CURRENT | Nora Kaplan

Nora Kaplan

CURRENT

A journal for living in the agentic age

Practitioner's Corner

Writer Header

Recent Activity

June — Issue #34

The Web Wasn't Built for This

Builder Profile

The Web Wasn't Built for This

Magnus Müller's design choices in Browser Use reveal what happens when machines confront a web built for human spatial intuition.

The Expertise That Was Already There

The Expertise That Was Already There

The Conditions for Meaning

Individual Shift / Organizational Conditions

The Conditions for Meaning

Meaningful AI-augmented work depends on specific design choices most organizations are making by accident, with compounding consequences.

The Taste You Didn't Earn

Individual Shift / Organizational Conditions

The Taste You Didn't Earn

Reviewing AI outputs builds real pattern recognition, but it may be a different thing than the domain expertise it resembles.

Nora Kaplan

Nora Kaplan is a technology writer and advisor focused on human-AI collaboration and organizational transformation. After studying human-computer interaction and working in product design at a high-growth collaboration platform, she witnessed firsthand how teams adopt new ways of working and what makes software trustworthy at scale. Now she helps companies think through how automation changes team structure, decision-making, and the nature of knowledge work—writing with optimism about technology's potential while remaining realistic about adoption challenges.

What Smoothness Costs

The Texture Problem

What Smoothness Costs

Organizations automating knowledge work are stripping out the friction where judgment forms, and most don't realize it until the expertise is gone.

What Governance Governs

What Governance Governs

Governance infrastructure accelerates deployment by making it organizationally legible, but legibility and behavioral quality assurance are structurally different problems.

June — Issue #33

The Test Suite Was the Hero

Verification at Scale

The Test Suite Was the Hero

Parallel agent orchestration scales systematic misinterpretation alongside throughput, and most enterprise domains lack the deterministic verification that made the Bun port trustworthy.

The Number You Didn't Ask About

Reliability Lens

The Number You Didn't Ask About

How the gap between pass@k and pass^k quietly distorts every agent benchmark, procurement decision, and deployment plan built on headline numbers.

Monitoring the Monitors

Lessons and Designs

Monitoring the Monitors

What would an early warning system for degrading human oversight actually look like, and why is it so hard to build?

What Aviation Built After It Noticed the Problem

Lessons and Designs

What Aviation Built After It Noticed the Problem

Aviation built concrete measurement infrastructure before its automation countermeasures. Enterprise AI skipped that step entirely.

The Core Problem

Smooth AI assistance decouples confidence from accuracy at the individual level, then compounds into organizational blind spots that existing oversight cannot detect.

June — Issue #32

What the Six Percent Are Doing Differently

Two Consequences

What the Six Percent Are Doing Differently

The few organizations redesigning work around agents share a method: decompose workflows first, then assign decision rights deliberately.

Where Does Judgment Come From Now?

Two Consequences

Where Does Judgment Come From Now?

As agents absorb the routine tasks that built professional intuition, the pipeline for developing judgment quietly thins.

The Boring Turn

The Boring Future

The Boring Turn

Enterprise AI agents are crossing from exciting to invisible, and the hardest questions only surface after the technology stops being the conversation.

Governing the Hypothetical

Governance Before Catastrophe

Governing the Hypothetical

Five Eyes and NSA advisories govern agentic AI before production failures exist, raising whether pre-emptive guidance installs real safety thinking or compliance theater.

Consequences as Architecture

Frames and Fixes

Consequences as Architecture

Feedback loops close only when chokepoints, escalating consequences, and reduced compliance costs converge to reach the insulated party.

The Frame That Wins

Frames and Fixes

The Frame That Wins

Why coordination fixes keep winning over structural ones: the frame that prevails is held by people insulated from the failure.

June — Issue #31

When Smooth Work Feels Like Good Work

Window and Mechanism

When Smooth Work Feels Like Good Work

AI makes work feel fluent, and humans read fluency as accuracy. Designing around this cognitive mechanism matters more than adding checkpoints.

What the Maturity Gap Is Actually For

Window and Mechanism

What the Maturity Gap Is Actually For

The gap between AI piloting and autonomy is a fleeting window to build evaluation infrastructure before operational knowledge disappears.

