Site Search

Search across every article.

Full-text search over titles, headings, and body prose. Filter by series or depth.

Series
Depth
100articles indexed
  1. 01
    AI Evals·L1

    Benchmarks ≠ Evals

    IN THIS NOTE YOU WILL LEARN 01. Why a model that tops every leaderboard can still catastrophically fail your users in production. 02. The precise architectural difference between t

    Read article
  2. 02
    AI Evals·L1

    Non-Determinism

    IN THIS NOTE YOU WILL LEARN 01. Why the same prompt can produce different outputs on different runs — and why setting temperature to zero doesn't fix it. 02. Why "task completed" i

    Read article
  3. 03
    AI Evals·L1

    The Quality Owner

    IN THIS NOTE YOU WILL LEARN 01. Why defining "good enough" for AI is a product decision that regulations now require someone to own. 02. Why the PM is the natural fit for quality o

    Read article
  4. 04
    AI Evals·L1

    Failure Anatomy

    A doctor doesn't treat each cough separately. They diagnose the infection. The coughs stop on their own. Here's what makes this practice more than quality assurance: it's product d

    Read article
  5. 05
    AI Evals·L1

    Golden Datasets

    A driving test with only straight roads teaches nothing about parallel parking, night driving, or highway merges. The ratio that separates honest evals from flattering ones is 60/2

    Read article
  6. 06
    AI Evals·L1

    The Three Gulfs

    IN THIS NOTE YOU WILL LEARN 01. The three root causes behind every AI product failure — and why most teams misdiagnose which one they're facing. 02. Why the fix for each gulf is co

    Read article
  7. 07
    AI Evals·L1

    Two Axes of Checking

    Traces & Observability What a trace actually is, why "telemetry" is three different capabilities vendors market under one word, and how the provider landscape actually works.

    Read article
  8. 08
    AI Evals·L1

    Traces & Observability

    The Tool Landscape The four categories of eval tooling, how to avoid the three procurement traps, and why PMs — not engineers — should lead tool procurement.

    Read article
  9. 09
    AI Evals·L1

    The Tool Landscape

    Your First Eval Suite The three components every eval reduces to, how to build a working system in one week, and why starting small beats designing the comprehensive system.

    Read article
  10. 10
    AI Evals·L1

    Your First Eval Suite

    IN THIS NOTE YOU WILL LEARN 01. The three components every eval reduces to — data, task, scores — and why that simplicity is the point. 02. How to build a working eval system in on

    Read article
  11. 11
    AI Evals·L2

    Machine Rubrics

    IN THIS NOTE YOU WILL LEARN 01. Why "was it good?" is the wrong evaluation question -- and what to replace it with. 02. The rubric structure that separates shipping decisions from

    Read article
  12. 12
    AI Evals·L2

    Judging the Judge

    Smarter Judges Why most judge improvements come from changing the structure of the judging problem -- not from better wording. Five techniques that consistently move the needle.

    Read article
  13. 13
    AI Evals·L2

    Smarter Judges

    The RAG Triad The three independent metrics that decompose RAG quality -- context relevance, faithfulness, and answer relevance -- and why keeping them separate is the entire point

    Read article
  14. 14
    AI Evals·L2

    The RAG Triad

    Conversation Evals Why per-turn quality does not sum to session quality -- and the four metrics that capture what single-turn evaluation misses.

    Read article
  15. 15
    AI Evals·L2

    Conversation Evals

    IN THIS NOTE YOU WILL LEARN 01. Why per-turn quality does not sum to session quality — a bot can ace every individual response and still fail the conversation. 02. The four metrics

    Read article
  16. 16
    AI Evals·L2

    Evaluating Agents

    IN THIS NOTE YOU WILL LEARN 01. Why standard outcome evaluation breaks for agents -- and the math that makes this concrete. 02. What trajectory evaluation is, how it differs from p

    Read article
  17. 17
    AI Evals·L2

    Using Traces to Debug What Went Wrong

    Evals in CI/CD Why the same release gate that catches broken code should also catch AI behavior regressions -- and how to build it.

    Read article
  18. 18
    AI Evals·L2

    Shipping Safely

    Production Monitoring Why CI/CD eval gates and production monitoring are different tools solving different problems -- and why confusing them leaves you blind.

