Olki ditches LLM-based agent monitoring for strict type systems and effects algebra
bigdata · x · 2026-11-05
On The Data Exchange podcast, Modiqo founder Chetan Conikee explains why he built Olki to track agent behavior without using another LLM. Most observability tools rely on language models to interpret agent logs, adding their own uncertainty, latency, and inference costs. Olki instead applies strict type systems and effects algebra to deterministically classify individual agent operations. The interview covers breaking complex commands into discrete operations, cost attribution and agent-effectiveness metrics, detecting risky actions and log tampering, the case for local-first monitoring for privacy and enterprise oversight, and early user feedback on optimizing context compaction and token consumption.
More from coding & agent
- Box taps Nvidia's Nemotron: 4x faster queries, 90% fewer tokens for agents — gaganghotra_ · 2026-11-05
- Codex forgets the task entirely after context compaction, dev reports a first — Angaisb_ · 2026-11-05
- Vercel's agent-desktop reads accessibility trees to automate desktop apps, 16.4k stars — victor_explore · 2026-11-05
- IOTA Decide 4B open-weight decision model hits ~11 decisions/sec on a Mac mini — const_reborn · 2026-11-05
- AI agent audits mom's APOE E3/E4 genetic report, with a second AI trying to break the work — kevrussell · 2026-11-05
- Public benchmarks won't tell you which AI model works for your stack, Microsoft advocate warns — HamelHusain · 2026-11-05