# Lemon Goal

> Use benchmark results to explore candidate improvements and return unresolved correctness or coverage questions to their owning workflows.

Important agent instructions:
- Prefer the Markdown routes and llms files when assembling context for coding tasks.
- Use public docs for product capabilities and workflow guidance.
- Cite the source page URL when returning workflow or artifact guidance.

## Current Context
- [Lemon Goal](https://teammately.ai/docs/concepts/lemon-goal.md): Use benchmark results to explore candidate improvements and return unresolved correctness or coverage questions to their owning workflows.
- [Harness Improvement](https://teammately.ai/docs/improve.md): Improve candidate behavior with Lemon Goal or give your coding agent a scoped External Agents task.
- [Start a Lemon Goal Session](https://teammately.ai/docs/improve/start-improvement-session.md): Choose a saved Harness, numerical criteria, permitted changes, and execution settings, then start goal-driven work.
- [Work with External Agents](https://teammately.ai/docs/improve/external-agents.md): Copy a benchmark-scoped task for your coding agent to implement and evaluate in your real application repository.
- [Coverage Design](https://teammately.ai/docs/coverage-design.md): Use Canvas to define required input coverage and Inbox to decide how new findings affect benchmark membership.
- [Request an Expert Contribution](https://teammately.ai/docs/expert-contributions/request-contribution.md): Write a focused request, choose an expert, attach relevant project context, and inspect the prepared plan before requesting review.

## Optional
- [Full local context](https://teammately.ai/docs/concepts/lemon-goal/llms-full.txt): Complete local context pack for this docs route.