# Welcome to Help Center **Twig is an API-first RAG platform for building AI agents backed by your data sources.** ## What is Twig? Twig provides: * RAG infrastructure with vector search and LLM orchestration * Data connectors for ingestion and sync from external sources * Agent configuration APIs and UI for behavior, prompts, and RAG strategy selection * Validation framework to check for hallucinations, missing citations, and accuracy * Deployment targets: REST API, embeddable widgets, browser extensions, Slack/Outlook/Zendesk apps ### Core Capabilities #### 🔌 Data & Integration * **Data Connectors** - Zendesk, Confluence, Slack, Google Drive, SharePoint, OneDrive, GitBook, Notion, websites, and others. See [full list](https://github.com/thrivapp/twig-help-docs/blob/staging/data-integration/connectors.md). * **Sync Schedules** - Configure refresh intervals (hourly, daily, weekly, or manual) per data source * **PII Detection** - Regex-based and NER-based filtering before indexing (configurable per organization) * **Multi-Tenant Architecture** - Organization-level data isolation with per-tenant embeddings * **REST API & MCP Server** - Programmatic control over agents, queries, data sources, and evals #### 🤖 Agent Builder & Intelligence * **Agent Configuration UI** - Web UI for configuring prompts, temperature, model selection, and data source filters * **RAG Strategies** - Redwood (single-pass retrieval), Cedar (multi-query expansion), Cypress (agentic multi-hop with tool calling) * **Session Memory** - Conversation history stored per session (retention: 30 days default) * **Agentic Workflows** - Multi-step reasoning with function calling (requires Cypress RAG strategy) * **Agent Personas** - System prompt configuration, response length limits, tone presets, data source scoping #### ✅ Quality & Validation * **7-Dimensional Validation** - Checks for: hallucination (claim not in sources), missing data (retrieval gaps), accuracy (factual errors), relevance (off-topic), tone (persona mismatch), completeness (partial answers), citations (source attribution) * **Source Attribution** - Inline citations with document ID, chunk ID, and URL (when available) * **Evaluation Framework (Evals)** - Run test queries against agents to measure: answer accuracy, latency (p50/p95), retrieval precision/recall, cost per query * **Quality Workbench** - Review agent responses, tag incorrect answers, capture feedback for fine-tuning * **Hybrid Inbox** - Agent drafts responses, human approves/edits before sending (available in Zendesk/HelpScout apps) #### 🚀 Deployment & Scalability * **Deployment Channels** - REST API, embeddable widget (iframe), Chrome extension, Slack app, Outlook add-in, Zendesk native app, HelpScout app * **Infrastructure** - Self-hosted: Docker/Kubernetes manifests available. Cloud: Hosted on AWS with auto-scaling. * **Observability** - Query logs with retrieval traces (which chunks were retrieved, why), latency breakdowns (embedding, retrieval, LLM), error tracking * **Caching** - Query result cache (configurable TTL), embedding cache (deduplication at ingestion) #### 🔐 Enterprise Security * **SSO Integration** - SAML 2.0 and OAuth 2.0 (Google, Microsoft, Okta, Auth0) * **Role-Based Access Control** - Roles: Admin, Developer, Viewer. Permissions: manage agents, manage data sources, view analytics, API access. * **Data Residency** - Embeddings and metadata stored in: US East (default), EU West, AP Southeast (configurable per organization) * **Compliance** - GDPR: data deletion APIs, export APIs. HIPAA: BAA available on Enterprise plan. * **Audit Trails** - All queries, data source syncs, user actions logged with timestamps, user IDs, IP addresses ## Quick Start **Prerequisites**: Twig account with API access ```bash # Set your API key export TWIG_API_KEY="your_api_key_here" # Create an agent curl -X POST https://api.twig.so/v1/agents \ -H "Authorization: Bearer $TWIG_API_KEY" \ -H "Content-Type: application/json" \ -d '{"name": "Support Agent", "rag_strategy": "redwood"}' # Query the agent curl -X POST https://api.twig.so/v1/query \ -H "Authorization: Bearer $TWIG_API_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id": "agent_123", "query": "What is your refund policy?"