Tour the demo repository
The helixor-decision-demos repository holds runnable examples for the runtime. This page walks its structure: what each directory is for, which example shows what, and which ones run with nothing but the runtime wheel. Run the Quickstart first; it clones the repository and installs the runtime.
The repository is private for now
You get read access with your Developer license request. Links on this page go to https://github.com/HelixorAI/helixor-decision-demos and work once your GitHub account has access. The repository's code is Apache-2.0; the runtime it calls is proprietary and is not in it.
Directories#
| Directory | What it is for |
|---|---|
examples/ | The tutorial, 01 to 08, on the runtime's built-in example pack (data protection). Each adds one capability: evaluate, measure, guard a prompt, stream, serve, custom rules, generated SDK. |
use_cases/ | The runtime's other engines on business problems: loan recourse, demand forecasting, belief tracking, routing, rostering and sales dialogue. |
integrations/ | Patterns that connect the runtime to other systems: a batch CSV pipeline, a guardrail for an agent framework, and clients for a Helixor server. |
playbooks/ | regulatory_pii_guard.yaml, the playbook behind the built-in example pack. Read it before you write your own; see Playbooks. |
sdks/ | Typed Python and Java clients generated from the example pack's manifest. The native library they are written for is Planned; the Python client runs its generated evaluator when you ask for it explicitly. |
docs/ | ARCHITECTURE.md: what the 0.2.x runtime does and does not protect. |
tests/ | Checks that the examples compute what they print, plus repository hygiene. Run them with pip install -e ".[dev]" and python -m pytest. |
run_all.sh | Runs every example and prints PASS, FAIL, SKIP or KNOWN for each, with the reason. |
Which example shows what#
The last column is what run_all.sh reported on a clean checkout with only the runtime wheel installed.
| Example | What it demonstrates | With the wheel alone |
|---|---|---|
examples/01_quickstart.py | Your first decisions: action, clean output and receipt for four payloads. Quickstart step 4. | PASS |
examples/02_batch_benchmark.py | Throughput and p50/p90/p99 engine latency over 5,000 evaluations on your machine. See Reproduce the benchmarks. | PASS |
examples/03_prompt_interceptor.py | Decide on a prompt before it reaches a language model: send, send redacted, or stop. Quickstart step 5. | PASS |
examples/04_streaming_interceptor.py | Redact a token stream in flight and halt it on a fatal match; sync and async filters. Quickstart step 5. | PASS |
examples/05_http_service.py | The engine as an HTTP and SSE service. Starts and stops its own server on a free loopback port. | PASS |
examples/06_decision_protocols.py | REST, SSE and WebSocket against one engine. Starts and stops its own server. | PASS |
examples/07_custom_rules.py | Where custom rules go: in a playbook you compile with your Developer license, not into the built-in pack. | PASS |
examples/08_generated_sdk_client.py | The generated typed Python client: typed state, decide(), batch. | PASS |
use_cases/loan_recourse.py | The smallest change that flips a denied loan, then a stress test. Quickstart steps 5 and 6. | PASS |
use_cases/demand_forecasting.py | A Bayesian forecaster switching regime. Its "95%" interval is not calibrated: 8 of the 13 demo actuals fall outside it. | PASS |
use_cases/belief_tracking.py | Confidence in a hypothesis per context, with contradictions weighted more than confirmations. | PASS |
use_cases/fleet_routing.py, shift_rostering.py | Feasibility checks, suggestions and ranked fallbacks before planning routes or rosters. Routing plans in 0.2.1 are checked against hard constraints, not optimized. | SKIP: needs the helixor-solvers package, not part of the wheel |
use_cases/sales_arbitration.py | Sales dialogue arbitration. | KNOWN: 0.2.1 stops with FileNotFoundError: sales binding not found |
integrations/05_governed_query.py | A local simulation of the governed-query contract: different fields for different roles, with an access receipt. It calls neither the runtime nor a data source. Governed data access is Planned. | PASS |
integrations/06 (guardrail) | A guardrail on model output, in the shape an agent framework expects. The model output is canned text. | PASS |
integrations/07_batch_csv_pipeline.py | A CSV of records through the runtime field by field, with a clean file and a per-field report. | PASS |
integrations/01 to 04 | Clients for a Helixor server: evaluate, decide with streaming, the playbook lifecycle, ontology binding. | SKIP: need a server (HELIXOR_API_URL), which is not part of the license request |
Run it all#
./run_all.sh
Helixor decision demos: helixor_runtime 0.2.1, Python 3.12.13 Examples (PII Guard tutorial) PASS examples/01_quickstart.py 0.1s PASS examples/02_batch_benchmark.py 0.3s ... Use cases PASS use_cases/loan_recourse.py 0.1s ... SKIP use_cases/fleet_routing.py needs the helixor-solvers package (not in the runtime wheel) SKIP use_cases/shift_rostering.py needs the helixor-solvers package (not in the runtime wheel) KNOWN use_cases/sales_arbitration.py runtime 0.2.1 does not package the sales playbook ... Result: 14 passed, 0 failed, 6 skipped, 1 known issues
A SKIP names what the example needs; a KNOWN names a documented runtime defect and checks that the example still fails with that error, so a fix is noticed. Neither counts as a pass. The script exits non-zero on any FAIL; add -v to see the last lines of a failure.
A suggested order#
| If you want to | Take, in order |
|---|---|
| Guard what goes into and out of a language model | examples/01, 03, 04, then integrations/06, then the Guard a model call tutorial |
| Serve decisions to services in other languages | examples/01, 05, 06, then Serve decisions to other languages |
| Process files and keep an audit trail | examples/01, 02, integrations/07, then Run decisions over a batch |
| Explain and reverse adverse decisions | use_cases/loan_recourse.py: change a cap as in Quickstart step 6, then add a candidate change of your own |
| Decide on your own rules | examples/07, read playbooks/regulatory_pii_guard.yaml, then Add custom rules with your Developer license |
How this page was verified#
The statuses and output above come from run_all.sh on a fresh clone of the repository (commit 1ed2315) in a new Python 3.12 virtual environment with only the runtime 0.2.1 wheel installed, on 2026-09-29. The tests (python -m pytest) reported 29 passed and 2 skipped (the routing and rostering tests, for the same reason as above).