Knowledge and Agents

This feature is coming soon. This documentation describes the planned functionality for how Kodexa agents will interact with the Knowledge System.

Agents in Kodexa can both build and consume knowledge, creating a feedback loop where the system learns from documents and proposes configurations for human approval.

The Vision

Agents do the heavy lifting of discovering patterns and proposing configurations. Humans stay in control by reviewing and approving what goes into production.

Building Knowledge: Feature Discovery

When an agent processes documents, it may discover new entities that should be tracked as Knowledge Features.

The Flow

Example: New Vendor Discovery

Agent processes invoice from “NewTech Solutions Inc.”
Agent checks if a vendor feature with matching ID exists
No match found - agent proposes new feature:

# Agent-proposed feature (status: pending_review)
featureType: vendor
status: pending_review
proposedBy: invoice-processing-agent
confidence: 0.92

properties:
  vendorId: "NTS-2024-001"  # Extracted from invoice

extendedProperties:
  displayName: "NewTech Solutions Inc."
  address: "123 Innovation Way, Austin, TX"
  extractedFrom: "invoice-2024-03-15-001.pdf"

Human reviews the proposed feature in the Knowledge interface
Human approves (or modifies and approves)
Feature becomes active and available for linking

What Agents Extract

Agents can propose features based on:

Explicit data: Vendor names, customer IDs, document types
Inferred classifications: Language, document category, urgency
Patterns: Recurring entities across multiple documents

Consuming Knowledge: Intelligent Processing

Agents have access to all active knowledge and use it to make processing decisions.

The Flow

Example: Applying Extraction Rules

Document arrives - classified as SEC 10K filing
Agent queries Knowledge Sets matching “SEC Filing Type = 10K”
Knowledge Set returns Items:
- Use 10K-specific extraction prompt
- Apply annual report validation rules
- Route to SEC compliance queue
Agent applies these configurations during processing

Proposing Knowledge Sets

The most powerful capability: agents can propose entire Knowledge Sets by observing patterns.

The Flow

Example: Pattern Discovery

Scenario: Agent notices that invoices from Vendor X frequently have validation exceptions for missing tax IDs, and users always override with the same justification. Agent proposes:

# Agent-proposed Knowledge Set
name: Vendor X Tax ID Exception
description: |
  Vendor X (Government Agency) is tax-exempt.
  Skip tax ID validation for their invoices.

status: pending_review
proposedBy: validation-analysis-agent
confidence: 0.88

evidence:
  - 47 invoices from Vendor X in past 90 days
  - 45 had tax ID validation overridden
  - Override reason consistently: "Government agency - tax exempt"

# Conditions
features:
  - featureTypeSlug: vendor
    properties:
      vendorId: "VENDOR-X-001"

# Actions
items:
  - itemType: validation-rule
    properties:
      ruleType: skip-field
      targetField: "vendor/tax_id"
      reason: "Government agency - tax exempt"

Human reviews:

Sees the evidence (47 invoices, consistent overrides)
Verifies the business logic makes sense
Approves the Knowledge Set
System now automatically skips tax ID validation for Vendor X

The Human-in-the-Loop Principle

All agent-created knowledge requires human approval before becoming active.

Why This Matters

Aspect	Agent Role	Human Role
Pattern Detection	Analyzes thousands of documents	Reviews proposed patterns
Feature Creation	Extracts and proposes entities	Validates accuracy
Rule Discovery	Identifies correlations	Confirms business logic
Configuration	Proposes settings	Approves for production

Review Interface

The Knowledge interface shows:

Pending Features: Agent-proposed entities awaiting approval
Pending Sets: Agent-proposed rules awaiting approval
Evidence: Why the agent made the proposal
Confidence Score: Agent’s certainty level
Impact Preview: What would change if approved

Feedback Loop

Agents learn from human decisions: When humans:

Approve - Agent learns this pattern is valuable
Reject - Agent learns to avoid similar proposals
Modify - Agent learns the correct approach

Configuration

Enabling Agent Knowledge Building

# Assistant configuration
assistantDefinitionRef: kodexa/document-processing-assistant
options:
  knowledge:
    featureDiscovery: true      # Propose new features
    setProposal: true           # Propose knowledge sets
    confidenceThreshold: 0.75   # Minimum confidence to propose
    requireEvidence: true       # Must include evidence

Review Notifications

# Project configuration
notifications:
  knowledgePendingReview:
    enabled: true
    channels:
      - email
      - slack
    recipients:
      - knowledge-admins@company.com

Best Practices

1. Start with High Confidence Threshold

Begin with confidenceThreshold: 0.9 and lower as you trust the agent’s proposals.

2. Review Regularly

Don’t let pending items pile up. Regular review keeps the feedback loop active.

3. Document Rejections

When rejecting proposals, add notes so the pattern is understood:

# Rejection with feedback
status: rejected
rejectionReason: "This pattern only applies to Q4, not year-round"
rejectedBy: john.smith
rejectedAt: 2024-03-15T10:30:00Z

4. Use Staging Environment

Test agent knowledge building in staging before production:

# Development/staging only
options:
  knowledge:
    featureDiscovery: true
    setProposal: true
    autoActivate: false  # Never auto-activate, always review

Coming Soon

Batch Review: Review multiple proposals at once
Approval Workflows: Route proposals to specific reviewers
A/B Testing: Test proposed rules on subset before full activation
Confidence Trends: Track agent accuracy over time

Knowledge System Overview - Foundation concepts
Knowledge Feature Types - Define metadata categories
Knowledge Item Types - Define configurable behaviors

Introduction

Activity

Knowledge System

Organization & Projects

Resources

Modules

The Vision

Building Knowledge: Feature Discovery

The Flow

Example: New Vendor Discovery

What Agents Extract

Consuming Knowledge: Intelligent Processing

The Flow

Example: Applying Extraction Rules

Proposing Knowledge Sets

The Flow

Example: Pattern Discovery

The Human-in-the-Loop Principle

Why This Matters

Review Interface

Feedback Loop

Configuration

Enabling Agent Knowledge Building

Review Notifications

Best Practices

1. Start with High Confidence Threshold

2. Review Regularly

3. Document Rejections

4. Use Staging Environment

Coming Soon

​The Vision

​Building Knowledge: Feature Discovery

​The Flow

​Example: New Vendor Discovery

​What Agents Extract

​Consuming Knowledge: Intelligent Processing

​The Flow

​Example: Applying Extraction Rules

​Proposing Knowledge Sets

​The Flow

​Example: Pattern Discovery

​The Human-in-the-Loop Principle

​Why This Matters

​Review Interface

​Feedback Loop

​Configuration

​Enabling Agent Knowledge Building

​Review Notifications

​Best Practices

​1. Start with High Confidence Threshold

​2. Review Regularly

​3. Document Rejections

​4. Use Staging Environment

​Coming Soon

​Related Documentation

The Vision

Building Knowledge: Feature Discovery

The Flow

Example: New Vendor Discovery

What Agents Extract

Consuming Knowledge: Intelligent Processing

The Flow

Example: Applying Extraction Rules

Proposing Knowledge Sets

The Flow

Example: Pattern Discovery

The Human-in-the-Loop Principle

Why This Matters

Review Interface

Feedback Loop

Configuration

Enabling Agent Knowledge Building

Review Notifications

Best Practices

1. Start with High Confidence Threshold

2. Review Regularly

3. Document Rejections

4. Use Staging Environment

Coming Soon

Related Documentation