Force-Field
the agentic harness for safer AI

Force-Field: the agentic harness for safer AI.

Force-Field is the agentic harness for safer AI from Spin State Labs. FORCE governs what the model says: no flattery, premises challenged, sources cited, reasoning shown, confidence tagged. FIELD governs what an agent may do: a per-agent manifest plus a local Enforcement Gate with a kill switch, protected paths, tool-call budgets and a hash-chained ledger.

How an action is handled

Design principles

Controls in code

A limit that matters is enforced by software at the point of action, not by asking a model to behave.

A person decides what matters

Consequential actions wait for approval from a second person, with a record of who approved what.

Model-agnostic

Work is routed by policy, sensitivity, cost and the task at hand, so a model can be changed without rebuilding.

Your context stays yours

Prompts, policies, knowledge, traces and evaluation sets belong to the organisation and can be exported.

Everything is traced

Each step records what was asked, what was retrieved, which model answered and which checks ran.

Knowledge with proof

Answers cite their sources, and an organisation's facts are validated by a person before agents use them.

Documentation is on its way. This site will hold it as it is written.