}' ``` Full setup instructions: [Quick Start Guide](https://help.twig.so/getting-started/quick-start) ## For Engineers ### 🏗️ Architecture & Concepts * [Platform Architecture](https://help.twig.so/getting-started/overview) - Ingestion pipeline, vector DB, LLM orchestration, API layer * [RAG Concepts](https://help.twig.so/getting-started/core-concepts) - Embeddings, vector search, chunking, retrieval scoring * [RAG Strategy Selection](https://help.twig.so/broken-reference) - Redwood vs Cedar vs Cypress: latency, cost, and accuracy tradeoffs ### 💻 API & Integration * [REST API Reference](https://help.twig.so/product/developer-api/rest-api) - Endpoints for agents, queries, data sources, evals * [Authentication](https://help.twig.so/product/developer-api/authentication) - API key generation, bearer token usage, key rotation * [Webhooks](https://help.twig.so/product/developer-api/webhooks) - Events: data\_sync\_complete, eval\_run\_complete, agent\_query\_complete * [SDKs](https://help.twig.so/product/developer-api/sdks) - TypeScript, Python clients (npm/pip packages) * [Rate Limits](https://help.twig.so/product/developer-api/rate-limits) - Current limits: 100 req/min (queries), 10 req/min (data sync) ### 🤖 Building Agents * [Agent Creation](https://help.twig.so/product/overview/add-an-ai-agent-persona) - API and UI steps, required fields, default values * [Agent Configuration](https://help.twig.so/product/overview/configuration) - System prompts, temperature (0-2), model selection (GPT-4, Claude) * [Agentic Workflows](https://help.twig.so/product/advanced/agentic-workflows) - Multi-step planning with Cypress RAG strategy * [Function Calling](https://help.twig.so/product/advanced/agent-tools) - Custom tools, OpenAPI spec format, authentication ### 📊 Data Pipeline * [Data Source Setup](https://help.twig.so/broken-reference) - OAuth flows, API credentials, sync schedules, filters * [Chunking Configuration](https://help.twig.so/rag-scenarios-and-solutions/chunking/optimize-chunks) - Chunk size (default: 512 tokens), overlap (default: 50 tokens), splitting strategies * [Vector Search Tuning](https://help.twig.so/rag-scenarios-and-solutions/vectors/similarity-calibration) - Similarity thresholds, reranking, hybrid search ### 🔍 Debugging & Monitoring * [Retrieval Debugging](https://help.twig.so/rag-scenarios-and-solutions/monitoring/retrieval-debugging) - View retrieved chunks, similarity scores, reranking decisions * [Evaluation Framework](https://help.twig.so/product/monitoring/evals) - Create test sets, run evals, track metrics over time * [Performance Tuning](https://help.twig.so/product/monitoring/performance-tuning) - Latency analysis: embedding (avg 50ms), retrieval (avg 200ms), LLM (varies) * [Cost Tracking](https://help.twig.so/product/monitoring/cost-optimization) - Per-query cost breakdown: embedding, LLM tokens, vector search ## Troubleshooting by Symptom | Symptom | Diagnostic Guide | | ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Agent returns wrong or hallucinated answers | [Retrieval Accuracy](https://help.twig.so/rag-scenarios-and-solutions/accuracy/wrong-answers) - Check retrieval scores, increase top\_k, adjust similarity threshold | | Semantic search returns irrelevant results | [Vector Search Tuning](https://help.twig.so/rag-scenarios-and-solutions/vectors/poor-search-results) - Verify embedding model, test query expansion, enable reranking | | Context window exceeded error | [Token Management](https://help.twig.so/rag-scenarios-and-solutions/llm/context-overflow) - Reduce top\_k, decrease chunk size, use truncation | | Query latency >3s | [Performance Analysis](https://help.twig.so/product/monitoring/performance-tuning) - Profile embedding/retrieval/LLM steps, check cache hit rate | | Data source sync fails | [Data Integration Errors](https://help.twig.so/rag-scenarios-and-solutions/data-integration/confluence-sync) - Verify credentials, check rate limits, review error logs | [View all solutions](#solutions-by-problem) ## Security & Compliance * [Authentication & Authorization](https://help.twig.so/product/security/authentication-authorization) - API keys, SSO, role permissions * [SSO Setup](https://help.twig.so/product/security/sso-integration) - SAML/OAuth configuration steps * [PII Detection](https://help.twig.so/rag-scenarios-and-solutions/privacy/pii-detection) - Enable PII filters, configure regex patterns * [Data Privacy](https://help.twig.so/product/security/data-privacy) - Data residency options, deletion APIs, export APIs ## Support * **Technical Support:** * **Issue Reports:** Include: query ID, agent ID, timestamp, error message, reproduction steps ## Next Steps **New to RAG?** Start with [RAG Concepts](https://help.twig.so/getting-started/core-concepts) - covers embeddings, vector search, and retrieval. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://help.twig.so/readme.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.