Don't ask the model to decide.
Ask it questions. Decide in code.
A decision circuit is a set of typed questions a model answers with probabilities, and a set of gates that turn those probabilities into decisions: thresholds, AND/OR/NOT, votes, verification. The model never sees the gates. Every decision carries its probability, its outcome, and a trace. When the number sits too close to a threshold to call, the gate says so and a human gets the case.
A support-triage circuit, live
drag the probabilities a model might return; gates re-evaluateInputs · what the model answered
Gates · what code decided
Nudge pii to 0.65 and watch redact stop answering. That's the point: inside the band, the circuit escalates instead of guessing.
Write one
The circuit above, in Python
# questions the model answers c = Circuit() c.noul("pii", "Does the message contain personal information about a private individual?") c.noul("business", "Are all identifying details about a business rather than a person?") c.noul("angry", "Is the customer angry?") c.choice("dept", "Which team should handle this?", {"billing": "Money, refunds", "technical": "Bugs, outages", "other": None}) # gates code evaluates c.gate("redact", (Q("pii") & ~Q("business")) >= 0.6, band=0.1, on_uncertain="escalate") c.gate("route", argmax("dept", min_confidence=0.35)) c.gate("human", (Q("angry") | Q("pii")) >= 0.6) out = c.run(SystemOne(api_key=KEY), "Card charged twice, refund NOW. My card ends in 4412.") out["gates"]["redact"] # {'value': True, 'p': 0.97, 'outcome': 'decided', 'trace': ['pii p=0.97', 'gate _redact_1 p=0.98', 'and under independence -> p=0.95']}
The arithmetic is deliberately simple and is written into the trace: AND is a product, OR is 1 − ∏(1 − p), NOT is 1 − p. AND and OR assume the inputs are independent, and every trace says so, because a reviewer should see that assumption next to the number.
| form | meaning |
|---|---|
Q("pii"), Q("dept")["billing"], Q("urgency")[3] | a question's probability, or one option's |
~a, a & b, a | b, e >= tau | NOT, AND, OR, threshold with an uncertainty band |
argmax("dept", min_confidence=…) | top option; abstain below the confidence floor |
majority("q1", "q2", "q3") | vote across paraphrased questions |
verify("dept", check=Q("supported"), tau=…) | a negative checker: escalate when the check doesn't support the pick |
order("severity", [c1, c2, …]) | bucket an ordered score |
G("route")["billing"] | gates over gates |
Numbers
The 2025 article, re-run on a model built for this
The original write-up classified 100 water-utility customer calls into eleven types with two LLM parsers and a negative checker, combined into confidence tiers. Same calls, same circuit, one call to a System One model:
| 2025 · Claude Sonnet 3.7, three LLM calls | 2026 · Jev, one call | |
|---|---|---|
| single question, no circuit | 91% | 98% |
| circuit, overall | 87% | 98% |
| high-confidence calls | 80 calls · 92.5% right | 93 calls · 97.8% right |
| latency | three round trips | 325 ms for all three questions |
And a test that didn't exist before: nine kinds of judgment (extract, compare, count, apply a rule, check a claim against a record, …) times six ways of laying out the data, every label computed by code. Jev scores 95% on it. It also gets confident on inputs built to be undecidable, which is exactly what a threshold with a band is there to catch.
Agents
The circuit sits where the agent shouldn't be trusted
LangChain
CircuitToolGuard judges each tool call: allow, block, or pause with the standard human-in-the-loop interrupt. CircuitRouter picks a model per run.
OpenAI Agents SDK
Input, output, and tool guardrails from a circuit. Tripwires carry the gate's probability and trace.
Claude Agent SDK
A PreToolUse hook whose allow / deny / ask maps straight onto the gate's decided / blocked / uncertain.
guard = CircuitToolGuard(c, jev, gate="block", tools=[delete_file, send_email])
agent = create_agent(model, tools=[read_file, delete_file, send_email], middleware=[guard])
Compared with a single yes/no classifier at a fixed 0.5, a circuit combines several questions, makes the threshold and its band explicit, and sends the uncertain cases to a person instead of silently allowing or blocking them.
Models
Built for System One models
Circuits need calibrated probabilities. That's what a System One model produces: typed questions in, a distribution per question out, in one pass, in about 200 ms. The SystemOne backend talks to any server speaking that contract.
Jev · TypeSafe
The model that made this practical. Drop in an API key.
circuit-1.7b · open weights
Our own S1 model, trained on code-labeled data with a pointer readout. Runs on a laptop.
Yours
A backend is one method: answer(state, questions). Wrap a cache, inject code-owned facts, chain fallbacks.
No S1 model yet? Chat models can stand in through logprobs (OpenAI-compatible) or tool use (Claude), with the caveat that a chat model's stated confidence isn't calibrated the way an S1 model's output is.