctrl+yfor Haider

See who knows the code

How Doc-test works. Broken steps go in. Real ones 1stRun found: jafgen --years 6 failed with No such option in the dbt guide. entire: command not found after the Entire install. A migration guide link that returns 404. A dbt guide that never states it needs Python 3.12. No module named typer. curl: command not found. AccuKnox docs that say 0.9.0 while the installer fetches 0.9.58. KeyError NEATLOGS_API_KEY.

How Doc-audit works, on dbt-labs/dbt-core. The project flags page was last edited 453 days ago, with 29 code changes since. The infer-configs page is 709 days old. 15 of 1,405 pages are stale. 72 shipped features have no docs. AccuKnox/help has 87 stale pages, and its oldest page is 1,100 days old.

Rajbir Biswas Watch on YouTube

Doc-test

1stRun Runs Your Quickstart Like a Brand-New User

You give it

A public docs URL, like docs.getdbt.com/guides/duckdb
A tool name. Your coding agent finds its quickstart page.
A GitHub repo, for Doc-audit

It plans, runs and proves

One model call turns the page into at most 10 steps, one command each.
Each step runs in a clean Docker container.
A broken step gets a fix. A fresh container reruns every step with no model calls.

Not yet

Pages behind a login
API specs and bug reports as input
Long-running servers. It skips them and says why, like dbt docs serve below.

Every step runs on your machine. Only the docs page and the output of a failed step go to the model. Read the known limits

1A step breaks

jafgen --years 6Error: No such option: --yearsThe dbt guide never worked on a fresh machine.
21stRun fixes the docs

jafgen --years 6jafgen 6The tool now takes the years as a plain number.
3A second clean run proves it

9 of 9 steps passed

The Plan 1stRun Made From the dbt Page

10 steps, one command each

1git clone https://github.com/dbt-labs/jaffle_shop_duckdb.gitThe container had no git, so 1stRun installs it first.Fixed
2cd jaffle_shop_duckdbPassed
3pip install -r requirements.txtA docs bug. The guide never says it needs Python 3.12, which networkx 3.7 needs. The fix pins 3.6.1.Fixed
4dbt seedPassed
5dbt buildPassed
6dbt docs generatePassed
7dbt docs serveIt starts a web server, which a headless container cannot check.Skipped
8ls -lah *.duckdbPassed
9python -m pip install jafgenPassed
10jafgen --years 6A docs bug. The tool now takes jafgen 6.Fixed

Fresh container: 9 of 9 runnable steps passed, with no model calls.

A real run on the dbt + DuckDB quickstart. Replay this run

1stRun Already Sent Fixes and Bug Reports to dbt, Polars, Chroma and HTTPX

Test your docs

Doc-audit

Each Fix Goes to the Person Who Knows the Code

AltimateAI/altimate-code14 people, 619 commits in 12 months

People

Code · share of each part

Top 3 Tasks on This Board

Built from public commits in the last 12 months. Suggestions, not assignments.

Open the full board See the dbt-core team

Doc-audit

Find the Pages Your Code Left Behind

1Paste a repo

dbt-labs/dbt-core
Any public GitHub repo with docs in it.
21stRun reads the history

Page edited Jul 202529 code changes since

fix(flags): normalize project flag keys to uppercaseJul 2, 2026
3You get the list

15stale pages
72features with no docs

The Doc-audit board for dbt-labs/dbt-core: 15 stale pages and 72 features with no docs, in columns to ship next

Open the dbt-core audit

Audit a repo

Receipt

Every Run Ends With a Receipt

1stRunOct 10, 2026

Docs page help.accuknox.com/knoxctl
Broke at step 2. Missing curl, gnupg and sudo.

1Model cost$0.0453

2Team plan cap$0.0469796.4% of the cap used

3Clean rerun5 of 5

Verified

PricedYou see what the run cost.
CappedYour plan sets the most a run may spend.
ProvenA clean rerun passed every step.