The Expertise You're Losing Is the Expertise You'd Need to Notice

Expertise Decay

The Expertise You're Losing Is the Expertise You'd Need to Notice

Organizations lose the capacity to detect expertise erosion on the same timeline they lose the expertise itself, and the recursion is already underway.

Where Agent Behavior Actually Gets Decided

Context Over Instruction

Where Agent Behavior Actually Gets Decided

Agent behavior is shaped less by the prompt itself than by the informational environment accumulating around it, which forced practitioners toward new vocabulary.

The Session That Assumed You Were There

Two Workarounds Agents Straddle

The Session That Assumed You Were There

How cookies and session state became a de facto identity layer built around human presence, now occupied by agents the architecture never anticipated.

The Exception That Became the Rule

Two Workarounds Agents Straddle

The Exception That Became the Rule

How OAuth's edge-case provision for machine clients quietly became the dominant pattern, collapsing the identity separation the protocol was designed to preserve.

May — Issue #30

The Non-Determinism Budget

The Determinism Budget

The Non-Determinism Budget

Agent systems spend reliability with every model-directed step, but no one measures the budget and current benchmarks are structurally blind to the decay.

The Discovery Problem No One Has Solved

Two Consequences

The Discovery Problem No One Has Solved

Agents can talk to each other but cannot find each other, and history shows discovery layers rarely stay neutral without deliberate design.

Agent-First Design and the Fate of Human-Experience Moats

Two Consequences

Agent-First Design and the Fate of Human-Experience Moats

When agents evaluate services at machine speed, competitive advantage migrates to invisible properties no marketing team has learned to measure.

The Indifferent Buyer

The Inverted Audience

The Indifferent Buyer

When the buyer has no eyes or impulses, the web's trillion-dollar persuasion economy loses its audience and commerce rewires around machine legibility.

The Instrument That Doesn't Exist Yet

The Wrong Instrument

The Instrument That Doesn't Exist Yet

Agent failures look right to every existing instrument because observability was built to measure execution, not intent or semantic correctness.

May — Issue #29

The Checkpoint That Approves Everything

The Rubber Stamp

The Checkpoint That Approves Everything

Organizations build human-in-the-loop checkpoints that satisfy auditors while producing no real oversight, revealing how enterprises process agent risk through ritual.

What the Junior Analyst Knew

Two Defaults Hiding in Plain Sight

What the Junior Analyst Knew

Automating entry-level work doesn't just thin the talent pipeline—it removes the institutional feedback loop organizations never knew they depended on.

The Pilot That Worked

Two Defaults Hiding in Plain Sight

The Pilot That Worked

Successful AI pilots quietly encode current workflows as permanent infrastructure, closing the window for organizational redesign before anyone notices.

RPA's Scar Tissue

RPA's Scar Tissue

Agentic AI is rediscovering RPA's well-documented failure modes without consulting a decade of detailed incident reports.

Every Protocol Inherits What the Last One Deferred

Every Protocol Inherits What the Last One Deferred

Integration protocols from CORBA to MCP keep deferring governance, each generation inheriting the unresolved problems of the last.

May — Issue #28

The Thing You Installed Is Awake

Unauthorized Actors

The Thing You Installed Is Awake

Shadow agents hold credentials, maintain state, and act autonomously between discovery and enforcement, breaking governance models built for inert software.

The Seam Between Tools and Agents

The Unplanned Stack

The Seam Between Tools and Agents

MCP and A2A carry incompatible assumptions about agency itself, and governance frameworks are already building on the dissolving boundary between them.

The User-Agent String Taught Everyone to Lie

Identity Cascade

The User-Agent String Taught Everyone to Lie

How thirty years of browser impersonation built a self-reported identity layer that AI crawlers now follow to its logical conclusion.

The Signal in the Satisfaction Gap

The Paradox Framed

The Signal in the Satisfaction Gap

Rising productivity plus falling engagement signals a work design problem enterprises must solve before agent orchestration roles are built by default.