    Read article
  19. 19
    AI Evals·L2

    Production Monitoring

    IN THIS NOTE YOU WILL LEARN 01. Why CI/CD eval gates and production monitoring are different tools solving different problems — and why confusing them leaves you blind. 02. The thr

    Read article
  20. 20
    AI Evals·L2

    Human Review

    IN THIS NOTE YOU WILL LEARN 01. Why human review is not a fallback for when automation fails -- it is a precision system for cases automation was never meant to resolve. 02. The di

    Read article
  21. 21
    AI Evals·L3

    Deep Rubrics

    IN THIS NOTE YOU WILL LEARN 01. Why pass/fail evaluation hides the real quality story -- and when multi-dimensional rubrics become non-negotiable. 02. How production eval tools (La

    Read article
  22. 22
    AI Evals·L3

    Failure Analysis

    IN THIS NOTE YOU WILL LEARN 01. Why treating every failed trace as a unique bug is the most expensive debugging strategy -- and how failure mode genealogy reduces hundreds of incid

    Read article
  23. 23
    AI Evals·L3

    A/B Testing for AI

    IN THIS NOTE YOU WILL LEARN 01. Why offline eval wins don't always translate to production wins -- and what causes the gap between "scored better on the dataset" and "actually impr

    Read article
  24. 24
    AI Evals·L3

    The Eval Flywheel

    IN THIS NOTE YOU WILL LEARN 01. Why static eval suites decay over time, and why a 98% pass rate can be the most dangerous number on your dashboard. 02. How the production-to-annota

    Read article
  25. 25
    AI Evals·L3

    Progressive Deployment

    IN THIS NOTE YOU WILL LEARN 01. Why strong eval results are necessary but insufficient for deploying agents — and what fills the gap between “benchmarks pass” and “safe in producti

    Read article
  26. 26
    AI Evals·L3

    Eval Economics

    In This Note You Will Learn 01. Why cost per API call is the wrong metric -- and why cost per successful task changes every decision about model selection, judge design, and human

    Read article
  27. 27
    AI Evals·L3

    Build vs. Buy

    Red Teaming Why conventional quality evals miss the most dangerous failures, and how adversarial testing has matured into continuous CI/CD and production monitoring.

    Read article
  28. 28
    AI Evals·L3

    Red Teaming

    IN THIS NOTE YOU WILL LEARN 01. Why a system that scores 95% on correctness can still be trivially exploited through its tools, context window, or retrieval pipeline -- and why con

    Read article
  29. 29
    AI Evals·L3

    Evals Are the New PRD

    IN THIS NOTE YOU WILL LEARN 01. Why evaluation systems — not product requirement documents — now carry the operational definition of “success” in AI products, and what happens to t

    Read article
  30. 30
    AI Evals·L3

    The Limits of Evaluation

    In This Note You Will Learn 01. Why a passing eval suite is evidence, not proof -- and the five specific technical limits that make every evaluation system an incomplete proxy for

    Read article
  31. 31
    AI Evals·L4

    When AI Knows It's Being Tested

    In This Note You Will Learn 01. Why evaluation awareness -- a model recognizing it's being examined and responding strategically -- is a qualitatively different problem from benchm

    Read article
  32. 32
    AI Evals·L4

    Zero-Human Evaluation Loops

    In This Note You Will Learn 01. Why zero-human evaluation loops don't eliminate human judgment -- they move it upstream into specifications, validation harnesses, and policy packag

    Read article
  33. 33
    AI Evals·L4

    Evaluating AI in the Physical World

    In This Note You Will Learn 01. Why computer-use agents -- systems that perceive screenshots, click buttons, navigate apps, and take irreversible actions -- require a fundamentally

    Read article
  34. 34
    AI Evals·L4

    When the Student Outperforms the Teacher

    In This Note You Will Learn 01. Why every evaluation framework in this series rests on an assumption that is already breaking -- that a human or weaker model acting as judge can re

    Read article
  35. 35
    AI Evals·L4

    MCP & Tool Ecosystem Evaluation

    In This Note You Will Learn 01. Why "did the model call a tool?" is a dangerously shallow evaluation question -- and how MCP turns tool use into a five-layer evaluation problem: se

    Read article
  36. 36
    AI Evals·L4

    Production-Grade Trace Scoring

    In This Note You Will Learn 01. Why a dashboard glowing at 0.93 across faithfulness, coherence and helpfulness can still ship a product nobody uses — and why polishing those number

    Read article
  37. 37
    Agentic Stack·L1

    Prompt ≠ Context

    A prompt is what you type. Context is everything the model sees.

