Knowledge Base
Upload PDFs, docs, CSVs, or crawl your website. The RAG pipeline retrieves relevant context so the agent answers from your content.
Custom Actions
Connect any API with OpenAPI specs, manual configuration, or MCP tools. The agent can take actions on behalf of users.
Workflows
Define specialized behaviors for common scenarios like refunds, onboarding, or troubleshooting.
Identity Verification
Verify end users with HMAC signatures or JWT tokens so the agent can access personalized data securely.
Widget Integration
Drop a script tag into your site. Configure appearance, register client-side tools, and control the widget programmatically.
Analytics
Monitor conversations, collect feedback, and track resolution rates from the dashboard.
How it works
- Configure your agent in the dashboard — set a system prompt, choose a model, and upload knowledge sources.
- Embed the widget on your site with a single script tag and your API key.
- Users ask questions and the agent streams answers using your knowledge base, actions, and workflows.
- Monitor and improve through the activity feed, feedback ratings, and conversation history.
Architecture overview
Agentic Trust runs as a Next.js application backed by PostgreSQL with pgvector. Chat requests are routed to an isolated agent container running the Claude Agent SDK with MCP tool servers for knowledge retrieval, custom actions, and workflow execution.| Component | Technology |
|---|---|
| Dashboard & API | Next.js (App Router), React, Tailwind CSS |
| Database | PostgreSQL + pgvector (Drizzle ORM) |
| Auth | WorkOS AuthKit (dashboard), API keys (widget) |
| AI Models | Claude Sonnet 4.6, Haiku 4.5, GPT-5.2, Gemini, and more |
| Embeddings | OpenAI text-embedding-3-small (1536 dimensions) |
| Agent Runtime | Docker container with Claude Agent SDK + MCP tools |