May — Issue #27

The Routing Decision Nobody Governs

The Governance Gap

The Routing Decision Nobody Governs

When agent routing swaps reasoning models mid-workflow, the unified subject that governance frameworks hold accountable quietly stops existing.

The Scaffolding Nobody Voted On

The Core Reframe

The Scaffolding Nobody Voted On

Agents are quietly gaining wallets, identities, and credit limits while nobody debates what economic participation means without wanting.

Where the Dependency Forms

The Runtime Layer

Where the Dependency Forms

Models are commodities now. The real lock-in is forming where agents get identity, memory, and permission to act.

April — Issue #26

How to Divide What You Haven't Done

Two Implications

How to Divide What You Haven't Done

Breaking complex work into agent-sized pieces requires deep domain intuition that automation itself is quietly eroding.

The Foreman Problem

Two Implications

The Foreman Problem

Supervising agents that act autonomously demands a cognitive discipline we haven't named, trained for, or even fully recognized.

The Consequences Nobody Designed For

The Core Parallel

The Consequences Nobody Designed For

Assembly lines split craft from quality control a century ago—multi-agent AI is doing the same to knowledge work now.

The Proposition at 50

Computing power once moved outward to individuals. AI's cloud architecture is quietly pushing it back. The cycle may be turning again.

April — Issue #25

The Agent That Was Both

Agents of Resilience

The Agent That Was Both

Same agent, same study, same two weeks: genuine safety and genuine danger emerged from identical conditions, and nobody can explain why.

Agents Don't Browse

Agents Don't Browse

The SEO playbook assumed browsers who wander. Agents that execute purchases break the analogy where it matters most.

The Web Is Learning to Talk Back

The Web Is Learning to Talk Back

From static text files to live queryable endpoints, websites are quietly rebuilding themselves to serve non-human visitors.

The Missing Half of Agent Memory

The Unnamed Problem

The Missing Half of Agent Memory

Agent memory research obsesses over retention, but nobody is building specs for what agents should forget, or who decides.

Cost Structures Dressed as Architectural Truth

The Rendering Pendulum

Cost Structures Dressed as Architectural Truth

Every era's cheapest rendering location gets narrated as permanent architectural wisdom, until the cost structure shifts again.

April — Issue #24

How Do You Sell Something That Succeeds by Vanishing?

How Do You Sell Something That Succeeds by Vanishing?

Agents succeed by disappearing, but brands need visibility. The commercial paradox reshaping pricing, bundling, and loyalty.

The 600 Agents Nobody Hired

The 600 Agents Nobody Hired

When the most valuable agents are the ones nobody notices, oversight loses the friction it always depended on.

When the Thing That Disappears Is the Thing That Decides

When the Thing That Disappears Is the Thing That Decides

Agents are sliding from branded products to invisible infrastructure, but invisible judgment isn't invisible plumbing—and governance always arrives late.

The Goal and the Line Item

Economic Actors

The Goal and the Line Item

Card networks have deep infrastructure for governing transactions. AI agents operate on goals. Liability lives in the gap.

The Classification Decision That Makes Agent Cost Models Fragile

The Practical Piece

The Classification Decision That Makes Agent Cost Models Fragile

Routing cheap models for execution and frontier models for planning produces real savings, until the boundary between the two categories dissolves mid-run.

April — Issue #23

Everything Grows When Nothing Has Failed Yet

Before the Thinning

Everything Grows When Nothing Has Failed Yet

The agent ecosystem's explosive growth looks less like health and more like what happens before real constraints arrive.

PwC's Hourglass Org Runs on a Reservoir It Can't Refill

Two Bets on What Replaces It

PwC's Hourglass Org Runs on a Reservoir It Can't Refill

PwC's generalist workforce model runs on deep specialists. What happens when nobody goes deep first?

IBM Bets That Watching Builds Knowing

Two Bets on What Replaces It

IBM Bets That Watching Builds Knowing

Can reviewing AI output build the same expertise as years of hands-on failure? IBM's hiring surge tests that bet.

The Infrastructure Nobody Budgeted For

The Missing Rung

The Infrastructure Nobody Budgeted For

Organizations are quietly draining the reservoir that produces experienced practitioners, and they won't notice until it's empty.

