# Field Guide to Fable — Thariq Shihipar — session 2026-07-16T21:39:17.137Z → 2026-07-16T21:58:44.137Z

_50 transcript lines · 56 slides · source: full recording_

## Transcript

**[00:00:12 · 0]** Please welcome to the stage, member of technical staff at Anthropic, Tariq Shehepar. Hey, everyone. I'm Tarek. I work at Anthropic on Cloud Code. Before we get started, we have a tradition on Cloud Code where, we take a selfie before a talk.

**[00:00:42 · 0]** So if you don't mind, if you strike a pose with me, I'll, take a quick selfie at AI Engineer. Okay. Incredible. Well, yeah. To kick things off, like we said, Fable is back.

**[00:01:00 · 0]** We're rolling it out later today. Stay tuned for exact timeline. Me and Cat Wu and Simon Wilson will be doing a fireside chat at 12:30. We might have some updates for you then. But Fable is a model I'm just so, so excited about.

**[00:01:18 · 0]** It's one of those anthropic models where you're just gonna remember it, like, Sonnet 3.5 new, Opus four, Opus 4.5. It's a model that I just have a lot of, like, affection and excitement for. And the best way to describe Fable to me is, like, the the map is opening up. You know? Like, you are playing, like, an RPG, and you've been on the tutorial, and now you get to the point where the, like, you know, the open world starts.

**[00:01:45 · 0]** Right? And there's so much that you can do and explore, but there's also it's also a little bit intimidating and confusing, right, because there's so much you can do. And so what I wanted to do in this talk is give you guys a field guide to Fable. Right? How do you work with this new class of models?

**[00:02:07 · 0]** So I've got four parts to it. I've been working on this as a series of articles and blog posts, but, you know, when we announced Fable was coming out, I was like, okay, let me do, all of this at once at the talk, you know, speed run. So there are four parts, unhobbling Claude, finding your unknowns, dealing with the grief, and being unreasonable. So, first, unhobbling Claude. I think something we say really often is that the models are grown, not designed.

**[00:02:44 · 0]** Right? We don't wake up and be like, we need 99% on Sweebench. Right? Like, the models are, you know, something we grow carefully. We give it data and feedback and compute, but ultimately, it's, you know, something that we It's a little bit organic, and we sort of figure out and learn with the model as we use it.

**[00:03:05 · 0]** And so, that what that also means is that what contains them is us. Right? The harness we put them in and the way we prompt them is basically, like, a function of our understanding of Claude. Right? And by unhobbling it, I mean, how can we understand Claude better to unleash it?

**[00:03:25 · 0]** And we need to understand Fable more. So I think one of my points is that, you know, we're still so early, and I think there's a lot more understanding in Fable, to unlock. And, I think I'll give you a quick example about how models get smarter because it's a little bit unintuitive. Right? Like, there I saw this viral tweet couple weeks ago being, like, you know, why can't LLMs say which Pokemon end in a w?

**[00:03:54 · 0]** There are a thousand Pokemon, right, and turns out there are two who whose names end in a w, Croconaw and Drednaw. Right? And it turns out if you ask a normal chat model, it can't answer it, which is kind of confusing because, like, you know, and it definitely knows all the names of the Pokemon. Right? But if you ask Cloud code, it can.

**[00:04:13 · 0]** Right? Because what it does is that it fetches every Pokemon and writes a script to filter for AW. Right? And so this is what I mean by, like, unhobbling Claude. We call this capability overhang.

**[00:04:28 · 0]** Right? Claude gets smarter in spiky ways. So it doesn't just remember every Pokemon and reason through it. But if you give it the code execution tool, it can find the two Pokemons that end with a w. Right?

**[00:04:41 · 0]** And so this is I think part of the challenge with Fable is figuring out this capability overhang. What is now possible? And I think this is, like, a discovery that I'm excited to go on with you. To make this a little bit clearer, I'm gonna talk about a few different examples of how models have progressed in the past. One of the big examples, obviously, is, like, chat.

