---
author: EO
date: '2026-05-04'
guest: ''
layout: post.njk
source: https://www.youtube.com/watch?v=wRDk9_JoIic
speaker: EO
tags:
  - ai-agents
  - web-interaction
  - reliability
  - product-development
  - ai-workflow
title: 'AI Agents: Navigating Reliability and the Future of Web Interaction'
summary: Abhishek Das, co-founder of Ytorii, critiques the current state of AI agents, highlighting reliability issues in long workflows and the normalization of errors. He shares his journey, the vision for proactive AI assistants, and the critical importance of product craft, taste, and rigorous development in building dependable AI products.
insight: ''
draft: true
series: ''
category: ai-application
area: tech-engineering
project: []
people: []
companies_orgs:
  - Ytorii
  - IIT Roorkee
products_models:
  - Grad-Cam
media_books: []
status: evergreen
---
### AI Agents: The Promise and the Peril of Current Technology

尽管市面上涌现了大量宣称能执行任意网络任务的 AI 代理产品，但现实往往是，它们在首次尝试时便会失败。这种不确定性和低可靠性，尤其是在需要多步骤（如10步、20步甚至50步）的复杂工作流程中，会导致错误率迅速累积，使得任务的整体成功率变得很低。演讲者对此深表忧虑，认为行业似乎已经开始容忍甚至“正常化”这种不确定性和低可靠性，尤其是在产品交付方面。作为一名产品构建者，他认为将一个宣称无所不能但实际却无法一次性正常工作的代理产品交付给用户是不可接受的。他强调，如果一个代理产品无法在第一次尝试时就可靠地工作，那么它就“不够好”。这种对“含糊不清”和“不可靠”的容忍，尤其是在智能代理产品领域，是需要被挑战的。

<details>
<summary>Original English</summary>

There's
 basically
 a
 hundred
 different


agent
 products
 out
 there
 that
 are
 saying


that
 like
 this
 can
 do
 anything
 on
 the


web
 and
 you
 try
 it
 once
 and
 it
 doesn't


really
 work.
 If
 we
 think
 of
 a
 10step,
 20


step
 or
 50step
 workflow,
 even
 if
 the


accuracy
 at
 each
 step
 is
 like
 90%,
 the


10%
 error
 rate
 compounds
 very
 quickly


and
 so
 the
 overall
 success
 rate
 of
 a


task
 of
 a
 workflow
 is
 like
 quite
 low.
 So


that's
 one
 of
 the
 reasons
 why
 the


technology
 is
 not
 there
 yet
 to
 do
 long


horizon
 workflows.
 It
 feels
 like
 we
 have


started
 normalizing
 and
 developed
 a


tolerance
 for
 non-determinism
 and
 low


reliability
 in
 shipping
 products.
 The


product
 builder
 in
 me
 is
 like
 really


annoyed
 that
 how
 is
 this
 okay
 for


someone
 to
 ship
 an
 agentic
 product
 where


they
 say
 that
 this
 can
 do
 anything
 but


you
 try
 it
 the
 first
 time
 and
 like
 it


doesn't
 work.
 I
 push
 back
 on
 that


getting
 normalized
 especially
 with


aentic
 products.
 If
 it's
 not
 good
 enough


to
 work
 on
 the
 first
 try
 it's
 not
 good


enough.
 The
 true
 differentiator
 is
 in.

</details>

### Abhishek Das's Journey: From Medicine to Building AI Futures

Abhishek Das，Ytorii 的联合创始人兼联合 CEO，讲述了他如何从一个具有医生世家背景的家庭，最终投身于工程和人工智能领域。尽管来自医学世家，但他本人却对血液感到恐惧，这使得他早早地决定不追随父辈的脚步。他对科学及其严谨的**科学方法**（Scientific Method）——从提出**假设**（hypothesis），设计**实验**（experiments）来验证或推翻假设，到得出**结论**（conclusions）并提出下一轮假设——深感着迷。这种对系统性探究过程的欣赏，引导他进入工程领域。在 IIT Roorkee 的本科学习期间，他遇到了许多才华横溢的人，但很快意识到自己对电气工程（尤其是电力系统方向）的兴趣不高。这促使他在大一结束时做出了一个重要的“叛逆”决定：不再过度关注电气工程，而是将大量时间投入到学习**编程**（programming）和**软件构建**（build software）上。IIIT Roorkee 当时拥有强大的编程社群和文化，特别是 SDS Labs 这样的团队，他们热衷于为校园构建各类应用程序，这极大地激发了他的热情。从零开始构建东西，并看到用户如何与之互动，这种“多巴胺”的反馈成为了他持续前进的动力。他从小就怀有创业的愿望，尽管在本科毕业和博士毕业时都曾认真考虑过，但因各种原因未能实现。最终，他认为解决世界上的有趣问题并实现自己关心的**愿景**（vision），而非仅仅为他人工作，是促使他创业的关键。

