leaven

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.

Optimize environment system prompts with GEPA through prime gepa run. Use when asked to improve prompt performance without gradient training, compare baseline versus optimized prompts, run GEPA from CLI or TOML configs, or interpret GEPA outputs before deployment.

Review verifiers environments for correctness, robustness, and ecosystem compatibility. Use when asked for environment code review, quality audit, migration validation, or release readiness checks for local environments or environments pulled from the Hub.

Train models with verifiers environments using hosted RL or prime-rl. Use when asked to configure RL runs, tune key hyperparameters, diagnose instability, set up difficulty filtering, or create practical train and eval loops for new environments.

Encode small integer batches using the house checksum protocol.

Product marketing, positioning, GTM strategy, competitive intelligence, ICP definition, April Dunford methodology, product launch planning, messaging workshops, battlecards, market entry guides, sales enablement, persona messaging, category design, analyst relations, pricing narrative, segmentation, and when a user mentions product marketing, positioning, GTM, go-to-market, launch, PMM, competitive teardown, differentiated messaging, buyers, personas, sales deck, or battlecard.

Edit CSV spreadsheets with Python while preserving headers and producing the requested output file.

Use after substantial Leaven planning/spec work and before setting or launching a long-running /goal, especially for public APIs, optimizer/eval/agentic surfaces, paper reproduction, crate topology, or any task where user intent could be replaced by a nearby provable proxy.

Use when writing or reviewing Leaven Rust docstrings, module docs, examples, intra-doc links, Errors, Panics, Safety, feature-gated docs, or dspy-rs signature field descriptions.

Use when changing Leaven fallible APIs, Result surfaces, error enums, failure mapping, retry/display decisions, panic boundaries, or internal OneOf error plumbing.

Use when changing Leaven tests, proof strategy, law/example/scenario/regression coverage, trait contract suites, fixtures, test placement, or local versus full verification.

Use when changing Leaven Rust traits, capability seams, trait laws, cold versus hot trait boundaries, default methods, shared implementations, or downstream implementability.

Use when changing Leaven domain state, IDs, enums, validated data, state transitions, option-vs-sum choices, provenance, or APIs where Rust types can preserve truth.