docs: add AI attribution policy

Documents the project's AI tool policy across contributor-facing
locations: optional Assisted-by trailer for humans, default-on for
AI assistants, and an Attribution checkbox in all PR templates.

Assisted-by: Claude Code
Signed-off-by: Alex Bozarth <ajbozart@us.ibm.com>

Author: ajbozarth

.github/PULL_REQUEST_TEMPLATE/component.md

@@ -25,3 +25,6 @@ Use this template when adding or modifying components in `mellea/stdlib/componen
 - [ ] Tests added to `tests/components/`
 - [ ] New code has 100% coverage
 - [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)
+
+### Attribution
+- [ ] AI tools used (Assisted-by trailer added to commits)

.github/PULL_REQUEST_TEMPLATE/misc.md

@@ -16,3 +16,6 @@
 - [ ] Tests added to the respective file if code was changed
 - [ ] New code has 100% coverage if code as added
 - [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)
+
+### Attribution
+- [ ] AI tools used (Assisted-by trailer added to commits)

.github/PULL_REQUEST_TEMPLATE/requirement.md

@@ -28,3 +28,6 @@ Use this template when adding or modifying requirements in `mellea/stdlib/requir
 - [ ] Tests added to `tests/requirements/`
 - [ ] New code has 100% coverage
 - [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)
+
+### Attribution
+- [ ] AI tools used (Assisted-by trailer added to commits)

.github/PULL_REQUEST_TEMPLATE/sampling.md

@@ -26,3 +26,6 @@ Use this template when adding or modifying sampling strategies in `mellea/stdlib
 - [ ] Tests added to `tests/sampling/`
 - [ ] New code has 100% coverage
 - [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)
+
+### Attribution
+- [ ] AI tools used (Assisted-by trailer added to commits)

.github/PULL_REQUEST_TEMPLATE/tool.md

@@ -20,3 +20,6 @@ Use this template when adding or modifying components in `mellea/stdlib/tools/`.
 - [ ] Tests added to `tests/stdlib/tools/`
 - [ ] New code has 100% coverage
 - [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)
+
+### Attribution
+- [ ] AI tools used (Assisted-by trailer added to commits)

AGENTS.md

@@ -95,33 +95,44 @@ mkdir -p .bob && ln -s ../.agents/skills .bob/skills
 
 Pre-commit runs: ruff, mypy, uv-lock, codespell
 
-## 7. Timing
+## 7. AI Attribution
+
+AI tools are welcome for development work in this project.
+
+**For AI assistants:** The project requires sign-offs — use `-s` when committing. Do not add a separate `Signed-off-by` line in the AI's own name. Add an `Assisted-by:` trailer to the commit footer by default:
+
+```text
+Assisted-by: Claude Code
+Assisted-by: IBM Bob
+```
+
+## 8. Timing
 > **Don't cancel**: `pytest` (full) and `pre-commit --all-files` may take minutes. Canceling mid-run can corrupt state.
 
-## 8. Common Issues
+## 9. Common Issues
 | Problem | Fix |
 |---------|-----|
 | `ComponentParseError` | Add examples to docstring |
 | `uv.lock` out of sync | Run `uv sync` |
 | Ollama refused | Run `ollama serve` |
 | Telemetry import errors | Run `uv sync` to install OpenTelemetry deps |
 
-## 9. Self-Review (before notifying user)
+## 10. Self-Review (before notifying user)
 1. `uv run pytest test/ -m "not qualitative"` passes?
 2. `ruff format` and `ruff check` clean?
 3. New functions typed with concise docstrings?
 4. Unit tests added for new functionality?
 5. Avoided over-engineering?
 
-## 10. Writing Tests
+## 11. Writing Tests
 
 - Place tests in `test/` mirroring source structure
 - Name files `test_*.py` (required for pydocstyle)
 - Use `gh_run` fixture for CI-aware tests (see `test/conftest.py`)
 - Mark tests checking LLM output quality with `@pytest.mark.qualitative`
 - If a test fails, fix the **code**, not the test (unless the test was wrong)
 
-## 11. Writing Docs
+## 12. Writing Docs
 
 If you are modifying or creating pages under `docs/docs/`, follow the writing
 conventions in [`docs/docs/guide/CONTRIBUTING.md`](docs/docs/guide/CONTRIBUTING.md).
@@ -139,7 +150,7 @@ Key rules that differ from typical Markdown habits:
   mellea source; mark forward-looking content with `> **Coming soon:**`
 - **No visible TODOs** — if content is missing, open a GitHub issue instead
 
-## 12. Feedback Loop
+## 13. Feedback Loop
 
 Found a bug, workaround, or pattern? Update the docs:
 

CONTRIBUTING.md

@@ -283,6 +283,17 @@ Closes #123
 git commit -s -m "feat: your commit message"
 ```
 
+### AI Tools
+
+AI-assisted development is welcome. You are responsible for reviewing and understanding every change before submitting.
+
+AI tools following project guidelines add an `Assisted-by:` trailer to commit messages by default, identifying which tool was used:
+
+```text
+Assisted-by: Claude Code
+Assisted-by: IBM Bob
+```
+
 ### Pre-commit Hooks
 
 Pre-commit hooks run automatically before each commit and check:

docs/docs/community/contributing-guide.md

@@ -171,6 +171,10 @@ git commit -s -m "feat: your commit message"
 
 **Branch naming:** `feat/topic`, `fix/issue-id`, `docs/topic`
 
+### AI tools
+
+AI-assisted development is welcome. You are responsible for reviewing and understanding every change before submitting. AI tools following project guidelines will add an `Assisted-by:` trailer to commit messages by default.
+
 ### Pre-commit hooks
 
 Pre-commit hooks run automatically before each commit and check: