Agno CEO on self-improving agent infrastructure: agents trained on their own traces
pritisinghhhh · x · 2026-10-26
Agno founder & CEO Ashpreet Bedi outlines how companies can build shared agent platforms that improve themselves. Every team will run agents needing the same foundation—runtime, knowledge access, persistent state, sandboxes, permissions, and audit trails. Consolidating traces of what users asked, what context agents used, and which tools they called turns observability into an improvement engine: hand the trace and source code to a coding agent to generate better instructions, fix tools, or update knowledge, then track long-term that changes actually help—closing a run→learn→improve loop.
More from coding & agent
- 5-layer agent memory setup: Mem0 cuts tokens 93%, Snowflake ontology lifts accuracy 20% — Arindam_1729 · 2026-10-26
- Skills written entirely by the model are useless, and stacking skills taxes agent context — HamelHusain · 2026-10-26
- Grok Bot hands-on: auto-logs hundreds of tasks to Linear and runs scheduled security checks — koltregaskes · 2026-10-26
- agent-saifu: an MCP server that gives AI agents their own isolated DeFi wallets — DecisiveCS · 2026-10-26
- GigaMail ships three MCP security patches against indirect prompt injection leaks — Soft-Lie-434 · 2026-10-26
- Hermes Agent Lands Web Desktop UI, Enabled with a Single Command Locally — intellectronica · 2026-10-26