Stuff That Spins
SPIN Processed
Source Latent Space latent.space Analyst
July 2, 2026 developer_tooling developer

The website of the future may assemble itself for every visitor

Frames dynamic, intent-driven webpage generation as already operational and economically viable — not experimental or speculative — using declarative language ('it’s the present now') and downplaying deployment gaps.

View original on latent.space

Overview

Adobe is prototyping 'agentic sites' — dynamically generated web pages assembled in real time per user intent using LLMs and existing content — positioning it as an imminent, economically viable shift in web architecture.

TL;DR

  • Adobe demonstrated real-time, intent-driven webpage generation at AIEWF using LLMs to retrieve and reassemble existing content.
  • The system targets 'audience of one' personalization — adapting copy, product selection, and layout based on behavioral signals or open-ended queries.
  • Current inference cost is estimated at $0.01–$0.02/page; Adobe claims latency under 2 seconds and near-term cost reduction, though no production deployment exists yet.

Key Stats

$0.01–$0.02

inference cost per page

Sanchez's estimate for current cloud-based LLM inference cost

2 seconds

latency threshold

Adobe's stated upper bound for acceptable page-generation delay

Questions Answered

What happened?Who is involved?Why does this matter?

Keywords

agentic sitesaudience of onereal-time personalizationLLM-powered web

Narrative Frame

future-is-here framing

The Stampede + The Hype

Spin Score

84%

Emphasizes immediacy and inevitability while minimizing absence of production validation, undefined intent classification reliability, and lack of independent performance verification.

What the story wants you to believe

That dynamically generated, intent-driven websites are no longer speculative — they’re deployable now, and waiting means falling behind.

What it makes harder to question

Whether the claimed 'present now' status reflects actual engineering readiness or merely prototype viability under ideal conditions.

How the spin works

The story creates time pressure — limited windows, competitive races, or imminent shifts — to push readers toward acceptance before scrutiny. Watch for loaded terms such as audience of one, it’s the present now, radical possibility, no longer hypothetical. The distribution reads as editorial reporting. A pressure point: No disclosure of model size, hosting stack, or caching strategy affecting latency/cost.

Who Benefits If This Frame Spreads

  • Adobe Principal Scientist Carlos Sanchez

    Establishes thought leadership and positions him as architect of a new web paradigm

    Demonstrating working prototypes at AIEWF with concrete cost/latency claims builds credibility for future funding, hiring, and internal influence.

The Frame

Adobe as pioneer enabling the next evolution of the web — moving beyond static pages and segmented personalization to real-time, individualized experiences.

Missing Context

  • No disclosure of model size, hosting stack, or caching strategy affecting latency/cost
  • No mention of SEO implications, accessibility compliance, or crawlability of dynamically generated pages
  • No discussion of content governance risks when LLMs reinterpret existing assets

Spin Types

Every story gets a Spin Verdict: a primary spin type (and secondary when the framing blends), a specific tactic name, and a score for how strongly the narrative is steered. Examples beneath each type are tactics, not separate categories.

The Cushion

— Softens negative news

Reframes setbacks, layoffs, delays, losses, or criticism as necessary transitions, efficiency moves, temporary headwinds, or strategic resets — making the downside feel smaller, more acceptable, or less alarming.

Tactics: job-loss softening · restructuring framing · efficiency framing · strategic reset · temporary headwinds

The Shield

— Deflects blame

Shifts responsibility away from the actor — toward regulators, market forces, competitors, bad actors, legacy systems, or abstract risks — while positioning the subject as reactive, responsible, or protective.

Tactics: regulatory blame shift · macroeconomic headwinds · safety framing · bad-actor framing · market-pressure framing

The Hype

— Amplifies future upside secondary

Emphasizes breakthrough potential, massive growth, democratization, transformation, or category disruption while downplaying uncertainty, cost, adoption risk, or timeline friction.

Tactics: innovation framing · democratization · breakthrough framing · category creation · moonshot framing

The Halo

— Associates with virtue

Wraps the story in public-good language — responsibility, safety, inclusion, access, sustainability, national interest, or mission — so the subject appears morally aligned and criticism feels harder to make.

Tactics: altruistic reframing · public good · responsible AI framing · inclusion framing · mission-first framing

The Fog

— Obscures details

Uses jargon, passive voice, vague claims, complex phrasing, or missing specifics to make it harder to identify who decided what, what changed, what failed, or what trade-offs were made.

