# Kiln - Doramagic AI Context Pack > Purpose: pre-work context for the user's host AI. This pack does not prove that the project has been installed, run, or validated. ## Project - canonical_name: `Kiln-AI/Kiln` - capability: Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more. - expected_user_outcome: Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more. ## Operating Boundaries - Do not claim that the project has been installed, run, called through an API, or used on local files unless separate evidence proves it. - Project facts must come from repo evidence, Claim Graph, or explicit source references. - When a capability is not verified, mark it as unverified instead of completing it as fact. - publish_status: `publishable` - blocking_gaps: none --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Kiln Overview and System Architecture**: importance `high` - source_paths: README.md, pyproject.toml, Makefile, CONTRIBUTING.md, AGENTS.md - **AI/ML Pipeline: Models, Adapters, Evals, Optimizers, Fine-Tuning, RAG, and Agents**: importance `high` - source_paths: libs/core/kiln_ai/adapters/model_adapters/base_adapter.py, libs/core/kiln_ai/adapters/model_adapters/litellm_adapter.py, libs/core/kiln_ai/adapters/model_adapters/mcp_adapter.py, libs/core/kiln_ai/adapters/model_adapters/litellm_config.py, libs/core/kiln_ai/adapters/eval/eval_runner.py - **Desktop App, Web UI, and the Kiln Chat Assistant**: importance `high` - source_paths: app/desktop/desktop.py, app/desktop/desktop_server.py, app/desktop/run_desktop_dev.sh, app/web_ui/src/routes/(app)/+layout.svelte, app/web_ui/src/routes/(app)/assistant/+page.svelte - **Backend REST API, Data Model, Git Sync, and Extensibility**: importance `medium` - source_paths: libs/server/kiln_server/server.py, libs/server/kiln_server/run_api.py, libs/server/kiln_server/task_api.py, libs/server/kiln_server/project_api.py, libs/server/kiln_server/prompt_api.py ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `4e9bad4fb59d846950fa8d29de9b94c7feb20c2b` - inspected_files: `README.md`, `pyproject.toml`, `uv.lock` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Maintenance risk requires verification - Trigger: Project evidence flags a maintenance risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Maintenance risk requires verification - Trigger: issue_or_pr_quality=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 6: Maintenance risk requires verification - Trigger: release_recency=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/Kiln-AI/Kiln - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.