<details>
<summary>Original English</summary>

My
 name
 is
 Abhishek
 Das.
 I'm
 the


co-founder
 and
 co-CEO
 of
 Ytorii.
 So
 with


Ytori,
 we're
 building
 agents
 that
 can


take
 actions
 and
 complete
 tasks
 on
 users


behalf
 on
 the
 web
 so
 that
 you
 can
 focus


on
 whatever
 is
 most
 meaningful
 to
 you.


The
 three
 co-founders,
 we're
 all
 AI


researchers
 by
 background.
 It
 is
 a


bigger
 bet
 than
 just
 another
 agent


company.
 So
 Faith
 Lee
 and
 Jeff
 and
 they


were
 excited
 to
 support
 us.


I
 come
 from
 a
 family
 of
 doctors
 and


medical
 practitioners.
 So
 it
 was a
 bit


of
 a
 an
 irony
 that
 I'm
 scared
 of
 blood.


And
 so
 like
 the
 choice
 was
 pretty
 clear


that
 like
 yeah
 I'm
 not
 going
 to
 pursue


medicine.
 That's
 when
 I
 ended
 up


deciding
 to
 to
 pursue
 engineering.


Science
 and
 the
 scientific
 process
 and


method
 really
 appeals
 to
 me
 like
 the


whole
 life
 cycle
 of
 coming
 up
 with


hypothesis
 then
 designing
 experiments
 to


validate
 or
 invalidate
 those
 hypothesis


drawing
 conclusions
 and
 then
 coming
 up


with
 the
 next
 set
 of
 hypothesis.
 I
 think


that
 is
 a
 very
 neat
 sort
 of
 process
 and


method.
 I
 found
 that
 really
 inspiring.


And
 then
 I
 went
 to
 IIT
 Riy
 for
 my


undergrad.
 That
 was
 a
 an
 amazing
 sort
 of


learning
 experience.
 Met
 some
 of
 the


smartest
 people
 I
 know.
 And
 so
 first


year
 of
 college
 I
 was
 getting
 good


grades
 but
 very
 quickly
 I
 realized
 that


like
 electrical
 engineering
 especially


this
 was
 more
 geared
 towards
 like
 power


systems
 etc
 was
 not
 where
 my
 interest


was
 and
 so
 at
 the
 end
 of
 first
 year
 that


was
 sort
 of
 the
 first
 major
 sort
 of


rebellious
 streak
 in
 me
 where
 I
 decided


that
 okay
 like
 I
 don't
 see
 a
 future
 in


electrical
 engineering
 I'm
 going
 to
 stop


paying
 as
 much
 attention
 to
 it.
 So
 that


was
 like
 a
 fairly
 sign significant
 fork


in
 my
 in
 my
 life
 in
 some
 sense
 and


instead
 I
 ended
 up
 spending
 a
 lot
 of
 my


time
 learning
 programming
 and
 how
 to


build
 software.
 That's
 when
 I
 got
 into


building
 software
 and
 applications
 very


seriously.
 What
 also
 helped
 was
 that


IIIT
 Rurki
 had
 even
 at
 the
 time
 this
 is


like
 almost
 13
 14
 years
 back
 had
 a


really
 strong
 programming
 club
 and


culture.
 In
 particular,
 there
 was
 this


group
 called
 SDS
 Labs,
 which
 was
 a
 group


of
 like
 10
 15
 coders
 from
 from
 every


year
 who
 were
 just
 tinkering
 and
 hack


like
 building
 a
 ton
 of
 applications
 for


the
 internet
 for
 the
 rest
 of
 the
 campus.


Seeing
 how
 users
 use
 it,
 building


something
 from
 scratch
 and
 putting
 it


out
 there
 and
 seeing
 how
 users
 interact


with
 I
 think
 that
 was
 like
 a
 dopamine


hit
 that
 kept
 like
 sort
 of
 fueling
 this.


