delightful-ai

Create or update Braintrust Python SDK integrations built on the integrations API under `py/src/braintrust/integrations/`. Use when adding a new integration package, extending an existing provider integration, changing patchers, tracing, manual `wrap_*()` helpers, integration exports, `auto_instrument()` wiring, `py/noxfile.py` sessions, integration tests, or cassettes. Do not use when migrating an existing legacy wrapper from `py/src/braintrust/wrappers/` into the integrations API; use `sdk-wrapper-migrations` for that.

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

Build AI agents with Pydantic AI — tools, capabilities, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, stream output, define agents from YAML, or test agent behavior.

Run interactive brainstorming across verifiers environments, evaluations, GEPA, and RL training. Use when the user wants ideation, literature scanning, concept teaching, roadmap planning, or research program design grounded in local CLI sources, verifiers, and RL trainer code.

Discover and inspect verifiers environments through the Prime ecosystem. Use when asked to find environments on the Hub, compare options, inspect metadata, check action status, pull local copies for inspection, or choose environment starting points before evaluation, training, or migration work.

Create or migrate verifiers environments for the Prime Lab ecosystem. Use when asked to build a new environment from scratch, port an eval or benchmark from papers or other libraries, start from an environment on the Hub, or convert existing tasks into a package that exposes load_environment and installs cleanly with prime env install.

Run and analyze evaluations for verifiers environments using prime eval. Use when asked to smoke-test environments, run benchmark sweeps, resume interrupted evaluations, compare models, inspect sample-level outputs, or produce evaluation summaries suitable for deciding next steps.

Audit and optimize verifiers environments for async performance. Use when asked to profile, speed up, or review an environment for concurrency bottlenecks, event loop blocking, or scaling issues under high rollout counts.

Use before starting any code work in beads-rs. Establishes jj commit rhythm and bd issue tracking workflow.

Use when creating custom Rust lints with Dylint, implementing LateLintPass or EarlyLintPass, checking code patterns with rustc internals, or when user mentions "lint", "dylint", or "clippy-like"

Use when working on beads from a specific epic, or when asked to "do a bead from <epic-id>". Claims the next available bead from the epic, works it with jj rhythm, verifies, and closes it.

Use when noticing something off (code smell, design smell, workaround) while working and want to capture it without losing flow - grounds observation in codebase and files a proper bead that future agents can execute

Use when verifying Firkin can be installed and used from a fresh external Rust project without local path dependencies.

Use when preparing, publishing, verifying, or diagnosing Firkin crates.io/GitHub releases from the standalone Firkin repository.

Use when iterating quickly on Firkin performance, local profiling, stage timing, bottleneck attribution, smoke evidence, or benchmark-derived instrumentation in the Firkin checkout.

Use rs-hack for large Rust refactors in Firkin/Cube, especially moving the CubeAPI Firkin backend into firkin-runtime::single_node with AST-aware discovery, batch transforms, dry-run/apply/revert discipline, and compile gates.