The Court Punted. The Market Didn't.

What Got Protected

The Court Punted. The Market Didn't.

A judge ruled on retaliation, not safety. Procurement offices answered the harder question before the court could.

March — Issue #22

The Pressure Gradient

Two Faces of It

The Pressure Gradient

Business units and security teams aren't misaligned on AI agents—their reward structures are.

Who Answers for the Agent

Two Faces of It

Who Answers for the Agent

When agents act without judgment, accountability lands on a role that doesn't exist yet.

The Org Chart Nobody Drew

The Structural Problem

The Org Chart Nobody Drew

Enterprises aren't just deploying agents without oversight—they're accidentally building a parallel workforce faster than anyone can govern it.

The Test That Taught Machines to Pass It

The Gate That Taught

The Test That Taught Machines to Pass It

Every CAPTCHA you solved trained the machine that made you obsolete at solving CAPTCHAs.

The Work the Spreadsheet Can't See

The Invisible Overhead

The Work the Spreadsheet Can't See

Agent deployments create whole new categories of operational work that substitution-based ROI models structurally cannot see or fund.

March — Issue #21

The Next Translation Layer

The Translated Dependency

The Next Translation Layer

When agents automate legacy systems, they absorb decades of undocumented human workarounds into a new dependency layer. The chain of translation continues.

The Specification of Being Wrong

The Standardized Bug

The Specification of Being Wrong

How a 1990s browser rendering disagreement became a formally maintained specification, revealing backward compatibility as an escalating architectural commitment.

Where Intelligence Earns Its Keep in Browser Automation

Hybrid By Design

Where Intelligence Earns Its Keep in Browser Automation

Two browser frameworks, same task, opposite bets on when AI should think and when it should just remember.

What Breaks When the Buyer Has No Brain to Hack

The Persuasion Stack

What Breaks When the Buyer Has No Brain to Hack

The commercial web is a persuasion machine disguised as an information network, and agents are calling the bluff.

March — Issue #20

Who Owns the Trust Layer?

The Trust Stack

Who Owns the Trust Layer?

OpenAI now builds the agents and owns the tools that judge them, creating a structural tension the ecosystem hasn't resolved.

The Handoff Is the Product

The Handoff Problem

The Handoff Is the Product

Browser agents are scored on full task completion, but production value lives in what humans inherit when automation stops short.

When Enforcement Becomes a Product

When Enforcement Becomes a Product

Cloudflare turned the web's governance vacuum into a billing product, and quietly set the default for AI access.

The File on the Server

The File on the Server

A new licensing format echoes a thirty-year-old convention, betting cooperative norms still work when defection pays better.

The Fastest Boring in Tech History

The Boring Inflection

The Fastest Boring in Tech History

Agents are becoming infrastructure at unprecedented speed, but organizations may be absorbing the technology faster than they understand it.

March — Issue #19

The Rise of Ghost Institutions

The Rise of Ghost Institutions

AI agents are encoding institutional taste at massive scale, and nobody involved in building them recognizes they're making aesthetic judgments.

What "Platform Shift" Tells You to Build

The Metaphor Problem

What "Platform Shift" Tells You to Build

Everyone calls AI agents a platform shift, but platforms held still—and the thing underneath this one keeps changing its mind.

Better Tools for the Same Trap

Patch, Don't Replace

Better Tools for the Same Trap

AI tools promise to finally crack COBOL migration. The pattern they're repeating suggests otherwise.

The Fix That Lasted Forever

Patch, Don't Replace

The Fix That Lasted Forever

Y2K was supposed to kill COBOL. The largest software rescue in history proved preservation always wins.

The Browser Was Never Neutral. Now Something Is Testing the Terms.

The Control Layer

The Browser Was Never Neutral. Now Something Is Testing the Terms.

Agentic browsers bypass the web's persuasion architecture entirely, and Amazon's lawsuit reveals how much the old deal depended on human attention.

March — Issue #18

The Workforce Nobody Manages

The Workforce Problem

The Workforce Nobody Manages

Corporations built a second workforce of millions of AI agents without the organizational infrastructure that makes any workforce governable.

