Veljko Kovac
Head of FDE
Veljko Kovac contributes to the Cognee blog, with articles in deep dives, integrations, tutorials. Explore their published work below.
Published topics
Deep DivesIntegrationsTutorials

Published articles (8)
Coding Agent Findings Without Coordinates Are Just Hearsay
A coding agent’s saved finding can only be checked if it records the code element it concerns, the version examined, and the evidence behind it. Why shared folders, CLAUDE.md, skills, commit hashes, and wiki pages each record only part of that, and what the missing layer needs.
Read article ↗Cognee Memory for BAND Agents
Give any BAND agent a persistent, shared knowledge graph in one line of code: install cognee-integration-band, wrap your adapter, and get auto-recall, auto-capture, and room-level consolidation.
Read article ↗Separate memories for organization, agent and user: Support AI Agent Use-Case
Most support teams don't have a support problem — they have a context problem. Here's how we built a support agent on top of cognee using user, agent, and organization memory.
Read article ↗Memory as a Decorator
Adding memory to agentic workflows used to mean restructuring your stack. One decorator changes that. We ran 198 simulated sales conversations — and the results make a strong case for structured memory.
Read article ↗Expanding Custom Graph Models for Reliable Agent Memory & Retrieval
Learn how Custom Graph Models in cognee create a stable, domain-aware memory layer for agents — and how the Cascade feature progressively discovers missing schema from real data.
Read article ↗Memory as a Harness: Turning Execution Into Learning
Memory as a Harness: Turning Execution Into Learning
Read article ↗Building Self-Improving Skills for Agents
Learn how to build self-improving skills for AI agents with Cognee. Transform static SKILL.md files into evolving components that learn from failure. Try it now.
Read article ↗Structure Your Skills with Cognee
Turn AI agent skills into a knowledge graph with Cognee. Route tasks by meaning, learn from feedback, and improve over time. Start building smarter agents now.
Read article ↗