    Read article
  38. 38
    Agentic Stack·L1

    The Context Window

    Attention degrades before the window fills.

    Read article
  39. 39
    Agentic Stack·L1

    The CONTEXT Stack

    Seven layers. Miss one, and the model compensates badly.

    Read article
  40. 40
    Agentic Stack·L1

    Context Rot

    More tokens doesn

    Read article
  41. 41
    Agentic Stack·L1

    The Constitution

    Your system prompt IS your product definition.

    Read article
  42. 42
    Agentic Stack·L1

    Knowledge at Inference

    RAG is a context supply chain, not a feature.

    Read article
  43. 43
    Agentic Stack·L1

    Memory Architecture

    The model doesn

    Read article
  44. 44
    Agentic Stack·L1

    Tools Shape Behavior

    Tool descriptions change reasoning before any call.

    Read article
  45. 45
    Agentic Stack·L1

    Structure as Control

    Constrain the output space, reliability goes up.

    Read article
  46. 46
    Agentic Stack·L1

    Your First Context Pipeline

    From scattered prompts to an engineered system.

    Read article
  47. 47
    Agentic Stack·L2

    What Is a Harness?

    The 90% of your AI product that isn

    Read article
  48. 48
    Agentic Stack·L2

    Context Assembly

    The pipeline that runs before every inference call.

    Read article
  49. 49
    Agentic Stack·L2

    The 3C Lifecycle

    Create it, compress it, cache it.

    Read article
  50. 50
    Agentic Stack·L2

    Multi-Turn State

    What to keep, what to summarize, what to drop.

    Read article
  51. 51
    Agentic Stack·L2

    The Harness Decision

    Start with the simplest harness that could work.

    Read article
  52. 52
    Agentic Stack·L2

    Context Observability

    If you can

    Read article
  53. 53
    Agentic Stack·L2

    Context Economics

    Every token has a price. Budget accordingly.

    Read article
  54. 54
    Agentic Stack·L2

    Graceful Degradation

    When context fails, the system shouldn

    Read article
  55. 55
    Agentic Stack·L2

    Evaluating the Harness

    Test the system, not just the model.

    Read article
  56. 56
    Agentic Stack·L2

    The Harness-Eval Contract

    If your evals can

    Read article
  57. 57
    Agentic Stack·L3

    The Agentic Shift

    The model decides what happens next.

    Read article
  58. 58
    Agentic Stack·L3

    The Spectrum of Agency

    Not maximum autonomy. Optimal autonomy.

    Read article
  59. 59
    Agentic Stack·L3

    Agent Anatomy

    Five components. Most agents only need three.

    Read article
  60. 60
    Agentic Stack·L3

    Architecture Patterns

    The right pattern depends on your constraints.

    Read article
  61. 61
    Agentic Stack·L3

    The Autonomy Design

    Back to Agentic Stack In This Note You Will Learn 01. Why autonomy is a per-capability decision, not a per-agent decision -- and the five levels that structure that choice from sug

    Read article
  62. 62
    Agentic Stack·L3

    Multi-Agent Coordination

    Every handoff loses 37% of context.

    Read article
  63. 63
    Agentic Stack·L3

    Agent Reliability

    90% per step x 10 steps = 35% end-to-end.

    Read article
  64. 64
    Agentic Stack·L3

    Agent Governance

    What the agent can do, must do, must never do.

    Read article
  65. 65
    Agentic Stack·L3

    Agent Economics

    Single agent: $9. Full harness: $200.

    Read article
  66. 66
    Agentic Stack·L3

    The Living System

    Models change. Your architecture must survive it.

    Read article
  67. 67
    Agentic Stack·L4

    The Protocol Layer

    MCP + A2A: how agents will talk to the world.

    Read article
  68. 68
    Agentic Stack·L4

    Agent-Native Products

    Design for agents as users.

    Read article
  69. 69
    Agentic Stack·L4

    Self-Improving Context

    When agents optimize their own context.

    Read article
  70. 70
    Agentic Stack·L4

    The Trust Architecture

    Safety at industrial scale.