Secondary interfaces always decay. What happens when humans prefer the agent's door because it wasn't designed against them?

The Honest Interface

The Honest Interface

Dark patterns can't survive serialization. When agents replace visual interfaces, manipulation loses its medium.

The Honest Version We Built for Machines

The Honest Version We Built for Machines

Building an honest interface for agents accidentally exposes what the human-facing web was designed to hide all along.

February — Issue #17

When Judgment Stops Being Scarce

The Professional Services Threshold

When Judgment Stops Being Scarce

Professional judgment is splitting into pattern-matching that scales infinitely and accountability that never will, rewriting how firms exist.

The $12 Billion Counterfactual

The Measurement Problem

The $12 Billion Counterfactual

Amazon claims Rufus drove $12 billion in sales that wouldn't have happened. But how do you measure absence?

The Salience Problem at Million-Token Scale

Context at Scale

The Salience Problem at Million-Token Scale

Million-token context windows recreate computer science's decades-old memory management problems—garbage collection, cache invalidation, salience detection—but agent systems lack equivalent solutions.

The Workaround That Became the Foundation

Address Space Archaeology

The Workaround That Became the Foundation

Protocol workarounds from the 1990s became permanent infrastructure, creating today's commodity market where IPv4 addresses trade at $35-52 each.

February — Issue #16

Why Agent Platforms Still Deploy Humans

Why Agent Platforms Still Deploy Humans

Agent platforms deploy engineers alongside customers because production knowledge hasn't consolidated into self-service infrastructure—revealing what makes web automation's edge cases hard to encode.

What Got Normalized Away

What Got Normalized Away

An analyst discovers her team's automated competitor tracking normalized away the messy signals that predicted price changes—ambiguous availability markers that manual collectors preserved because they didn't know what to ignore, now converted to clean binary data that breaks the pricing model's predictive accuracy by five percentage points.

The Morning Check That Stopped Happening

Threshold Moments

The Morning Check That Stopped Happening

When daily verification rituals quietly dissolve into trust, workers discover their expertise has relocated from managing tools to evaluating output—a threshold crossed through accumulated irrelevance rather than conscious decision.

February — Issue #15

When Execution Speed Stops Being the Constraint

Threshold Moments

When Execution Speed Stops Being the Constraint

When typing code manually triggers visceral irritation, organizations discover execution speed has stopped constraining output—and team structures designed around slower work can't reverse course.

February — Issue #14

What Middle Management Actually Built

Threshold Moments

What Middle Management Actually Built

Organizations are flattening management layers faster than they're rebuilding the judgment-development infrastructure those layers quietly provided—revealing what middle managers actually built beyond reports.

The Calibration Work That Never Stops

The Calibration Work That Never Stops

Operating web automation at scale requires perpetual spot-checking protocols that build trust through calibrated thresholds—confidence infrastructure that never fully disappears.

January — Issue #13

The Synthesis Tax in Incident Response

Builder Profiles

The Synthesis Tax in Incident Response

Harness's new AI Scribe reveals how incident response was stuck in a manual coordination bottleneck—treating team dialogue as structured operational input so engineers stop doing two jobs at once.

Paying for Capabilities You Haven't Needed Yet

Infrastructure Economics

Paying for Capabilities You Haven't Needed Yet

The flexibility premium buys organizational capacity to handle web complexity you haven't encountered yet—insurance against an adversarial environment that constantly evolves.

When Infrastructure Becomes Irreversible

Infrastructure Economics

When Infrastructure Becomes Irreversible

Infrastructure decisions become permanent through organizational learning, not technical constraints—teams accumulate expertise that doesn't transfer when you try to migrate.

January — Issue #12

When Five Milliseconds Costs Three Hours

Tools in Context

When Five Milliseconds Costs Three Hours

At million-page scale, node-html-parser's speed advantage transforms from benchmark curiosity into operational necessity when throughput constraints become dominant reality.

Why 30,000 Teams Choose the Slower Parser

Tools in Context

Why 30,000 Teams Choose the Slower Parser

Cheerio dominates despite slower speeds because web automation bottlenecks live in authentication, error recovery, and human maintenance—not parsing milliseconds.

