Running an AI Agent Fleet Series' Articles

John

Jul 13

Why I Rejected an Event Bus for My Solo Agent Fleet: State Is Truth, Events Are Rumors

#agents #architecture #mcp #systemdesign

7

7 min read

John

Jul 13

Stop Hooks as Hard Constraints: Enforcing Claude Code Behavior Outside the Model

#agents #ai #claude #llm

6

6 min read

John

Jul 14

No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions

#agents #ai #llm #testing

1

2

4 min read

John

Jul 14

Stop AI Agent Drift Across Sessions With Versioned, Grep-able Rules

#agents #ai #llm #productivity

2

5 min read

John

Jul 15

Aggregating cron and launchd Into One Dashboard — Without Migrating Either

#automation #devops #monitoring #productivity

6 min read

John

Jul 16

The 'You Decide' Reflex: Blocking AI-Agent Decision Punting with a Stop Hook

#agents #ai #llm #productivity

38

8 min read

John

Jul 17

Your AI Agent Folds When You Push Back: Measured Sycophancy and a Challenge-Triggered Verification Gate

#agents #ai #architecture #llm

25

8 min read

John

Jul 18

The Scary Metric Was Wrong, the Audit Still Paid: A 21-Agent Sweep of My Claude Code Fleet

#agents #ai #automation #claude

7 min read

John

Jul 18

Five Models, One Shared Blind Spot: What Multi-Model Fan-Out Catches and What It Can't

#agents #ai #llm #testing

2

6 min read

John

Jul 19

Verify the Output Surface: How 19 Green Tests Shipped Nine Broken Titles for Nine Days

#automation #cicd #devops #testing

8 min read

John

Jul 19

Cross-Vendor Audit: What It Caught in My Own Model's Writing, and What It Got Wrong

#ai #llm #productivity #writing

6 min read

John

Jul 21

Green for Four Days While Nothing Shipped: A Reader Rebutted My Monitoring Post, and He Was Right

#devops #monitoring #python #systemdesign

2

8 min read

John

Jul 21

I Asked Three Judges If I Was Wrong. One JSON Field Decided the Answer.

6 min read

John

Jul 22

Your Agent Telemetry Ranks Your Routing Policy, Not Your Models

#agents #ai #analytics #llm

1

4

6 min read

John

Jul 23

My AI Subagent Faked the Verification Output I Asked It to Attach

#agents #ai #claude #softwaredevelopment

2

14

6 min read

John

Jul 25

Deterministic Tool Adoption Gates: Score It, Don't Vibe It

#agents #ai #cli #github

2

7 min read

John

Jul 26

Rotating the Hostile Seat: A Six-Round Adversarial Design Review Before Hardening an Agent

#agents #architecture #security #softwareengineering

7 min read

Commenters expose a flaw in the gate logic

John

Jul 28

My Verification Gate Cleared on a Keyword, Not Evidence

#agents #ai #architecture #llm

11

30

6 min read

John

Jul 29

A Forced Dissent Slot Has a Floor: Read It by Convergence, Not Presence

#ai #llm #machinelearning

2

6 min read

John

Jul 30

Four Models Cited My Numbers Perfectly. One Still Misread Them.

#ai #analytics #data #llm

6 min read

John

Jul 31

Our Quality Gate Was 24x Noisier Than What It Guarded

#data #machinelearning #testing

5

2

8 min read

Reveals dispatchers confound agent benchmarks

John

Aug 2

Sub-Agent Metrics Are Not Comparable to Main-Thread Metrics

#agents #ai #llm #machinelearning

9

44

11 min read

John

Aug 4

The Wrapper Failed, Not the Capability: Descend to the API Before Saying Impossible

#api #backend #softwareengineering

1

10 min read

John

Aug 7

The Quota Said 100% Used. Actual Demand Was 13%.

#api #data #performance #python

2

7

9 min read

John

Aug 8

Perfect Instrumentation Won't Save an Underpowered Experiment

#analytics #science #testing

1

6

8 min read

Replaying transcripts reveals a 64% filter rate

John

Aug 8

The Gate Only Logged When It Fired. I Replayed 116,022 Candidate Stop Points to Find the Rest.

#agents #automation #llm #programming

1

19

8 min read

John

Aug 9

Our Status Column Said 30 Waiting. Six Were.

#debugging #monitoring #software

7 min read

John

Aug 9

Two of Five Gates Replayed Clean. The Other Three Read a Ledger With No History.

#agents #automation #software #softwareengineering

1

8 min read

John

Aug 12

The Guardrail Pointed at a File That Never Existed

#agents #ai #coding #llm

4

6 min read

John

Aug 12

An Empty Prompt Is Not a Blind Review

#agents #ai #llm #testing

1

5 min read

John

Aug 13

One Leg Can Raise an Objection. It Can't Settle One.

#agents #ai #automation #llm

10

6 min read

John

Aug 13

Route the Claim to Its Verifier - Legs Are Not Votes

#agents #ai #llm

7 min read

John

Aug 14

The Bug Was in the Brief, Upstream of Both Reviews

#agents #ai #llm #writing

1

2

7 min read

John

Aug 14

The Key's Owner Wasn't the Spender

2

6 min read

John

Aug 15

The Fix Was Committed. The Old Value Kept Running.

#cli #debugging #softwareengineering

5 min read

John

Aug 15

The Gate Pinned a Model That No Longer Exists

1

5 min read

John

Aug 16

Deprecation Doesn't Reach the Copies

#architecture #documentation #productivity

6 min read

John

Aug 16

The Rule That Triggered on Its Own Advice

6 min read

John

Aug 18

Exit 0, Empty stdout: the Quota Died on stderr

#automation #cli #debugging

4 min read

John

Aug 19

Your Report's Numbers Are Computed. Its Sentences Are Not.

#code #python #software #softwareengineering

6 min read

John

Aug 19

The Ablation Had Four Arms. None Matched What Shipped.

#debugging #software #softwareengineering

11 min read

John

Aug 20

The Count Read in the Thousands. It Was Thirty-Seven Things, Recounted.

#agents #ai #automation #softwareengineering

1

11 min read

John

Aug 21

Why My Correct Config Value Was Being Ignored

#debugging #mcp #programming

2

8

5 min read

John

Aug 22

The Proxy I Added to Measure Tokens Tripled Them

#agents #ai #llm #tooling

3

8 min read

John

Aug 22

Same Bytes, 20% Fewer Tokens: Token Counts Are Model-Scoped

#agents #ai #api #llm

4

6 min read