Groundwork

You have a prototype: your documents, a model, useful output. What you don't have is the apparatus that makes it responsible to ship — a privacy pre-step, an evaluation built from your own failures, and a gate that stops a quiet prompt tweak from deploying a system that fabricates. That apparatus usually requires an ML engineer. Groundwork scaffolds it instead.

Groundwork's units are deployment patterns, not products — think Terraform modules for trustworthy AI deployments. groundwork init <archetype> scaffolds the whole harness for a pattern:

Every check is deterministic: same inputs, same result, every time — no LLM judge, and no API key for the checks themselves.

Quick start — 60 seconds, no API key

git clone https://github.com/nickjlamb/groundwork.git && cd groundworknpm install && npm run buildnpm run demo          # document QA: the whole loop passes, fully offlinenpm run demo:break    # the system starts fabricating — watch the gate go red

✗ GROUNDING demo-savings: ungrounded number "14" — not in the provided context✗ GROUNDING demo-unanswerable-appeals: unanswerable question — the answer did not abstain

The same loop for structured extraction:

npm run demo:extraction         # documents → fields, every check greennpm run demo:extraction:break   # a guessed date of birth, a dropped field — red, by name

✗ EXTRACTION demo-referral: SCHEMA: /referral_date must be string✗ EXTRACTION demo-referral: FABRICATED field "date_of_birth": document does not state it (got "12 April 1988")

That red build is the product: a fabricated figure, a guessed field, or a failed abstention becomes a CI failure, not a user complaint.

Ready for your own system?

npm install -D @pharmatools/groundworknpx groundwork init                # document QAnpx groundwork init extraction     # structured extraction

How it works

[Architecture: your repo (adapter, gold cases, config) flows into groundwork check (redaction pre-step, eval, results) which is compared against a committed baseline by a CI gate]

For extraction, one schema choice does most of the safety work: nullability is the abstention contract. A field the system must always find is non-nullable; a field the document may not state is nullable, and the system returns null for it — unknown → null, never guessed. A guessed value in a null-gold field fails by name: FABRICATED field "date_of_birth": document does not state it.

Examples

Commands

groundwork init [archetype]      scaffold the harness for a pattern (document-qa, extraction)groundwork check                 redaction self-test + the archetype's evalgroundwork check --baseline      freeze this run as the regression floorgroundwork check --ci            exit non-zero on failure or regression vs baselinegroundwork cost                  measured token usage + savings, in leverage order

Two ways to learn it: docs/GETTING-STARTED.md is the reference walkthrough (about half an hour), and the course covers the same ground as checkpoint-driven lessons — including the sabotage test, where you deliberately break your own system to prove the gate catches it, and a lesson on the extraction archetype. The scaffolded playbook (GROUNDWORK.md) lives inside your repo, where your team will actually read it.

Use from Claude

The same checks ship as an MCP server (groundwork-mcp, stdio) so Claude Code, Cowork, or Claude Desktop can run them conversationally — check_readiness on a repo, check_answer_grounding on a single answer, check_extraction on a single record (no repo needed), scaffold_harness, cost_summary:

{ "mcpServers": { "groundwork": { "command": "npx", "args": ["-y", "@pharmatools/groundwork", "mcp"] } } }

There's also an Agent Skill (skills/groundwork-readiness/) that teaches an agent to run the gate and report results honestly — including refusing to present a green check as a safety certification.

What Groundwork is not

Groundwork is a strong floor, not a guarantee. Deterministic checks catch the failures that can be caught deterministically; they cannot certify an AI system safe. For high-stakes outputs — anything touching health, money, legal standing, or safety — a human must review before the output reaches the person it affects. Extraction raises the stakes quietly: the record feeds decisions, so a wrong field is a wrong decision. The scaffolded playbook says this too, on purpose.

Project

• Status — two archetypes shipped (document QA, structured extraction) of a planned three. Depth before breadth: each pattern gets finished properly before the next starts. See the roadmap.
• Contributing — bug reports, gold-case patterns, and examples are especially welcome: CONTRIBUTING.md.
• Releases — tagged on GitHub, versions on npm, history in CHANGELOG.md.
• Built on — OpenGATE (evaluation) and Redacta (privacy), both open source.

Licence

MIT. Everything init scaffolds into your repo is MIT-0 — yours, no attribution needed.