And
 I
 would
 stay
 up
 nights
 to
 to
 build


this,
 to
 add
 features,
 to
 like
 improve


it
 and
 and
 so
 on,
 right?
 Especially


because
 I
 was
 surrounded
 by
 people
 who


were
 as
 obsessed
 with
 this
 stuff
 as
 I


was.
 And
 that
 was
 like
 extremely


extremely
 motivating.


To
 be
 honest,
 I
 wanted
 to
 start


something
 of
 my
 own
 for
 as
 long
 as
 I
 can


remember.
 I
 had
 strongly
 considered
 it


at
 the
 end
 of
 my
 undergrad,
 at
 the
 end


of
 my
 PhD,
 and
 for
 various
 reasons


didn't
 end
 up
 doing
 it.
 So,
 it
 was
 just


a
 matter
 of
 time.
 And
 the
 main
 reason


for
 it
 is
 that
 like
 there's
 lots
 of


interesting
 problems
 in
 the
 world
 to


solve
 to
 go
 after.
 Like
 I
 did
 want
 to


push
 on
 that
 vision
 that
 I
 care
 about
 as


opposed
 to
 working
 on
 somebody
 else's


vision.

</details>

### Reimagining the Web: Proactive Agents and Enhanced Accessibility

Over the past few decades, the fundamental interaction model of web browsers has remained largely unchanged: opening a page, clicking, scrolling, and typing. However, there's a significant opportunity now to reimagine this experience. The future, as envisioned by Abhishek Das, involves interacting with our **AI assistants** (AI assistants) that can take actions and complete tasks on our behalf on the web. This means moving towards a slightly higher level of abstraction, where **digital agents** (digital agents) work proactively in the background for us, handling mundane "digital chores" so we can focus on more meaningful and interesting tasks. This is seen as a more achievable near-term reality than physical agents. This collaborative model aims to improve overall productivity, rather than simply replacing humans. Furthermore, this evolution will democratize web access, making it easier for individuals, such as parents who may not want to learn every new website's interface, to accomplish tasks online simply by directing their AI assistant.

<details>
<summary>Original English</summary>

Over
 the
 last
 two
 or
 three


decades,
 web
 browsers
 by
 and
 large
 have


stayed
 the
 same,
 right?
 Like
 we
 open
 a


browser,
 we
 open
 a
 web
 page,
 we
 click


around,
 scroll,
 type
 stuff,
 etc.
 There


is
 an
 opportunity
 now
 to
 reimagine
 what


that
 experience
 looks
 and
 feels
 like.


We're
 going
 to
 be
 talking
 to
 our
 AI


assistants
 that
 take
 actions
 and


complete
 tasks
 on
 the
 web.
 And
 a
 lot
 of


it
 is
 going
 to
 be
 agents
 that
 work
 in


the
 background
 in
 a
 proactive
 manner
 for


you.
 That's
 what
 the
 future
 looks
 like.


And
 that
 is
 how
 we
 approached
 it.
 It


felt
 like
 before
 physical
 agents
 become


a
 reality
 um
 digital
 agents
 will
 become


a
 reality
 like
 the
 timeline
 for
 digital


agents
 is
 shorter
 than
 for
 physical


agents.
 If
 you
 think
 about
 interacting


with
 the
 web
 maybe
 like
 5
 to
 10
 years
 in


the
 future,
 it
 is
 going
 to
 be
 at
 a


slightly
 higher
 level
 of
 abstraction.


Instead
 of
 us
 having
 to
 do
 digital


chores
 ourselves
 manually,
 it
 lets
 us


focus
 on
 tasks
 and
 stuff
 that's
 more


meaningful,
 that's
 more
 interesting
 to


us.
 Like
 if
 we
 can
 delegate
 all
 the


mundane
 stuff
 to
 AI
 assistants,
 AI


agents
 on
 our
 behalf,
 it
 lets
 us
 focus


on
 stuff
 that's
 more
 more
 interesting
 to


us.
 So
 it's
 more
 like
 humans
 and
 agents


working
 together
 to
 overall
 improve


productivity
 less
 so
 that
 like
 these


agents
 are
 going
 to
 like
 replace
 humans


and
 then
 humans
 won't
 have
 anything
 to


do.
 But
 part
 of
 it
 is
 also
 just
 making


it
 accessible
 to
 more
 people.
 Like
 my


parents
 for
 example
 no
 longer
 have
 to


learn
 every
 new
 website
 and
 how
 to


operate
 it,
 right?
 Like
 if
 they
 can
 just


tell
 an
 assistant
 that
 this
 is
 what
 I


want
 to
 do
 on
 this
 particular
 website


and
 it
 does
 it
 for
 them
 reliably,
 then


that's
 awesome,
 right?
 So
 it
 makes
 it


more
 accessible
 for
 more
 people.

