Use Autohand Code with AI integration skill guidance to add model calls, prompts, safety checks, streaming, and user-facing states.
Connect model calls to product behavior
AI features Build and change Implementation Code
autohand -p "Add this AI feature with model configuration, safety checks, streaming states, and tests"
A product AI feature with model configuration, prompt boundaries, UI states, and validation.
Add an AI feature to an app with Autohand Code is an AI product workflow that connects model calls to app behavior with prompts, configuration, safety checks, streaming or loading states, and tests. ### At a glance | Question | Answer | | --- | --- | | Best for | summaries, drafting, classification, assistant panels, retrieval-backed answers, and AI actions inside an existing app | | Primary inputs | User workflow and expected AI output; Model provider, prompt constraints, data sources, and privacy rules; UI states, error handling, rate limits, and tests | | Autohand Code returns | A product AI feature with model configuration, prompt boundaries, UI states, and validation. | | Avoid when | the product has no clear success criteria or the model output cannot be validated by users or tests | ### How Autohand Code handles this workflow 1. Finds the app boundary where AI behavior belongs. 2. Adds model configuration, prompt inputs, safety limits, and fallback behavior. 3. Builds loading, streaming, empty, and error states that match the product. 4. Adds tests, mocks, or manual validation for expected and unsafe outputs. ### Best inputs - User workflow and expected AI output - Model provider, prompt constraints, data sources, and privacy rules - UI states, error handling, rate limits, and tests ### Strong prompt autohand -p "Add this AI feature with model configuration, safety checks, streaming states, and tests" ### Autohand Code CLI options - Use `/skills use firebase-ai-logic`, `/skills use azure-ai`, or a provider-specific AI skill for integration guidance. - Run `autohand -p "Add this AI feature with model configuration, safety checks, streaming states, and tests"` with product acceptance criteria. - Use `/mcp` for approved docs, schema, or retrieval tools needed by the feature. ### Review before accepting Review model config, prompt boundaries, privacy handling, UI states, tests or mocks, and failure behavior. ### Source and validation signals Autohand AI maintains this workflow as first-party product guidance for Autohand Code. Use the [Autohand CLI Playbook](https://github.com/autohandai/code-cli/blob/main/docs/AUTOHAND_PLAYBOOK.md), [CLI reference](/docs/working-with-autohand-code/cli-reference.html), and [configuration reference](https://github.com/autohandai/code-cli/blob/main/docs/config-reference.md) when choosing between interactive mode, command mode, auto-mode, feature-enabled /goal, /settings, skills, MCP, and permission settings. The related resources below link to product docs and tutorials for the workflow, and the final answer should name repository-specific files, commands, outputs, or docs that a reviewer can verify. ### Frequently asked questions ### What is Add an AI feature to an app with Autohand Code? Add an AI feature to an app with Autohand Code is an AI product workflow that connects model calls to app behavior with prompts, configuration, safety checks, streaming or loading states, and tests. ### When should a team use Add an AI feature to an app? Use it when an AI call needs to become a product feature with states, policy, and validation. ### What evidence should reviewers check for Add an AI feature to an app? Review model config, prompt boundaries, privacy handling, UI states, tests or mocks, and failure behavior.
Skill Skilled: Firebase AI Logic Use app-level AI feature integration guidance. https://skilled.autohand.ai/skill/firebase-ai-logic Guide Model Selection Choose model behavior for the workflow. /docs/guides/model-selection.html Reference MCP Servers Connect approved tools and knowledge sources. /docs/working-with-autohand-code/mcp-servers.html