    Read article
  71. 71
    Agentic Stack·L4

    The Model-Harness Boundary

    What shifts when models get smarter.

    Read article
  72. 72
    Harness Engineering·L1

    Why Your Agent Fails · Harness Engineering 01

    Episode 01 of Harness Engineering: the model spoke last, but the failure rarely began there. Four layers, four verbs, six failure shapes, and the incident questions that lead to an owner.

    Read article
  73. 73
    Harness Engineering·L1

    Inside a Production Agent Harness · Harness Engineering 02

    Episode 02 of Harness Engineering: three views of one machine — four responsibilities, five decisions inside the control plane, and the session, harness, and sandbox runtime underneath.

    Read article
  74. 74
    Harness Engineering·L1

    Three Small Changes, Dramatic Outcomes Harness Engineering 03 Ravi Teja Palanki

    Episode 03 of Harness Engineering: four changes that improve reliability without replacing the model — retry with evidence, a versioned output shape, a narrowed tool surface, and an external completion check.

    Read article
  75. 75
    Harness Engineering·L1

    Five Paradoxes Every PM Must Hold Harness Engineering 04 Ravi Teja Palanki

    Episode 04 of Harness Engineering: five tensions every PM must hold — intelligence and reliability, constraints and autonomy, scaffolding and permanence, specificity and generality, demo and production — and the decision card that makes each one testable.

    Read article
  76. 76
    Harness Engineering·L1

    What It Costs, What It Returns Harness Engineering 05 Ravi Teja Palanki

    Episode 05 of Harness Engineering: why cheaper model calls can raise the bill, the five cost centers the token invoice hides, the runtime line, the reliability dividend, and a six-line monthly value review that ends in expand, hold, or narrow.

    Read article
  77. 77
    Harness Engineering·L1

    Your Monday Morning Harness Kit Harness Engineering 06 Ravi Teja Palanki

    Episode 06 of Harness Engineering: a nine-day diagnostic and a twelve-week runway — map the system you already have, read fifty sessions, audit tools and evals, place your team on the maturity ladder, and file four owned tickets.

    Read article
  78. 78
    Harness Engineering·L1

    Organizations That Rebuilt Around Agents Harness Engineering 07 Ravi Teja Palanki

    Episode 07 of Harness Engineering: three layers already have owners and the harness does not — an ownership map, three internal operating models, the Harness PM decision rights, and human review run as a service.

    Read article
  79. 79
    Harness Engineering·L1

    When the Harness Becomes the Habit · Harness Engineering 08

    Harness Engineering finale: capabilities move, product obligations remain. Turn traces into evals, changes, releases, and measured retirement.

    Read article
  80. 80
    Environment Engineering

    Begin With Consequence · Environment Engineering 01

    Episode 01 of Environment Engineering: design starts with acceptable consequence, not with a sandbox. Reach, authority, persistence and recoverability, graded into a Consequence Envelope an AI PM can sign.

    Read article
  81. 81
    Environment Engineering

    Construct the Task World · Environment Engineering 02

    Episode 02 of Environment Engineering: what must be true before the agent begins. Runtime, inputs, connectivity, lifecycle — plus validation and run attestation, in one Environment Manifest.

    Read article
  82. 82
    Environment Engineering

    Give the Agent an Identity · Environment Engineering 03

    Episode 03 of Environment Engineering: who is acting, on whose authority, and for how long. Principals, authority models, just-in-time grants, evidence chains, and the Authority Matrix.

    Read article
  83. 83
    Environment Engineering

    Contain the Compromise · Environment Engineering 04

    Episode 04 of Environment Engineering: what the system still guarantees when the agent cannot be trusted. Compromise tests, trust zones, parameter provenance, egress bounds, fleet limits, and the Containment Model.

    Read article
  84. 84
    Environment Engineering

    Prove the Environment Is Working · Environment Engineering 05

    Episode 05 of Environment Engineering: how an AI PM defines what the evidence must prove. Three claims of health, quiet failures, drift versus harm, trajectory invariants, evidence classes, quality budgets, and the Environment Operating Contract.

    Read article
  85. 85
    Environment Engineering

    Decide What Runs Without You · Environment Engineering 06

    Episode 06 of Environment Engineering: which human gate the evidence has earned the right to remove, and what puts it back. Work classes, autonomy rungs, reversibility, promotion evidence, demotion triggers, and the Autonomy Ladder.