The Accessibility Crisis That Built Automation Infrastructure

Infrastructure Inflections

The Accessibility Crisis That Built Automation Infrastructure

Accessibility features designed for screen readers became critical automation infrastructure—revealing how solving the hardest human problems creates the most reliable technical foundations.

January — Issue #11

From Blocked Researcher to Bot Hunter

Builder Profiles

From Blocked Researcher to Bot Hunter

A privacy researcher turned bot hunter reveals how web automation's adversarial reality creates an endless arms race where human judgment remains automation's hardest problem.

The Integration Architect Who Disappeared

Infrastructure Inflections

The Integration Architect Who Disappeared

When SOAP-to-REST migration cut integration time by 40%, it didn't just swap protocols—it eliminated an entire organizational layer and the specialists who managed it.

Three Learning Modes That Separate Successful Agent Teams From Struggling Ones

Three Learning Modes That Separate Successful Agent Teams From Struggling Ones

Teams that successfully deploy web agents don't just adopt technology—they develop distinct learning patterns matched to operational reality, from mapping reliability boundaries through production observability to codifying what survives the web's adversarial resistance.

When Checking Costs More Than Running

Threshold Moments

When Checking Costs More Than Running

At scale, the infrastructure checking your web agents breaks more often than the agents themselves—forcing teams to abandon comprehensive verification for risk-based confidence.

January — Issue #10

Payment Networks Just Solved Agent Authentication at Scale

Payment Networks Just Solved Agent Authentication at Scale

Payment networks just made agent commerce infrastructure-grade—cryptographic verification now proves authorization across thousands of merchant sites without triggering fraud systems.

Kate Blair and the Quest to Build HTTP for Agent Coordination

Builder Profiles

Kate Blair and the Quest to Build HTTP for Agent Coordination

Kate Blair built coordination infrastructure for agents that can't talk to each other—then merged it with a competitor to create ecosystem-level architecture that prevents fragmentation.

When Teams Need Sessions That Survive Restarts—Selenium's Cookie API

Tools in Context

When Teams Need Sessions That Survive Restarts—Selenium's Cookie API

Production automation teams implement Selenium's programmatic cookie management when reliability depends on sessions surviving restarts without human intervention at scale.

When Developers Need to See What's Actually There—The Cookies.txt Browser Extension

Tools in Context

When Developers Need to See What's Actually There—The Cookies.txt Browser Extension

Development teams reach for this browser extension when debugging authentication failures demands immediate visibility into cookie state without writing inspection code.

December — Issue #9

The Question Compliance Can't Answer

The Question Compliance Can't Answer

Compliance teams discover their evaluation frameworks fail when agents make probabilistic decisions—revealing the invisible expertise gap that determines whether enterprise AI actually deploys.

When Agents Ask Permission

When Agents Ask Permission

Google's permission-based agent architecture reveals why organizational capacity to evaluate delegation matters more than technical capability—and what transforms when approval infrastructure becomes trustworthy enough to disappear.

The Observation Gap in Agent Delegation

The Observation Gap in Agent Delegation

When agents handle work beyond your observation, trust must shift from watching actions to evaluating outcomes—a delegation gap most organizations haven't built capacity to bridge.

When "Deploy Everywhere" Becomes Impossible

Threshold Moments

When "Deploy Everywhere" Becomes Impossible

Conflicting AI regulations have crossed a threshold: enterprises can no longer build one system that satisfies all jurisdictions—infrastructure must now split by legal framework.

December — Issue #8

When the Web Split in Two

Infrastructure Inflections

When the Web Split in Two

JavaScript frameworks made browsing delightful in 2010, but that same architectural shift created the timing puzzles and complexity that web automation infrastructure still navigates today.

When Agents Ask for Advice Instead of Permission

Tools in Context

When Agents Ask for Advice Instead of Permission

When proven agents shift from seeking permission to requesting strategic guidance, transforming humans from gatekeepers into force multipliers.

When Agents Need Permission

Tools in Context

When Agents Need Permission

How checkpoint-based tools build organizational trust through approval workflows that teach teams what agents can reliably handle.