**[00:05:01 · 0]** You know, the chat models were had to be given context. Right? Like, maybe you paste in your code base and maybe, naively, you might have thought, like, you know, the way we solve coding is by the context just gets really large and I can just paste in my entire code base. You know, it'll be a 100,000,000 context window. But it turns out that instead, if you give it arms, like you give it the bash tool and ways to work with the environment, it can build and search its own context.

**[00:05:25 · 0]** And that's sort of, like, the insight that led to cloud code. Right? And so, again, spiky, like, a new, like, innovation kind of, right, in how we think about and work with the model. And then recently, we've rolled out cloud tag. And what sort of unlocked cloud tag is its ability to work proactively in multiplayer.

**[00:05:45 · 0]** Cloud code, you know, is something that you have to prompt for it to do work, right, and this ability for cloud to wake itself up and do work is something that we think is unlocking the new wave of agents. But there's more here. So, for example, we recently removed 80% of the system prompt for cloud code, right? And this is one of the ways in which models and what they need changes over time. So originally, like, you know, maybe back in Sonnet 3.5 new, the best practices for a system prompt was a small system prompt, few tools, and lots of examples.

**[00:06:22 · 0]** Right? And then as the models get smarter, you can give them more information and more instructions, and they start following them. And so it's a larger system prompt with lots of examples and many tools. Right? But most recently, we found this new class of models want fewer want a smaller system prompt.

**[00:06:40 · 0]** The examples tend to constrain it because it's actually more imaginative than the examples we give it. And so, and we tried to give it context and not just constraints. We'd really try and avoid being, like, do not do this, which is really necessary for the previous models. And so this is like a way that the system prompt is changing and probably will continue to change. Another feature I really like is the ask user question tool.

**[00:07:06 · 0]** This is something I worked on when I first got to Cloud Code and it's when Cloud you know, is planning or wants to ask you a question, it can show you a multiple choice dialogue. For Opus four, it could barely call it. I had to, like, really tweak the tool to make sure that it was, that it would work, right, and then sometime at Opus 4.5, I was like, well, what if I asked it to, like, you know, ask me 40 questions about the spec? It could start interviewing me, right, and so its ability to ask questions jumped, right, and then most recently with Opus 4.8 and Fable, I can now build a whole HTML report with the questions embedded inside of them, and, it's just like a whole new way of interacting with with Claude, right? And so, this progression of how Claude can get information from you has also changed.

**[00:07:58 · 0]** Speaking of which, markdown in HTML is something I've also talked a lot about. You know, it turned Initially, markdown was a good output for the model. You know, it could show a little bit of rich information, and then, you know, with plan mode, it started to be for you. Like, you could understand what cloud was about to do. Now, you know, cloud can build you these in-depth HTML reports.

**[00:08:21 · 0]** Right. And so, again, a way of this the model's getting smarter in a spiky way. I really like to emphasize that this is closer to a biology than a physics. Right? It's still very empirical, very organic.

**[00:08:36 · 0]** We don't know all the rules, but there is some sort of science behind it. Right? Like, there is an intuition to build as well, and so I really, you know, encourage you to treat Fable like that. One of my favorite papers at Anthropic that we've written is on the biology of a large language model. All of our research papers are meant to be read by people with various degrees of technical expertise, but this is one of my favorites.

**[00:08:59 · 0]** So if you're looking to learn a little bit more, suggest you check it out. But so, yeah, we talked about on hobbling Claude, but it turns out when you're working with Fable, you also need to on hobble yourself. Right? And so one of the things that I think a lot about is that the map is not the territory. Right?

**[00:09:19 · 0]** When I'm working on a coding problem, the plan and prompt and spec that I have in my mind is the map. Right? But the territory is the actual code base, the real world, the constraints that Claude needs to navigate. Right? And whenever Claude runs into something in the territory that's not in the map, I call that an unknown.

