JSON-Driven Agent Logic
In EDDI, everything that defines an agent's behavior is a JSON configuration resource: rules (system prompts), LLM connector settings, workflow pipelines, tool configurations, and deployment descriptors. No code changes, no redeployment.
Why This Matters
- No redeployment β Change agent behavior by updating JSON, not source code
- Prompt engineer friendly β Non-developers modify rules via UI or REST API
- Version controlled β JSON configs live in Git alongside infrastructure-as-code
- Hot-reloadable β Changes take effect immediately, no server restart needed
- Auditable β Every configuration change is tracked in the immutable audit trail
- Import / Export β Agents are portable as ZIP files with automatic secret scrubbing on export. Import merges or overwrites β no version conflicts
- Agent Sync β Live instance-to-instance sync with structural matching, content diffing, and selective resource picking β no ZIP intermediary needed
- Prompt Snippets β Reusable, versioned system prompt building blocks referenced as
{{snippets.safety_rules}}β compose prompts from shared libraries - Behavior Rules β IF-THEN logic engine for routing, orchestration, and business logic decisions without code
Resource Types
EDDI manages these configuration resources: Rules (system prompts), Workflows (pipeline definitions), LLM Connectors (provider settings), HTTP Connectors (external API integrations), Agents (deployment descriptors), and Environments (deployment targets).