Open the sample receipt See how each cap is set

Watch 1stRun Test a Guide and Audit a Repo

1stRun film thumbnail: the dbt guide broke, fixed and proven, 9 of 9 steps pass

The film · 2:54

1stRun Finds, Fixes and Proves Broken Docs

A real run and its receipt, a real audit, the agent path, and the receipt.

Doc-test thumbnail: step 10 of a quickstart fails with no such option --years, then the fix passes 9 of 9 steps

Doc-test · 2:59

Your Docs Lie. 1stRun DocTest Proves It

Doc-audit thumbnail: 15 stale pages found in dbt-core, each fix goes to the person who knows the code

Doc-audit · 1:56

Find the Docs Your Code Left Behind

A real audit of dbt-core: one repo in, a run on a laptop, the board, an owner for each fix, and the receipt.

Teaser thumbnail: step 10 of the dbt DuckDB guide fails because jafgen rejects the --years flag

Teaser · 0:36

The dbt Guide That Never Worked

Doc-audit thumbnail: a dbt-core page is 453 days stale after 29 commits changed the code

Doc-audit · 0:57

Docs Rot Quietly. 1stRun DocAudit Finds It

Built With Alan AI, Claude, Docker and Langfuse

Alan AIThe AI agent inside 1stRun. It works through the quickstart steps and helps repair the ones that break.
ClaudePlans the runbook, repairs the first broken step and sorts each failure. It runs through the Claude Agent SDK.
DockerEvery run gets one clean container, and the proof run gets a second one.
LangfuseOptional. Every run becomes one trace, so a failed step comes with its cause.
OllamaOptional. A local model that backs up Claude when it sorts failures and judges audits.
FirecrawlOptional. Turns a docs page into clean markdown. Plain HTTP is the fallback.
git and GitHubDoc-audit reads the repo history. The fix goes out as a pull request you approve.

Compare 1stRun With Claude Code, GitHub Actions and GitHub Agents

1stRun does one job: it runs the quickstart, fixes the docs, proves the fix and opens the PR. A link checker or a docs linter only reads the page.

Yes Partly or with setup No

Feature	1stRun	Claude Code	GitHub Actions	GitHub Agents	Custom workflow
Runs the quickstart as a new developer	Every step runs in a fresh Docker container	Runs on your machine. An optional sandbox limits files and network	A fresh runner per job, but you script every step	Works in its own VM on your repo, not a new-user setup	Only as clean as the environment you build
Plans steps from a docs URL	Writes one step per command on the page	When you prompt it with the page	You write each step	Starts from an issue or task, not a docs page	You write the parser
Tries again when a step fails	Finds the cause, patches, retries up to 3 times per step	Iterates inside one session	The job fails and stops	Iterates and pushes commits to its draft PR	Only what you code
Proves the fix	A second clean container must pass the whole quickstart	Only if you ask for it	Only if you script a second run	Your repo's own tests, not a clean-user rerun	Only if you code it
Shows the cost of each run	Every run ends with a receipt. The mean run costs $0.018	Cost and token metrics, after you set them up	Logs and run history, no agent traces	A session log, with no cost trace you own	You build it
Opens the docs PR	After you approve once	When you ask	Only if you script it	Opens a draft PR and asks you for review	Only if you code it
Easy to start	Paste a docs URL, then paste the prompt into your coding agent	One prompt, but you define the test and the clean setup	A YAML file per quickstart	Assign an issue to Copilot	Highest effort
Proof in public repos	4 upstream docs PRs, all open	Not specific to docs	Not specific to docs	Not specific to docs	Depends on your build

Rajbir Biswas

Hi there, I'm Rajbir, a 21 y/o CS student at SRMIST who loves to research and build stuff. Currently a Backend Intern at Earthsense Labs Pvt. Ltd (IIT Delhi) & doing Research Internship at IIT Madras. I build secure, scalable web3 and AI-powered Applications from DeFi protocols and cross-chain systems to fraud detection pipelines and real-time APIs.

rajbir.tech GitHub @rangoliagt