    Read article
  86. 86
    Environment Engineering

    Build Safe Realism · Environment Engineering 07

    Episode 07 of Environment Engineering: how real a test environment must be, and what that realism costs. Fidelity versus exposure, reachability classes, data fidelity, shadow, replay, simulation, game days, and the Fidelity Plan.

    Read article
  87. 87
    Environment Engineering

    Make the Environment a Product · Environment Engineering 08

    Episode 08 of Environment Engineering: who owns the assembled system, what standard decides whether it ships, and what one durable outcome costs. Control joins, paved roads, exception budgets, vendor questions, and the Readiness Gate.

    Read article
  88. 88
    Environment Engineering

    The World Around the Agent

    Prologue to Environment Engineering: why production AI teams must design not only the agent, but the world it acts inside — reach, authority, persistence, recoverability.

    Read article
  89. 89
    AI PM OS·Bonus

    BONUS — The AI PM Career Path: Junior, Senior, Director

    The deliberate AI PM career architecture across three levels — Junior, Senior, Director — with 2026 compensation benchmarks, the five Bridger competencies mapped at each stage, and the earned criteria that move you up.

    Read article
  90. 90
    AI PM OS·Bonus

    BONUS — The Bridger Archetype Operationalized

    The integrative AI PM as a unified operating system. Five competencies operating together across three role contexts — solo-PM, trio-lead, portfolio-director. The most under-priced PM role in 2026.

    Read article
  91. 91
    AI PM OS·Bonus

    BONUS — The Dinner-Table / Boardroom Translator

    Five questions you would ask about any new hire — memory, trust, growth, economics, risk — translated into the five metrics that decide whether your AI agent works. The language layer for any room.

    Read article
  92. 92
    AI PM OS·Bonus

    BONUS — The Indian-Market AI PM Perspective

    Where the global AI PM playbook needs adaptation for India. Pricing, GTM, DPDP, talent, and the domestic market that compounds — the operating model translated into Indian conditions.

    Read article
  93. 93
    AI PM OS·Bonus

    BONUS — Salesforce Agentforce: Certified-Practitioner Deep Dive

    A certified-practitioner deep dive on Salesforce Agentforce — how Flex Credits actually work, the real adoption picture, the Data Cloud mirror, the by-segment verdict, and the Headless 360 pivot.

    Read article
  94. 94
    AI PM OS·Bonus

    BONUS — The Agent-as-Buyer Commerce Model

    When the buyer is an AI agent: programmatic discovery, sandboxed evaluation, API-priced negotiation, and MCP-grade integration. The four-step playbook for selling into agent procurement.

    Read article
  95. 95
    AI PM OS·Bonus

    BONUS — Agentforce vs Copilot: Strategic Comparison

    The platform-choice reference for AI PMs and CPOs deciding where to bet. Hidden patterns, scale-specific verdicts, and the audit framework that determines whether your enterprise needs Agentforce, Copilot, or both with deliberate boundaries.

    Read article
  96. 96
    AI PM OS·Bonus

    BONUS — The Future of AI PM as Agent Share Climbs

    The 2028 forecast and series conclusion: agent share past 60%, pricing converged, AAR + Trust Boundary as standard board metrics, Living Software as default. The compounding advantage of internalizing AI PM OS now.

    Read article
  97. 97
    AI PM OS·Bonus

    BONUS — How the 5% Actually Operate

    The operational manual the AI PM OS series argues for but never writes. The rhythms, documents, conversations, pre-mortems, habits, rules, and personal metrics that separate compounding AI products from successful pilots.

    Read article
  98. 98
    AI PM OS·L1

    Why AI PM ≠ SaaS PM

    Three SaaS assumptions that AI breaks, the harness mastery muscle that replaces them, and the litmus question that separates 0.1% AI PM teams from average ones.

    Read article
  99. 99
    AI PM OS·L1

    Why Most AI Products Fail

    The FTE Fallacy, the Margin Death Spiral, and Measurement Theater — the three traps that kill 95% of AI initiatives, and the diagnostic that catches them in a portfolio review.

    Read article
  100. 100
    AI PM OS·L1

    The Agentic PMF Standard

    The Indispensability Index, the 7 Fits adapted for AI, and the Agent Tax anti-pattern: a new PMF standard built for products users delegate to, not just use.

    Read article