</details>

### The Critical Path to Trustworthy AI: Craft, Taste, and Rigorous Development

Building reliable AI agents that can handle complex, long-horizon workflows is an ongoing challenge. A key aspect is developing the ability for these agents to recognize their own mistakes and backtrack effectively to find alternative solutions. Ytorii invests significant effort into building robust **evaluations** (evals) and **guardrails** (guardrails) to monitor production queries, quickly identifying areas where agents excel and where they need improvement. Given the sheer volume of websites, it's impossible to train on every single one; thus, models are expected to make mistakes, much like humans do. The crucial differentiator lies in whether the agent can recognize, backtrack, and correct itself. This requires a meticulous approach to product development, moving beyond mere functionality to focus on **craft** (craft) and **taste** (taste) – ensuring intuitive and well-designed user experiences. The practice of **dogfooding** (dogfooding), where the team rigorously uses their own product internally, is vital for refining their taste and understanding what constitutes a truly "awesome" or "magical" experience. The principle of **attention to detail** (attention to detail) is paramount; if users can trust the visible parts of a product, they are more likely to trust the unseen mechanisms. Projects like **Grad-Cam** (Grad-Cam) illustrate the importance of **interpretability** (interpretability) and providing "proof of work" – showing not just the answer, but the steps taken to reach it. This transparency is fundamental for building user trust and delivering reliable products that don't just appear, but are intentionally and meticulously built.

<details>
<summary>Original English</summary>

In
 this
 day
 and
 age,
 there's
 basically
 a


100
 different
 agent
 products
 out
 there


that
 are
 saying
 that
 like
 this
 can
 do


anything
 on
 the
 web
 and
 you
 try
 it
 once


and
 it
 doesn't
 really
 work.
 And
 there's


also
 this
 notion
 of
 that
 like
 if
 you


usually
 works
 right
 like
 if
 you
 try
 it


10
 times
 then
 maybe
 like
 three
 times
 or


like
 five
 times
 it
 it
 does
 the
 right


thing
 I
 push
 back
 on
 that
 getting


normalized.
 agents
 are
 basically
 making


a
 sequence
 of
 decisions.
 Like
 if
 we


think
 of
 a
 10step,
 20
 step
 or
 50step


workflow,
 even
 if
 the
 accuracy
 at
 each


step
 is
 like
 90%,
 the
 10%
 error
 rate


compounds
 very
 quickly.
 And
 so
 the


overall
 success
 rate
 of
 a
 task
 of
 a


workflow
 is
 like
 quite
 low,
 right?
 And


so
 that's
 one
 of
 the
 reasons
 why
 the


technology
 is
 not
 there
 yet
 to
 do
 long


horizon
 workflows.
 Being
 able
 to


recognize
 when
 it
 makes
 mistakes
 and


backtrack
 from
 that
 to
 then
 uh
 go
 down
 a


different
 branch
 is
 really
 really


important.
 We
 put
 in
 a
 lot
 of
 effort


into
 building
 evals
 and
 guardrails.
 Like


every
 single
 production
 query
 that
 a


user
 runs
 goes
 through
 a
 fairly


comprehensive
 set
 of
 evals
 that
 lets
 us


quickly
 identify
 where
 these
 agents
 are


doing
 well
 versus
 not,
 which
 domains


need
 more
 work
 and
 so
 on.
 That's
 one


aspect
 of
 it.
 And
 because
 we're
 in
 this


space
 of
 web
 agents,
 right?
 Like
 agents


that
 can
 do
 actions
 and
 tasks
 on
 the


web.
 It
 will
 never
 be
 the
 case
 that
 we


will
 be
 able
 to
 train
 on
 every
 single


website
 that's
 out
 there.
 Like
 there's


new
 websites
 coming
 up
 all
 the
 time.
 The


number
 of
 websites
 that
 exist
 in
 the


world
 is
 already
 pretty
 large.
 So
 we


will
 always
 be
 training
 on
 a
 finite
 set


of
 websites
 and
 improving
 these
 models


there.
 Like
 people
 make
 mistakes
 on
 new


website,
 click
 on
 the
 wrong
 buttons,


etc.
 all
 the
 time,
 right?
 Like
 so
 it
 is


very
 natural
 to
 expect
 models
 to
 also


make
 mistakes.
 But
 when
 it
 makes
 a


mistake,
 is
 it
 able
 to
 recognize
 and


then
 backtrack
 and
 correct
 itself
 to
 do


the
 right
 thing
 is
 a
 fairly
 important


ingredient
 in
 the
 recipe
 of
 like
 how
 we


train
 and
 build
 and
 ship
 these
 models.


