High Priority
Deploy `ai-agents.txt` Protocol
Establish a machine-readable manifest of your AI SaaS architecture, API endpoints, and knowledge graph specifically for autonomous AI agents.
Create a text file at `/ai-agents.txt` with a concise overview of your AI SaaS's core functionality and data domains.
Include markdown-style links to critical API documentation, SDK repositories, and foundational knowledge base articles.
Add a 'Capabilities' section in the file to explicitly list supported AI tasks (e.g., 'Text Generation', 'Data Analysis', 'Code Synthesis') and associated data formats.
Configure your AI SaaS Builders crawler protocols effortlessly.
Join 2,000+ teams scaling with AI.
High Priority
Agent-Specific Data Access Control
Fine-tune which sections of your AI SaaS, including specific model endpoints and datasets, should be accessible to authorized AI agents.
Define granular access policies using `User-agent:` directives for known AI agents (e.g., `User-agent: Devin`, `User-agent: ChatGPT-API-Crawler`) and custom agent identifiers.
Implement `Allow:` and `Disallow:` rules based on data sensitivity, API rate limits, and functional scope (e.g., `Allow: /api/v1/embeddings/`, `Disallow: /internal/training-data/`).
Utilize an API gateway or middleware to enforce these `ai-agents.txt` directives programmatically and log all agent access attempts for auditing.
Medium Priority
Structured Data for Semantic Ingestion
Leverage semantic HTML and structured data formats (JSON-LD) to enable LLM agents to precisely understand your AI SaaS's feature set and documentation hierarchy.
Wrap distinct AI model features and their parameters within `<section>` tags, using `aria-label` attributes to define the feature name (e.g., `aria-label='LLM Fine-Tuning API'`).
Employ `JSON-LD` schema markup for `SoftwareApplication` and `APIReference` to detail model versions, input/output schemas, and functional parameters.
Ensure all tabular data, especially for API pricing or performance benchmarks, uses `<thead>`, `<tbody>`, and `<th>` for unambiguous data extraction by agents.
High Priority
Contextual Chunking for Retrieval Augmented Generation (RAG)
Structure your AI SaaS documentation and knowledge base content so it can be efficiently 'chunked' and retrieved by RAG pipelines for agent responses.
Maintain conceptual coherence within logical content blocks, ideally under 750 tokens, focusing on single AI concepts or API functionalities.
Prepend each chunk with a clear, concise summary of its primary subject matter to mitigate context drift for retrieval systems.
Eliminate ambiguous pronouns and generic references; explicitly name AI models, features, parameters, or data entities (e.g., 'The `text-davinci-003` model' instead of 'It').
