Skip to main content

Epistemic trust layer for AI agents — confidence tiers, routing, and accountability

Project description

cognilateral-trust

Epistemic trust layer for AI agents. AI that tells you when it's guessing.

from cognilateral_trust import evaluate_trust

result = evaluate_trust(0.7)
if result.should_proceed:
    perform_action()
else:
    escalate(result.accountability_record.reasons)

Confidence Tiers (C0-C9)

Tier Name Route
C0-C3 Unverified → Measured basic
C4-C6 Tested → Falsifiable warrant_check
C7-C9 Governance → Resilient sovereignty_gate

License

Apache-2.0

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

cognilateral_trust-0.5.0.tar.gz (25.9 kB view details)

Uploaded Source

Built Distribution

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

cognilateral_trust-0.5.0-py3-none-any.whl (9.2 kB view details)

Uploaded Python 3

File details

Details for the file cognilateral_trust-0.5.0.tar.gz.

File metadata

  • Download URL: cognilateral_trust-0.5.0.tar.gz
  • Upload date:
  • Size: 25.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.11 {"installer":{"name":"uv","version":"0.10.11","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for cognilateral_trust-0.5.0.tar.gz
Algorithm Hash digest
SHA256 02e9e85944ede911b4a1462f3720eabbdeb2bd9b57dfd9ec0c1b05ed4554cfcb
MD5 96b8db650ceb39f44a85a94bae076df6
BLAKE2b-256 7634cdb41cdf6556016ee9380e484b262947d9f79a014fbd83c03c136358cb94

See more details on using hashes here.

File details

Details for the file cognilateral_trust-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: cognilateral_trust-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 9.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.11 {"installer":{"name":"uv","version":"0.10.11","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for cognilateral_trust-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a59f9596baa7dcf0e3e755c312fd7e7778105992cc83519c1a0c640ddf5411ad
MD5 539116e02072bc69da341c5c81e95b5e
BLAKE2b-256 707af7d953a72acd327d38120673782a3bde8c10e4916aa0a18337f7c364e729

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