Project-STROT

Agents at compile time.  Never at runtime.

pip install strot-ai

import strot

result = strot.run(
    tickets,
    query="Triage incoming support tickets into the correct workflow.",
    action_registry={
        "billing_dispute":  "Refunds, invoice corrections, double charges",
        "technical_defect": "Crashes, bugs, broken behavior",
    },
    llm="anthropic/claude-opus-4-8",   # used once, on first compile only
)

for o in result.outcomes:
    print(o["action"], round(o["confidence"], 2))
# billing_dispute 0.97
# technical_defect 0.94

The LLM runs once, at compile time. Production is a frozen, self-contained
Python artifact: a small local decision model arbitrates every record, nothing
is generated, every output is bounded, and low-confidence records abstain
instead of guessing.

STROT = Agentic Schema Intent + Compiler & State + Code + Execution + NLU
                      ⟹  JSON Decisions
          (classification · scoring · routing · typed answers)

How it works

            COMPILE  (once per intent + schema)
  intent + sample ─▶ synthesize ─▶ golden gate ─▶ teacher labels ─▶ calibrate
                     (labels,      (your known      (annotate         (fit the
                      projection,   answers must     a sample,         confidence
                      handlers)     pass)            once)             threshold)
                                        │
                                        ▼
                             frozen artifact  (.py)

            RUNTIME  (every record, forever)
  record ─▶ projection ─▶ decision model ─▶ confidence gate ─▶ typed JSON
            (compiled)     (144M, CPU,        (decide or         decision
                            ~60 ms)            abstain)

Two surfaces

run() - route each record to an action and execute the compiled handler.

decide() - answer typed questions (choice / score / boolean) per record:

result = strot.decide(records, questions={
    "is_bug_report":     {"type": "boolean", "instructions": "mentions crashes/errors?"},
    "customer_sentiment":{"type": "score", "min": 1, "max": 5, "instructions": "1 angry, 5 happy"},
    "routing_bucket":    {"type": "choice", "options": ["billing", "engineering", "spam"]},
})
# → {"booleans": {...}, "scores": {...}, "choices": {...}}  with probabilities + confidence

Measured

Real model (SupersonicLabs/Julia-1, 144M, CPU), real datasets, clean Docker containers:

Reproduce everything: benchmarks/ - with the losses published too.

On real risk narratives

Record-level, unstructured text - the kind cyber, financial, and insurance
triage actually runs on. Fully public, ground-truth datasets; classes balanced
so accuracy is interpretable; baselines shown; nothing is hand-labeled and STROT
never sees the test labels. (benchmarks/risk_narratives.py)

Both clear their baselines, the compiler lifts accuracy on the same 144M local
model (+2.7pp / +6.9pp), and low-confidence records abstain instead of guessing.
These are honest proof the architecture works on messy real narratives - not
production underwriting accuracy. For that, drop a task-trained specialist in the
nlu= slot; the compiler, calibration, and gate are unchanged.

What makes it different

• Compile once, decide forever - content-addressed artifact cache; schema drift triggers exactly one recompile.
• Golden-record promotion - artifacts must pass your known answers before they serve.
• Fitted guarantees - temperature scaling + split conformal prediction, baked in: dispatched decisions are wrong ≤ α of all records (marginal); the rest abstain.
• Measured, not guessed - the compiler scores labelings, and can train a distilled head, keeping only what beats the baseline on held-out data.
• 0% structural hallucination - output is selection + computation over your registry; nothing is generated at runtime.
• Model-independent - the decision model is a slot (nlu=): local Julia-1 by default, hosted APIs, or any drop-in specialist.

Install

pip install strot-ai            # core: pure stdlib
pip install strot-ai[local]     # + the local decision model (torch/transformers)
pip install strot-ai[hosted]    # + openai, for a hosted decision runtime
pip install strot-ai[anthropic] # + anthropic, for the synthesizer

Bake the local model into your image for offline production:

RUN pip install strot-ai[local] \
 && python -c "import strot; strot.prefetch_nlu(local_dir='/opt/julia-1', install=True)"
ENV STROT_NLU_CHECKPOINT=/opt/julia-1

(Never pip install julia - unrelated package.)

Documentation

DEVELOPERS.md - architecture, compile lifecycle, calibration
semantics and caveats, deployment, model swapping, full API reference.