**[00:09:39 · 0]** Right? Claude has to figure out what to do about it. It's a decision point that I haven't specified. And Fable is one of those first models where I felt that, like, I really have to figure out my unknowns because, if not, it's gonna traverse such a large area that, like, it's going to run into a lot of them. So how do you figure out your unknowns?

**[00:10:03 · 0]** Fables bottleneck my ability to match the map and the territory to find my unknowns. So a few few ways to think about this. I like to think of it in a matrix. So, like, for any problem, I have a bunch of known knowns. This is usually, like, what I write in my prompt.

**[00:10:21 · 0]** What do I want? Right. Then I have known unknowns. Things that, like, I know I haven't don't really know yet, but I just haven't figured out yet. I can, yeah.

**[00:10:31 · 0]** Then I've got unknown knowns, like, what's so obvious that I just wouldn't write it down, you know, but I'd know it when I see it. Right? And then, finally, unknowns and unknowns. What haven't I considered at all? What do I not know?

**[00:10:43 · 0]** Right? Like, what is something that, if I knew, could change how I prompt Claude? And luckily, you can use Claude. You can use Fable to find your unknowns. So So I'm going to go over a few examples of how I do that with Fable.

**[00:10:58 · 0]** The first is I like to do what I call a blind spot pass. So I like to say something like, hey, I'm working on a new auth provider that I know nothing about, like, in this code base. Can you do a blind spot pass to help me figure out my relevant unknown unknowns and help me prompt better? Right? And so this might have Claude go through the auth module and figure out, like, oh, you know, this is kind of like a hairy little dead end that comes up a lot.

**[00:11:23 · 0]** Maybe it searches my git diff or Slack. I might tell it where there's context. Right? So that I can learn about, you know, all the gotchas. And and you can use this very broadly.

**[00:11:33 · 0]** Right? You can use it to teach you about new fields. I recently did this for color grading when doing video editing. Because I think this is really powerful and Fable is incredible at it. In many ways, the model knows more about, you know, almost everything than I do.

**[00:11:48 · 0]** I just need to get it out of it. Then I like to use brainstorms and prototypes. This helps me figure out my unknown knowns. Right? Things like especially for design and for me, it's like know it when you see it.

**[00:12:02 · 0]** Right? So I might ask it to create a dashboard, and I tell it I have no visual taste, make me an HTML page with four wildly different design decisions so I can react to them. Right? And then, you know, you tweak this as you want, but, like, the idea is to sort of get an idea of, like, what are the things that you, you know, you can't describe in words. Right?

**[00:12:23 · 0]** And, like, work with the model to help figure that out. Then then interviews. So once I have an idea of, like, this is what I want to do, there's probably still a lot of, like, unknowns here, right, where I might not have considered something, I might not have specified it, and so I'll ask Claude to interview me, right, and I'll give it a little bit more context. In any of these questions, like, giving it a little bit more context about you and the work and the stage you're at, like, hey, yeah, prioritize questions that would change the architecture, is extremely helpful. Then references.

**[00:13:00 · 0]** One of the best ways to give Claude a map is to give it another map. Right? So instead of me writing out the spec, I can just say, hey, here is some code that represents what I want to be done. Right? It could be in a different system or language, but just read this code, understand it, and then use that to start your work.

**[00:13:22 · 0]** Right? And, again, this can be in a lot of different ways. If I'm making a React component, I might have an HTML mock up that is my map, right, that I pass in as a reference. I think this is really, really powerful and Fable is really incredible at it. Something else I've, like, really appreciated is implementation notes.

**[00:13:39 · 0]** So if while you're running Fable and it runs into an unknown, ask it to log it, right, so that you can see where the deviations happened and then you can sort of figure out why as well. You know, it'll usually give you some context about what happened. And then finally, I like to get a fable to quiz me about what happened, just to make sure I understand what I'm doing and I can represent this work when I'm creating a PR or merging it. This is a really great way of, like, making sure that you're, like, really in the loop with Fable, and I think that's, like, one of the most important parts of Fable is, like, staying in the loop and making sure that you, you get what you want. So, those are some of my tips for working with Fable.