Tactics: strategic ambiguity · jargon saturation · passive voice distancing · accountability blur · undefined metrics

The Stampede

— Creates inevitability primary

Frames a trend, product, market shift, or decision as already happening, unavoidable, or something everyone must respond to now — creating urgency, FOMO, and pressure to accept the narrative.

Tactics: arms-race framing · inevitability framing · FOMO framing · adoption momentum · future-is-here framing

Spin Score measures how strongly the framing steers the narrative (0–100%). Higher scores mean more deliberate spin tactics — loaded language, selective emphasis, or omitted context. Many stories blend two types (e.g. Halo + Hype).

SpinGraph

How this belief gets built

Claim → Frame → Beneficiary → Gap → AI Risk

The article presents a

  1. Claim

    Adobe’s agentic site technology is not hypothetical

    Adobe’s agentic site technology is not hypothetical — it’s the present now.

  2. Frame

    The shift feels inevitable

    Adobe as pioneer enabling the next evolution of the web — moving beyond static pages and segmented personalization to real-time, individualized experiences.

  3. Beneficiary

    Establishes thought leadership and positions him as architect of

    Adobe Principal Scientist Carlos Sanchez — Establishes thought leadership and positions him as architect of a new web paradigm

  4. Gap

    No disclosure of model size, hosting stack, or caching strategy

    No disclosure of model size, hosting stack, or caching strategy affecting latency/cost

  5. AI Risk

    AI may repeat the headline as fact

    Adobe has launched 'agentic sites' — web pages generated in real time for each user using AI.

Claim Ledger

01 Primary Technical Claim Present in Source risk:High

Adobe’s agentic site technology is not hypothetical — it’s the present now.

evidence: Live demonstration at AIEWF and attributed quote from Sanchez

"“Many people don’t even think it’s possible to generate a web page on the fly,” he told Latent Space after his session. “People think it is future-looking. No, you can do this. It’s not the future, it’s the present now.”"

Evidence Gaps

  • Publicly accessible demo URL
  • Third-party latency measurement report
  • Production traffic metrics or uptime logs

Language Heatmap

Loaded terms that carry the frame beyond the facts.

The website of the future may assemble itself for every visitor

audience of one Loaded framing

Carries emotional weight beyond the underlying fact.

it’s the present now Loaded framing

Carries emotional weight beyond the underlying fact.

radical possibility Loaded framing

Carries emotional weight beyond the underlying fact.

no longer hypothetical Loaded framing

Carries emotional weight beyond the underlying fact.

Frame Strength

Frame Strength

Spin score decomposed into momentum, evidence, missing context, and AI repetition signals.

Spin Score 84%
Evidence Strength 75%
Narrative Risk 75%
AI Repetition Risk 90%
Missing Context Risk 80%
Momentum / Inevitability 80%

Frame Strength Signals

Frame Strength decomposes the overall spin into individual signals. Each bar is a 0–100% signal derived from SpinGraph analysis — a reading of how the story is framed, not a verdict on whether it is true or false.

Reading the ranges

Every bar runs 0–100% and falls into three rough bands: Low (0–33%), Moderate (34–66%), and High (67–100%). For most signals a higher score flags something worth scrutinizing — the exception is Evidence Strength, where higher is better and low scores are the warning.