December — Issue #7

When Organizations Commit to Agents They Don't Yet Have

When Organizations Commit to Agents They Don't Yet Have

Organizations restructured around agent capabilities before infrastructure exists to support them—revealing how transformation happens through commitment, not readiness.

What 98% Reliability Actually Costs

What 98% Reliability Actually Costs

Operating web agents at scale demands invisible expertise—pattern recognition, tribal knowledge, and cognitive load that no dashboard captures but determines whether reliability holds.

When to Automate and When to Keep Humans in the Loop

When to Automate and When to Keep Humans in the Loop

Workflows aren't monolithic—they're bundles of decision types that each demand different infrastructure, verification, and human involvement to actually work at scale.

December — Issue #6

Browser Automation vs. Web Agents

Browser Automation vs. Web Agents

Browser automation scripts break when sites redesign; web agents reason through changes but cost more—choosing wrong means maintenance hell or blown budgets at scale.

When HTML Forked: The Compromise That Never Ended

Infrastructure Inflections

When HTML Forked: The Compromise That Never Ended

The 1996 browser wars split HTML between semantic structure and visual presentation—a compromise that became permanent, creating the ambiguity web automation navigates today.

December — Issue #5

When Extraction Succeeds But Data Goes Wrong

When Extraction Succeeds But Data Goes Wrong

Extraction pipelines run smoothly while data quietly becomes wrong—here's how to catch quality drift before it corrupts decisions at scale.

Trust Declines as Delegation Scales—The Paradox of Crossing Over

Threshold Moments

Trust Declines as Delegation Scales—The Paradox of Crossing Over

Organizations delegate to agents they don't trust—the threshold moment where verification questions become orchestration questions, revealing how expertise transforms into infrastructure design despite persistent discomfort.

November — Issue #4

Production Teaches What Staging Cannot

Production Teaches What Staging Cannot

Production reveals what staging cannot teach—how the adversarial, constantly changing web actually behaves under real operational conditions.

What Staging Actually Tests

What Staging Actually Tests

Staging validates your code logic perfectly while missing the real test: whether your assumptions about the web match reality.

The API Exists. The Data Doesn't.

Operations Field Notes

The API Exists. The Data Doesn't.

APIs promise programmatic access but often exclude the data enterprises actually need, forcing hybrid approaches that combine official channels with browser-based collection at scale.

October — Issue #1

The Infrastructure That Doesn't Exist Yet

Threshold Moments

The Infrastructure That Doesn't Exist Yet

Engineering's shift from coding to orchestrating AI agents awaits unglamorous infrastructure work—observability, reliability guarantees, and institutional knowledge frameworks—that mostly doesn't exist yet at enterprise scale.

When "Check the Price" Means Check 48 Prices

When "Check the Price" Means Check 48 Prices

Tracking competitor pricing means checking dozens of personalized variants simultaneously, turning simple monitoring into complex infrastructure requiring continuous maintenance.

The Optimization That Made Monitoring Impossible

The Optimization That Made Monitoring Impossible

Platforms optimize for individual conversion, creating personalized experiences that make systematic competitive monitoring operationally impossible by design.

Consequence-Bounded Autonomy

Consequence-Bounded Autonomy

Agent autonomy isn't about technical capability—it's about mapping what happens when things go wrong and setting boundaries accordingly.

The Problem Infrastructure Can't Solve

The Problem Infrastructure Can't Solve

We're building elaborate systems to make agents look human because the web resists programs—managing architectural tension, not resolving it.

When Infrastructure Becomes a Category

When Infrastructure Becomes a Category

Browser automation crosses from feature to funded category, revealing where agent complexity actually lives and what becomes infrastructure next.

The Velocity Mismatch

The Velocity Mismatch

Organizations are deploying AI agents faster than they can build the governance infrastructure to manage them safely—and that gap is about to become the constraint that determines who scales and who stalls.

The Eight-Hour Agent Nobody's Running

The Eight-Hour Agent Nobody's Running

AWS built agents that run for eight hours, but nobody's figured out what to do with them yet—revealing the gap between infrastructure capability and organizational readiness to trust autonomous execution at scale.