**[00:14:28 · 0]** I also want to say that the first time I used a middle class model, used Fable, I felt both a huge sense of, like, gain, but also a sense of loss, and I wanted to talk a little bit about that, you know. When I think about coding before LLMs, it feels like a foreign country, you know. Like, I used to run a YC startup about 30 people, and we're just constantly forced into trade offs because of how hard code was. Right? Like, we could make the the app fast, or we could try prototyping a new feature, and this might take a month, or this would take two months, and so we had to choose.

**[00:15:05 · 0]** It was just really, really hard. And now I went back to that code base a couple weeks ago, and I thought about some of the things that I wanted to do, and, it was just way easier. It was, like, the things that would have taken me weeks, I could do in hours. Yeah. And, at some point, it's like, yeah, like, how can you not laugh?

**[00:15:26 · 0]** Also, how can you not cry honestly? Like, it's like one of these things where, I really, really loved programming and writing code by hand. I love the feeling of, like, seeing the code base in my mind and, like, rotating it, but I also remember just, you know, like, staying up late nights trying to debug, working on things for weeks without working. Right? I just remember swimming in failure.

**[00:15:50 · 0]** I just remember that, like, the most of the projects I've ever worked on have failed. Most startups go bankrupt. You know? I think just overall programming and coding is extremely hard, and, like, as much as I enjoy those highs, I cannot go back. Right?

**[00:16:07 · 0]** And, the way my reflection here is, like, the only way out is through. Right? There's still a lot to learn with the agenda coding. There's a lot to learn with Fable, but I think if we try really hard and if we, like, stay in the loop, we un hobble it, we can get there, you know, and we can come out on the other side with just so much more. And so the last bit I wanted to talk about is the so much more part.

**[00:16:33 · 0]** Right? I call this being unreasonable. One of my favorite parts of anthropic is that we believe that trade offs are not real. Like, I think that very often I like, in my previous company, I was very used to being reasonable. So I'd, like, write down this list of priorities, and I'd be like, well, I guess we can prioritize this against this.

**[00:16:55 · 0]** Right? And, like, you know, that makes sense. So this will be our priority this quarter. But what if you just did all of it? What if you forest reality to show you the trade off?

**[00:17:08 · 0]** Right? This is something I've really valued at our culture in Anthropic, and my reflection going forward is that I'm gonna be a lot less reasonable. I think one of this, like, the math of Claude and Fable really changes how you think about trade offs, and there are so many trade offs that you make implicitly in your head. Right? Like, good, fast, cheap.

**[00:17:28 · 0]** Now it's pick three. Right? I think that, like, the best way to, like, do more ambitious work is to, like, reframe and make make ourselves more ambitious. Because I think the only way to prove that agents work is to do the best work of our lives faster than ever before. You know, for example, I made this deck last night in about four hours with Fable.

**[00:17:54 · 0]** I feel like it's a it's a deck I really like and I I really enjoyed it, but I also, you know, did it really fast. And I think that if you're here, you know, at AI Engineer, the world is kind of looking at you to prove that AI works. Right? That it's not just like a fad or something, but that it can make us more productive and also save us time. And that's my resolution for this year is to be more productive but work less and spend more time with people I really care about.

**[00:18:23 · 0]** I think it's also worth calling out that building is easier, but generating value is still hard, and I think this is something that we run into you know, as AI engineers sometimes where we think so much about the process of building and our our setups, but the the point is to generate value. Right? And, there it takes a lot of swings. It takes a lot of tries to find the valuable stuff, but that really is the goal and that's, like, you know, again, what the world is looking to us to prove that AI can really transform it. So to end, I just wanted to say, like, go explore, make it real, and, yeah, be less reasonable.

