Skip to main content

FJP-CONF v0.1 — behavioral conformance suite for Judgment-Grounded Agents.

Project description

FJP-CONF — Flow Judgment Protocol Conformance

Flow Judgment Protocol™ (FJP) is the judgment layer for AI agents and enterprise decision systems. It determines what changed, whether it matters, what matters most, and what should happen next.

FJP-CONF is the public, vendor-neutral conformance standard for FJP. It defines what it means for an agent to make accountable decisions — decisions that can be traced, challenged, and audited — and ships a runnable test suite so any developer can verify their own agent.

FJP-CONF tests an agent's observable output, not its internal method. Two agents may reach opposite conclusions and both conform. Conformance asserts that a decision is accountable — not that it is correct.

The idea in one paragraph

Retrieval-grade systems answer what is true. They do not answer was this worth acting on, and how would we know if it wasn't. When an agent acts, three questions must be answerable afterward: what did it act on, why did it judge that worth acting on, and what would have made that judgment wrong. FJP-CONF defines the minimum externalized structure — the Judgment-Grounded Record — that makes those questions answerable, independent of how the agent decides.

The Judgment-Grounded Record

For every action it recommends or takes, a conforming agent emits a record with four components:

Component Answers
signal what changed
judgment why it matters
action what should happen
falsifier what would make it wrong

Conformance levels

Level Name Adds
L0 Structural A well-formed record with all four components.
L1 Grounded Attributable signal; the action traces back to it.
L2 Falsifiable A concrete, checkable condition that would reverse the call.
L3 Accountable Records are retained and the falsifier can be re-evaluated.

Quickstart

Requires Python 3.11+. No third-party dependencies.

# validate a record at Level 2
python -m conformance.runner examples/passing_agent.json --level 2

# a non-conforming record
python -m conformance.runner examples/failing_agent.json --level 2

Exit codes: 0 conforms · 1 does not conform · 2 invalid input.

Programmatic use:

from conformance import evaluate, conforms

results = evaluate(record, level=2)
print(conforms(results))

Level 3 requires your agent to implement a small adapter (get_record, evaluate_falsifier); see conformance/adapter.py and examples/passing_agent_l3.py.

Run the tests:

python -m pytest -q

Claiming conformance

A conformance claim names a level and version and is reproducible by running this suite against your agent's output:

"Conforms to FJP-CONF v0.1, Level 2."

Authoritative verification and any official FJP-CONF certification are administered by Flow Information Systems. This open suite lets anyone self-check; see TRADEMARKS.md for what you may and may not call your implementation.

License and trademarks

Source code is licensed under the Apache License, Version 2.0 — see LICENSE. The code license does not grant rights in the trademarks.

Flow Judgment Protocol™, FJP™, FJP-CONF™, Judgment-Grounded Agent™, and "DNS resolves location. Flow resolves importance."™ are trademarks of Flow Information Systems (https://flowinfo.co). See NOTICE and TRADEMARKS.md.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fjp_conformance-0.1.0.tar.gz (14.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fjp_conformance-0.1.0-py3-none-any.whl (14.3 kB view details)

Uploaded Python 3

File details

Details for the file fjp_conformance-0.1.0.tar.gz.

File metadata

  • Download URL: fjp_conformance-0.1.0.tar.gz
  • Upload date:
  • Size: 14.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for fjp_conformance-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7c203c4afcd305f3116dc8d4ee7db8de8da619faeb9a9446013838d81ce70d16
MD5 64ac11e180311ddbbed6f6855b881be7
BLAKE2b-256 0f7dbae786620bfa81305840d698c81a523dbeab4787fc237eaca10a2b4fdbc9

See more details on using hashes here.

File details

Details for the file fjp_conformance-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for fjp_conformance-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 50828625811c6f97525516f40c70a7ca7cb66bc9ee986002d75083fec2d73fb7
MD5 6edf0166d7ccf7c665568d334d32cd96
BLAKE2b-256 245793897097a75ed6129b7834256be102771f8759aef1b249a63a06e613ff7c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page