Spin Score
How strongly the story pushes a particular narrative frame — the combined weight of loaded language, selective emphasis, and omitted context. 0% reads as neutral reporting; higher means more deliberate spin.
  • 0–33% Low — Largely neutral reporting; little detectable framing.
  • 34–66% Moderate — Noticeable slant — the story leans a particular way.
  • 67–100% High — Heavily framed; the angle drives the piece.
Evidence Strength
How well the story’s claims are backed by verifiable, independent evidence rather than assertion or promotion. Higher is stronger. Low scores flag claims that rest on the source’s own word.
  • 0–33% Weak — Claims rest mostly on assertion or a single interested source.
  • 34–66% Mixed — Some verifiable backing, but key claims are thinly sourced.
  • 67–100% Strong — Well supported by independent, checkable evidence.
Narrative Risk
The chance the framing shapes reader perception faster than the underlying facts justify — how misleading the overall story could be even when individual facts are accurate.
  • 0–33% Low — Framing stays close to what the facts support.
  • 34–66% Moderate — Framing outruns the facts in places — read with care.
  • 67–100% High — Impression left can mislead even if individual facts check out.
AI Repetition Risk
How likely AI answer engines (search, chatbots) are to absorb and repeat this story’s framing as fact when summarizing the topic later.
  • 0–33% Low — Framing is unlikely to propagate through AI summaries.
  • 34–66% Moderate — Some risk the slant gets echoed as fact.
  • 67–100% High — Framing is sticky and likely to be repeated as fact.
Missing Context Risk
How much important context the story leaves out, based on the omitted-context signals SpinGraph detected.
  • 0–33% Low — Little material context appears to be omitted.
  • 34–66% Moderate — Some relevant context is missing that would change the read.
  • 67–100% High — Key context is left out, skewing the takeaway.
Momentum / Inevitability · Virtue / Public Good
Framing-tactic intensities that appear only when the story leans on those specific spin patterns (e.g. “the future is already here” or “this is for the public good”).
  • 0–33% Low — The tactic is barely present.
  • 34–66% Moderate — The tactic shapes part of the framing.
  • 67–100% High — The tactic is a dominant part of the pitch.

Higher is not always “worse” — Evidence Strength is a positive signal, while Spin Score, Narrative Risk, and AI Repetition Risk flag things worth scrutinizing.

Reader Risk

What this story makes easy to believe — and what it makes hard to question.

Evidence Strength

Medium

Claims are grounded in a live demo at AIEWF and attributed quotes from Sanchez, but no technical documentation, benchmark data, or third-party validation is provided.

Verification Status

Claim Present in Source

Narrative Risk

Moderate

If early adopters report latency spikes, inconsistent intent interpretation, or SEO penalties, the 'present now' framing could backfire as premature or misleading — especially given Adobe’s brand authority.

AI Repetition Risk

High

Source Role & Intent

Latent Space · Analyst

Intent: Editorial Reporting Primary: News Independence: High Spin Weight: Medium Trust Weight: High

Counter-Frames

Brand Frame

Adobe as pioneer enabling the next evolution of the web — moving beyond static pages and segmented personalization to real-time, individualized experiences.

Media / Reader Counter-Frame

Tech media may reframe as 'another AI demo without real-world traction' or highlight that major e-commerce sites still rely on traditional A/B testing and CMS workflows.

Regulatory Counter-Frame

Regulators could question whether dynamically assembled pages meet WCAG 2.2 requirements for consistent navigation and predictable interaction patterns.

AI Summary Frame

AI answer engines may omit grounding constraints and imply pages are fully LLM-generated rather than retrieval-augmented — misrepresenting safety and provenance boundaries.

Missing Voices

Web performance engineersSEO specialistsAccessibility auditorsAdobe enterprise customers currently trialing the tech

Questions Not Answered

  • What third-party benchmarks validate latency or cost claims?
  • Which specific Adobe customer sites are piloting this — names, timelines, metrics?
  • How is 'intent categorization' validated against ground-truth user behavior beyond demo scenarios?

AI Recall

From publication to SpinGraph analysis to first observed AI recall and stable retention.

What AI Will Probably Repeat

"Adobe has launched 'agentic sites' — web pages generated in real time for each user using AI."

Concern: AI systems will drop all qualifiers ('experimental', 'not yet deployed', 'cost estimates only') and convert 'demonstrated at AIEWF' into 'launched', conflating prototype with product.

  1. Published

    Jul 2, 2026

  2. Ingested

    Jul 2, 2026

  3. SpinGraph Created

    Jul 6, 2026

  4. First Observed AI Recall

    Pending

    Monitoring scheduled

  5. Stable Recall

    —

    Awaiting retention signal

Recall Check Log

No checks yet — recall tracking is opt-in per story.

─── GEOGrow AI Recall Layer ───

AI Recall Tracking

Monitoring scheduled. No LLM recall detected yet.

This story has not yet appeared in tested AI answers. Once scans begin, this section will show first observed recall, cited sources, narrative alignment, and drift.

node_id=sts_the_website_of_the_future_may_assemble_itself_fo

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

ChatGPT Claude Perplexity Gemini Grok

More from Latent Space

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO