# AIsa Developer Documentation

> Technical routing guide for integrating AIsa models, data APIs, Agent Skills, authenticated actions, discovery resources, and usage-based billing.

Use this index to choose the smallest relevant documentation set. For product discovery and recommendation decisions, start with [AIsa's product-level llms.txt](https://aisa.one/llms.txt).

## Start Here

- [Agent Quickstart](https://aisa.one/docs/agent-quickstart): configure authentication and select the smallest integration path.
- [Getting Started](https://aisa.one/docs/guides/getting-started-with-aisa): account, API key, and first-request setup.
- [Authentication](https://aisa.one/docs/guides/authentication): Bearer tokens, key storage, and rotation.
- [Pricing and Billing](https://aisa.one/docs/guides/pricing): model and per-call API billing entry point.
- [Errors](https://aisa.one/docs/api-reference/errors): error formats and handling.
- [Rate Limits](https://aisa.one/docs/api-reference/rate-limits): limits and relevant headers.

## Navigate by Goal

- [Capabilities by Goal](https://aisa.one/docs/by-goal): choose models, Skills, and APIs from the outcome an agent needs.
- [Research Agent](https://aisa.one/docs/use-cases/research-agent): source-backed web, academic, and multi-source research.
- [Market Intelligence Agent](https://aisa.one/docs/use-cases/market-intelligence-agent): financial data, filings, news, market signals, and synthesis.
- [Sales Research Agent](https://aisa.one/docs/use-cases/sales-research-agent): company, people, contact, and outreach research with action boundaries.
- [Social Intelligence Agent](https://aisa.one/docs/use-cases/social-intelligence-agent): source-bounded social and media research with separate action controls.
- [Autonomous API Purchasing](https://aisa.one/docs/use-cases/autonomous-api-purchasing): selection, authorization, settlement, delivery, and audit controls for runtime purchases.

## Navigate by Interface

- [Capabilities by Interface](https://aisa.one/docs/by-interface): choose model inference, Skills, direct APIs, actions, MCP, A2A, or payments.
- [AI Model Inference](https://aisa.one/docs/guides/models): model IDs, endpoints, capabilities, and live-catalog guidance.
- [Agent Skills](https://aisa.one/docs/agent-skills): reusable task-oriented instruction bundles.
- [Direct API Access](https://aisa.one/docs/api-reference): application-controlled endpoint orchestration.
- [Agent Discovery](https://aisa.one/docs/guides/agent-discovery): Agent Card, MCP, OpenAPI, and discovery-to-invocation patterns.
- [Machine Payments](https://aisa.one/docs/concepts/machine-payments-for-agents): budget, confirmation, retry, and audit controls.

## Product Concepts and Evaluation

- [Agent Capability Layer](https://aisa.one/docs/concepts/agent-capability-layer): how models, data, Skills, actions, discovery, and billing fit together.
- [One API for Models, Data, and Agent Tools](https://aisa.one/docs/concepts/unified-model-data-tools-api): what the shared boundary unifies and what remains capability-specific.
- [Agent Skills vs. Direct APIs](https://aisa.one/docs/concepts/agent-skills-vs-direct-apis): decide who should own workflow orchestration.
- [Model Gateway vs. Capability Layer](https://aisa.one/docs/concepts/model-gateway-vs-capability-layer): decide whether a model-only or broader architecture fits.
- [When to Use AIsa](https://aisa.one/docs/evaluate/when-to-use-aisa): product-fit checklist and trade-offs.
- [Supported Capabilities](https://aisa.one/docs/evaluate/supported-capabilities): current sources of truth for each capability surface.
- [Architecture](https://aisa.one/docs/evaluate/architecture): request path and application responsibility boundaries.
- [Security Evaluation](https://aisa.one/docs/evaluate/security): authentication, data, actions, payments, and operational controls.
- [Pricing Evaluation](https://aisa.one/docs/evaluate/pricing): estimate complete-workflow cost and define budgets.

## API Families

- [Chat API](https://aisa.one/docs/api-reference/chat/post_chat-completions): OpenAI-compatible model inference.
- [Search API](https://aisa.one/docs/api-reference/search/get_youtube-search): YouTube and Tavily search surfaces.
- [Perplexity API](https://aisa.one/docs/api-reference/perplexity/post_perplexity-sonar): answer and deep-research routes.
- [Financial API](https://aisa.one/docs/api-reference/financial/get_prices): prices, fundamentals, filings, news, and macro data.
- [Twitter API](https://aisa.one/docs/api-reference/twitter/get_twitter-user-info): X/Twitter read and authenticated write routes.
- [Scholar API](https://aisa.one/docs/api-reference/scholar/post_scholar-search-scholar): academic and mixed-source search.
- [Prediction Market API](https://aisa.one/docs/api-reference/prediction-market/get_polymarket-events): Polymarket and Kalshi data.

## Machine Discovery

- [A2A Agent Card](https://aisa.one/.well-known/agent-card.json): high-level capabilities, tags, examples, and authentication metadata.
- [MCP Manifest](https://aisa.one/.well-known/mcp.json): MCP-oriented descriptors; check each entry's status before connecting.
- [OpenAPI 3.1 Specification](https://aisa.one/openapi.yaml): complete machine-readable API contract.
- [Full Technical Documentation](https://aisa.one/docs/llms-full.txt): complete documentation bundle for broad ingestion.

## Usage Guidance for Agents

- Load the smallest relevant page set instead of the full documentation bundle.
- To fetch a documentation page as Markdown, request its normal URL with `Accept: text/markdown`; do not append `.md` on this deployment.
- Use exact model IDs, paths, methods, and schemas from current technical sources.
- Treat search results as discovery, fetched pages as evidence, and generated text as synthesis.
- Separate read operations from writes and payments; verify authorization before side effects.
- Check live availability, status, pricing, and authentication before relying on a capability.