# AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTok

Source: [AI Engineer](https://www.youtube.com/watch?v=hD9-V56FNRI)  
Feed7 permalink: https://feed7.dev/p/ai-agents-are-just-distributed-systems-now-salman-munaf--105166eadd  
Published: 2026-08-29T00:00:00.000Z  
Trust: Source Linked (source_linked)

## Why Included

Make mutating tools idempotent, persist each step, bound retries and spend, and treat timeouts as unknown outcomes.

## Source Summary

Once agents mutate external state, timeouts mean unknown outcomes. Builders need idempotent tools, bounded retries, scoped credentials, durable traces, and explicit recovery paths.

## Practical Implication

Design every agent tool like a distributed-system boundary. Persist each step, define the source of truth, treat memory as an invalidatable cache, and bind approvals to the exact action, actor, timestamp, parameters, and expiration.

## Agent-Ready Context

A tool timeout does not prove failure: the remote side may already have committed the action. The talk recommends request IDs, **idempotency keys**, status lookups, circuit breakers, compensation operations, and limits on turns, spend, and parallel calls.

Design every agent tool like a distributed-system boundary. Persist each step, define the source of truth, treat memory as an invalidatable cache, and bind approvals to the exact action, actor, timestamp, parameters, and expiration.

A stronger model can reduce reasoning mistakes but cannot remove network ambiguity, stale state, or adversarial input. Some irreversible actions cannot be truly undone, so compensation and human approval remain domain-specific safeguards.

## Context Map

- Layer: agent
- Domains: coding
- Topics: harness-engineering, tool-use, agent-reliability

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.