DEV Community

Loop & Retry — agent reliability Series' Articles

Back to Walker Miller's Series
The cost of undoing: partial failures and the cleanup bill
loopandretry profile

The cost of undoing: partial failures and the cleanup bill

#failuremodes #cost #rollback #partialsuccess
Comments
8 min read
Your timeout is a bet: pricing the tradeoff before you pick a number
loopandretry profile

Your timeout is a bet: pricing the tradeoff before you pick a number

#cost #failuremodes #reliability #operations
Comments
6 min read
Tool output is untrusted input: prompt injection is a data-flow bug
loopandretry profile

Tool output is untrusted input: prompt injection is a data-flow bug

#tooldesign #security #promptinjection #agents
Comments 1
6 min read
The agent that trusted a bad API: silent failures and validation debt
loopandretry profile

The agent that trusted a bad API: silent failures and validation debt

#failuremodes #validation #cost #tooloutput
Comments
9 min read
The transcript is a log, not an index: retrieval for long-running agents
loopandretry profile

The transcript is a log, not an index: retrieval for long-running agents

#cost #tokens #contextengineering #longhorizon
Comments
6 min read
What an MCP server actually is, and the tool-design mistakes that break it
loopandretry profile

What an MCP server actually is, and the tool-design mistakes that break it

#mcp #modelcontextprotocol #tooldesign #claudecode
1
Comments 1
9 min read
What actually drives your Claude bill: cache misses, quadratic context, and prepaid retries
loopandretry profile

What actually drives your Claude bill: cache misses, quadratic context, and prepaid retries

#cost #tokens #claude #promptcaching
Comments
7 min read
What to actually measure when your agent "works"
loopandretry profile

What to actually measure when your agent "works"

#evals #testing #metrics #llmasjudge
Comments
9 min read
When not to build an agent
loopandretry profile

When not to build an agent

#agentarchitectures #workflows #cost #latency
Comments
8 min read
When a pipeline beats an agent: three shapes that don't need a loop
loopandretry profile

When a pipeline beats an agent: three shapes that don't need a loop

#agentarchitectures #workflows #design #reliability
Comments
5 min read
Your agent's p99 is a different animal
loopandretry profile

Your agent's p99 is a different animal

#latency #performance #reliability #tail
Comments 1
6 min read
Why this blog exists
loopandretry profile

Why this blog exists

#meta #ai #llm #agents
Comments
2 min read
What Idempotent Actually Means: Why Retries Are Safe (and When They Aren't)
loopandretry profile

What Idempotent Actually Means: Why Retries Are Safe (and When They Aren't)

#idempotency #api #agents #reliability
5
Comments 2
8 min read
How indirect prompt injection actually happens
loopandretry profile

How indirect prompt injection actually happens

#promptinjection #security #trustboundary #agents
Comments 3
7 min read
Context engineering: what fits and what gets dropped
loopandretry profile

Context engineering: what fits and what gets dropped

#contextengineering #contextwindow #memory #compaction
Comments
9 min read
Split-brain: when multi-agent memory consensus quietly fails
loopandretry profile

Split-brain: when multi-agent memory consensus quietly fails

#multiagent #failuremodes #memory #distributedsystems
Comments
7 min read
Goal drift: how a multi-agent crew ends up solving a different problem
loopandretry profile

Goal drift: how a multi-agent crew ends up solving a different problem

#multiagent #failuremodes #goaldrift #agentarchitectures
Comments
7 min read