Skip to content
View ravnlab's full-sized avatar

Block or report ravnlab

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ravnlab/README.md

RavnLab

The AI execution studio. Models are commoditizing; the value is the layer between a raw model and real-world value. We make AI reliable (data & evaluation), useful (automation & agents), and understandable (a creative studio for AI companies) - and everything we make is demonstrable.

Our client work is confidential by default, so what we publish is the kind of work you can verify yourself:

repository what it is
ravnlab-eval-harness The Plausible-Wrong Benchmark (RL-PWB-1) - 20 expert-anchored trap cases across law, medicine, finance, and engineering, with a zero-dependency grading harness and an Inspect AI adapter
pwmetrics Reference metrics for confident-wrong failure: grounding, calibration (ECE), the overconfidence gap, refusal correctness
review-gate-mcp A working MCP server that asks a human when it isn't sure - extraction with a human-review gate
confident-wrong-field-guide The research note behind all of it: a cross-domain taxonomy of the answer that reads perfectly and is false, every figure source-labeled

The standard everything is graded under is public: The RavnLab Evaluation Rubric, v1.0 · free tool: The Confident-Wrong Checklist · site: ravnlab.com

Pinned Loading

  1. confident-wrong-field-guide confident-wrong-field-guide Public

    A cross-domain taxonomy of the AI failure that matters most in production: the answer that reads perfectly and is false. Every figure source-labeled.

  2. pwmetrics pwmetrics Public

    Reference metrics for confident-wrong AI failure: grounding, calibration (ECE), the overconfidence gap, and refusal correctness. Zero dependencies.

    Python

  3. ravnlab-eval-harness ravnlab-eval-harness Public

    The Plausible-Wrong Benchmark (RL-PWB-1) - public case set and grading harness for confident-wrong AI failure. Graded under the RavnLab Evaluation Rubric v1.0.

    Python

  4. review-gate-mcp review-gate-mcp Public

    An MCP server that asks a human when it isn't sure - document extraction with a human-review gate.

    JavaScript