← Back to Home
Blog
Technical deep dives, architecture decisions, and lessons learned building Comis.
Engineering April 11, 2026 12 min read
How I Cut Our Multi-Agent Pipeline Cost by 64% with Cache Forensics
The story of debugging Anthropic's prompt cache behavior in production, discovering three root causes, building a cache fence system, and uncovering a TTL monotonicity violation - ultimately achieving 81% cost reduction.
Moshe Anconina
Security April 10, 2026 14 min read
Why AI Agent Security Is Hard (And What We Built to Solve It)
Most AI frameworks bolt security on after launch. Comis was designed around a different question: what happens when an AI agent has real power and someone tries to abuse it? 22 defense layers later, here's what I learned.
Moshe Anconina
Engineering April 9, 2026 15 min read
Anatomy of a Context Engine: 8 Layers That Keep AI Agents Affordable
How Comis processes every conversation through an 8-layer pipeline that strips thinking traces, evicts dead content, masks old observations, and compresses entire conversations - keeping costs predictable at any scale.
Moshe Anconina