But
 the
 other
 part
 is
 is
 more


ecosystemwide
 where
 like
 it
 feels
 like


we
 have
 started
 normalizing
 and


developed
 a
 tolerance
 for


non-determinism
 and
 low
 reliability
 in


shipping
 products.
 I
 don't
 like
 the


normalization
 of
 slop
 and


non-determinism
 and
 poor
 reliability


especially
 with
 agentic
 products.
 Yeah,


if
 it's
 not
 good
 enough
 to
 work
 on
 the


first
 try,
 it's
 not
 good
 enough.
 We
 take


sort
 of
 an
 80/20
 approach
 to
 it.
 Like


there
 is
 always
 the
 prioritization


question
 of
 like
 okay
 there
 are
 100


features
 that
 we
 could
 be
 building.
 What


are
 the
 top
 10
 that
 we
 need
 to
 focus
 on?


Like
 some
 of
 those
 are
 informed
 by
 users


and
 what
 what
 users
 are
 are
 telling
 us


what
 they're
 asking
 for.
 But
 very
 often


there
 are
 ways
 to
 build
 product
 that


users
 may
 not
 be
 asking
 for.
 But
 if
 you


built
 it
 and
 a
 lot
 of
 intuition
 goes


into
 identifying
 what
 those
 features


might
 be.
 Then
 users
 feel
 seen
 and
 they


feel
 like
 oh
 this
 is
 someone
 who
 is


listening
 to
 us.
 Even
 though
 that's
 not


exactly
 what
 they
 asked
 for
 initially.


I'll
 give
 you
 an
 example.
 The
 feature
 on


iOS
 or
 Android
 that
 like
 anytime
 you
 get


a
 two-factor
 authentication
 SMS,
 it
 auto


reads
 your
 SMS
 and
 fills
 it
 into


whichever
 app
 asked
 for
 it.
 It
 is
 hard


to
 imagine
 like
 a
 user
 asking
 for
 that


feature.
 But
 it
 saves
 a
 few
 seconds


multiple
 times
 a
 day
 for
 people
 all


across
 the
 world.
 But
 it's
 like
 a
 tiny


thing
 that
 makes
 users
 feel
 seen
 like
 oh


someone
 is
 actually
 giving
 thought
 how


to
 reduce
 these
 tiny
 paper
 cuts
 in
 our


in
 our
 day-to-day
 life.
 That's
 really


important.
 So
 like
 it
 is
 a
 marriage
 of


intuition
 with
 what
 users
 are
 actually


asking
 for.
 In
 a
 world
 where
 it's
 very


easy
 to
 come
 up
 with
 first
 prototypes


using
 these
 coding
 LMS
 the
 true


differentiator
 is
 in
 taste
 and
 craft
 in


how
 intuitive
 and
 welldesigned
 the


product
 is.
 One
 thing
 we
 do
 in
 the
 team


that
 helps
 with
 that
 I
 think
 is
 we
 take


uh
 dog
 fooding
 our
 own
 product
 very


seriously
 like
 every
 single
 week
 we
 have


an
 hour
 hour
 and
 a
 half
 docked
 out
 for


dog
 fooding
 new
 features
 in
 the
 product


at
 any
 given
 point
 of
 time
 we're
 running


like
 tens
 of
 experiments
 internally
 and


maybe
 like
 one
 of
 them
 will
 ship
 to
 the


um
 production
 version
 of
 the
 product


that
 external
 users
 will
 see.
 So
 like


constantly
 dog
 fooding
 our
 our
 own


product
 is
 a
 way
 to
 refine
 our
 own
 taste


for
 like
 okay
 what
 is
 good
 versus
 bad


what
 awesome
 or
 magical
 feels
 like.
 Like


anything
 else
 um
 a
 lot
 of
 reps
 uh
 to


build
 that
 muscle
 is
 like
 one
 way
 to
 go


about
 it.


