Skip to content
View lucianareynaud's full-sized avatar
11 followers · 8 following

Block or report lucianareynaud

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
lucianareynaud/README.md

Luciana Reynaud Ferreira

LLM Production Systems Engineer — FinOps · Observability · Governance

I build the control-plane layer for production AI systems: cost attribution, model routing, telemetry, policy enforcement, and auditability as engineering constraints from the start.

My repositories are reference implementations of that layer — inspectable, tested, and built to answer operational questions most teams cannot answer today.

→ lucianareynaud.github.io → medium.com/@lucianareynaud → linkedin.com/in/lucianareynaud

Pinned Loading

  1. llmscope llmscope Public

    PyPI-distributable LLM control plane: gateway choke point, cost attribution, OTel instrumentation, and offline reporting as an inspectable engineering artifact.

    Python 1

  2. llm-eval-gate llm-eval-gate Public

    Evidence-based quality gate for LLM deployments: evaluates telemetry against latency, cost, and error policies to produce auditable go/no-go release decisions for CI/CD.

    Python

  3. llmscope-reference llmscope-reference Public

    Pre-dispatch policy evaluation and cost attribution for LLM inference, built on llmscope.

    Python

  4. guardspan guardspan Public

    Compliance-aware LLM workflow for regulated financial environments: policy enforcement, model routing, output validation, and correlated audit trail via LangGraph and OTel.

    Python

  5. agent-cost agent-cost Public

    FinOps cost attribution for AI code agents: maps Kiro, Cursor, and Claude Code spend to git commits to reveal per-task cost, waste patterns, and agent ROI signals.

    Shell

  6. caseledger caseledger Public

    Policy-bounded decision traces for AI-assisted financial operations: versioned policy enforcement, human-in-the-loop gating, cost attribution, and auditable case outcomes.

    Python