115 controls · 9 dimensions · Free for your first workflow

Find every AI workflow
hiding in your codebase.
Then make them production-ready.

ShipSmith scans your repo, discovers your AI workflows automatically, and scores each one against 115 production readiness controls across 9 dimensions. Free for your first workflow.

No credit card required · Works with GitHub, GitLab, Bitbucket · Results in under 10 minutes

shipsmith scan

Scanning repo: github.com/acme/backend

───────────────────────────────────────

✓ Found: OpenAI GPT-4 call in /src/support/classify.ts

✓ Found: LangChain agent in /src/sales/outreach.py

✓ Found: Anthropic Claude call in /src/docs/summarizer.ts

✓ Found: LangGraph workflow in /src/onboarding/flow.py

───────────────────────────────────────

4 AI workflows discovered.

Readiness score: 3/9 dimensions passing.

→ Sign up to see control-level gaps and remediation plan

115
Production readiness controls
9
Assessment dimensions
< 10 min
Average scan time
Free
For your first workflow

Most AI workflows aren't production-ready.
Most teams don't know which ones they have.

👁

You're flying blind

You built an AI feature in Q3. Another team shipped one in Q4. Neither is monitored. Neither has a fallback. You find out in the incident review.

📋

Checklists don't scale

A spreadsheet works for one workflow. At 10 workflows across 5 teams, nobody is tracking anything consistently and gaps pile up silently.

💸

Production surprises are expensive

The cost of fixing a production AI failure is 10x the cost of catching it before launch. Most teams pay the 10x.

From codebase to production-ready in 3 steps.

01

Connect your repo

We scan your codebase using our AI agent. It finds every LLM call, agent, chain, and workflow — including the ones nobody documented.

02

Get your readiness score

Each discovered workflow is scored against 115 controls across 9 dimensions: Data, Model, Evaluation, Observability, Resilience, Security, Cost, Adoption, and Governance.

03

Fix what's failing

See exactly which controls are failing and why. Get remediation guidance mapped to each gap. Track progress as your team fixes them.

Recommended

Scan my repo automatically

Connect GitHub/GitLab and we find every AI workflow for you.

Connect repo →
Manual

Register a workflow manually

Describe your AI workflow and assess it immediately.

Register manually →

Free for your first workflow. Seriously.

Free
$0
  • Discover all AI workflows in your repo
  • Full assessment for 1 workflow
  • Dimension-level readiness scores
  • Top 3 failing dimensions
  • 1 user
Get started free →
Most popular
Pro
$1,099/mo

or $999/mo billed annually

  • Everything in Free
  • Assess all discovered workflows
  • Control-level gap breakdown (all 115 controls)
  • Full remediation plan per workflow
  • PDF readiness report
  • Remediation progress tracking
  • Up to 5 users
See full pricing →

Common questions

How does the codebase scanner work?+
We use an AI agent that reads your repository and identifies LLM API calls, agent frameworks (LangChain, LangGraph, etc.), and AI workflow patterns. It works with Python, TypeScript, JavaScript, and Java repositories.
Do you store my code?+
No. The scanner reads your code to identify AI workflow patterns and does not persist any source code. We store only the workflow metadata — file paths, framework detected, and workflow description.
What if I don't want to connect my repo?+
You can register your AI workflow manually — just describe what it does and which frameworks it uses. The assessment works exactly the same way.
What frameworks are supported?+
OpenAI SDK, Anthropic SDK, LangChain, LangGraph, LlamaIndex, AWS Bedrock, Hugging Face, Mastra, and raw REST API calls to any LLM provider.
How is this different from a spreadsheet checklist?+
A spreadsheet doesn't find your workflows for you, doesn't score them consistently, doesn't track remediation, and doesn't update as your codebase changes. ShipSmith does all four.
How long does the scan take?+
Most repos scan in under 10 minutes. Large monorepos (500k+ lines) may take up to 5 minutes.

Your AI is already in production.
Is it ready?

Scan your repo, discover your AI workflows, and get your production readiness score — free.

Scan Your Repo — Free →

No credit card required. Results in under 10 minutes.