The
 grad
 cam
 project
 was
 led
 by
 one
 of


my
 labmates.
 I
 was
 sort
 of
 a
 supporting


author
 on
 that
 paper.
 I
 was
 25
 when
 we


did
 that
 paper.
 It's
 been
 extremely


wellreceived.
 I
 think
 20
 30,000


citations
 is
 quite
 non-trivial
 at
 the


time.
 Interpretability
 in
 like
 around


deep
 learning
 models
 was
 like
 a
 big
 area


of
 focus
 still
 is
 to
 this
 day.
 And
 so
 it


was
 motivated
 from
 that
 that
 like
 okay


like
 these
 models
 especially


classification
 models
 to
 start
 with
 that


go
 from
 like
 images
 to
 classifying
 it
 in


one
 of
 thousand
 or
 10,000
 categories.


What
 part
 of
 the
 image
 are
 they
 looking


at
 to
 make
 those
 predictions?
 Right?


There
 is
 clearly
 some
 signal
 coming
 from


the
 image
 itself
 and
 then
 some
 signal


that
 may
 be
 coming
 from
 the
 label
 that


the
 classification
 model
 is
 predicting


and
 how
 can
 we
 combine
 the
 two
 develop


better
 intuition
 for
 what
 part
 of
 the


image
 the
 model
 is
 looking
 at.
 To
 this


day,
 it
 seems
 to
 work
 quite
 effectively


across
 a
 bunch
 of
 tasks
 and
 models.
 Like


with
 AI
 models,
 it
 is
 important
 for


models
 to
 be
 able
 to
 convey
 not
 just
 the


final
 prediction
 or
 the
 final
 answer,


but
 also
 the
 proof
 of
 work.
 like
 what


are
 the
 steps
 that
 went
 into
 coming
 up


with
 this
 final
 prediction
 or
 the
 final


answer.
 And
 so
 Grad
 Cam
 is
 like
 one


manifestation
 of
 that.
 But
 even
 in
 how


we
 build
 the
 the
 scouts
 product
 today,


like
 you
 can
 set
 up
 these
 scouts
 and


agents
 to
 monitor
 the
 web
 for
 something


and
 they
 will
 generate
 these
 reports
 and


notify
 you
 when
 they
 find
 something


that's
 of
 value
 to
 you.
 But
 there
 is
 a


button
 in
 the
 UI
 that
 lets
 you
 inspect


the
 work
 that
 went
 in
 in
 behind
 the


scenes
 like
 which
 websites
 were
 were


visited,
 what
 did
 the
 agent
 actually


look
 at
 to
 pull
 out
 this
 piece
 of


information
 and
 that
 gives
 you
 a
 glimpse


into
 the
 work
 that
 went
 in
 behind
 the


scenes
 to
 put
 this
 together.
 It
 is
 very


very
 important
 for
 trust
 building
 for


users
 to
 be
 able
 to
 trust
 that
 yes
 this


is
 a
 reliable
 product.


A
 lot
 of
 our
 time
 and
 attention
 in
 how


we're
 building
 our
 product
 at
 UTI
 goes


into
 thinking
 about
 how
 should
 we
 build


the
 product
 so
 that
 we
 don't
 make
 the


same
 mistake.
 Whenever
 we
 ship


something,
 we
 have
 to
 get
 it
 right.
 It


has
 to
 really
 work.
 It
 has
 to
 be


reliable.
 Users
 have
 to
 trust
 that
 it


works
 well.
 If
 we
 put
 attention
 to


detail
 into
 parts
 of
 the
 product
 that


users
 can
 see,
 then
 the
 user
 is
 more


likely
 to
 trust
 the
 parts
 of
 the
 product


that
 they
 cannot
 see.
 Right?
 like


everything
 awesome
 that
 we
 see
 around


us,
 it's
 like
 individuals
 or
 groups
 who


put
 in
 a
 lot
 of
 hard
 work
 and
 attention


to
 detail
 to
 build
 that.
 So
 I
 think
 we


should
 approach
 everything
 that
 we
 are


building
 with
 that
 kind
 of
 philosophy.


It
 takes
 time
 to
 build
 something


meaningful,
 to
 build
 something
 right,
 to


bring
 a
 vision
 of
 the
 future
 to
 life
 and


building
 like
 delight
 delightful
 and


reliable
 product
 experiences.
 It
 doesn't


just
 appear
 out
 of
 nowhere.

</details>