**[00:19:06 · 0]** Thank you.

## Slides

### 00:00:20–00:00:40

# THARIQ SHIHIPAR
## MEMBER OF TECHNICAL STAFF
### ANTHROPIC

[Stylized compass graphic behind the text]

### 00:00:40–00:01:00

# AI Engineer World's Fair

- INNGEST
- neo4j
- Braintrust
- CLOUDFLARE
- TOPK
- Z.AI
- Google

### 00:01:20–00:01:40

# AI Engineer World's Fair
- OpenAI
- Microsoft
- Akamai
- DataAI

### 00:01:40–00:02:00

# The Map is Opening Up
[Diagram of a map with a central red point, showing multiple paths (solid and dotted lines) connecting to it, with mountains, flags, and bird symbols as landmarks.]

### 00:02:00–00:02:20

# A Field Guide to Fable

## In the Land of AI Agents, the Verifiers Are King

Presented by Microsoft

AI Engineer World's Fair

AI

Tariq Shaukat / Chief Executive Officer
Sonar Makers of SonarQube

[Stylized map or diagram showing a path with points and triangular symbols]

### 00:02:20–00:02:40

# A Field Guide to Fable:
1. Unhobbling Claude
2. Finding your Unknowns
3. Dealing with the Grief
4. Being Unreasonable

### 00:02:40–00:03:00

# Models are grown, not designed.
[Illustration of a stylized plant growing with a star at the top, next to a blueprint-like geometric design]

### 00:03:00–00:03:20

# Models are grown, not designed.

### AI Engineer World's Fair
Presented by Microsoft

### In the Land of AI Agents, the Verifiers Are King
Tariq Shaukat / Chief Executive Officer Sonar Makers of SonarQube

[Line art illustration of a plant growing towards a star, with abstract geometric shapes in the background]

### 00:03:20–00:03:40

> What contains them is **us** — the harness we put them in, and the way we prompt them.

### In the Land of AI Agents, the Verifiers Are King

AI Engineer

### 00:03:40–00:04:00

# The Pokémon that end in “aw”

> Broski (@broskiFGC)
> its cool how half the global economy is contingent on this [black rectangle]
>
>

### 00:04:00–00:04:20

# The Pokémon that end in “aw”

### Screenshot of a tweet by Broski (@broskiFGC)
> its cool how half the global economy is contingent on this
>

### 00:04:20–00:04:40

# Fetch every Pokémon. Write a script. Filter for “aw.”

```bash
# Claude Code v2.1.143
# Opus 4.7 (1M context

### 00:04:40–00:05:00

### CAPABILITY OVERHANG
## Claude gets smarter in spiky ways

[Illustration of a stick figure climbing a steep, dark cliff face, with a dotted line indicating a path to a red dot near the top.]

### 00:05:00–00:05:20

# The evolution of agents

- **Chat**
  Has to be given context
- **Claude Code**
  Given arms to execute
- **Claude Tag**
  Acts proactively

[Diagram showing three stages of agent evolution: 1. Chat represented by a document and chat bubble, 2. Claude Code represented by a code editor window, 3. Claude Tag represented by a document with a highlighted section.]

### 00:05:20–00:05:40

# The evolution of agents

- **Chat**: Has to be given context
- **Claude Code**: Given arms to execute
- **Claude Tag**: Acts proactively

### Seeing Like an Agent
Thariq Shihipar / Member of Technical Staff ANTHROP\C

[Diagram illustrating the evolution of agents in three stages: a document and chat bubble representing "Chat", a code editor window representing "Claude Code", and a to-do list with one item highlighted representing "Claude Tag"]

### 00:05:40–00:06:00

# The evolution of agents

## Seeing Like an Agent

- **Chat**
  - Has to be given context
- **Claude Code**
  - Given arms to execute
- **Claude Tag**
  - Acts proactively

[Diagram showing three stages of agent evolution: a document and chat bubble, followed by a code editor window, then a task list with a highlighted item, connected by arrows.]

### 00:06:00–00:06:20

# We removed 80% of the system prompt from Claude Code

[Icon of a document with multiple lines of text, one line highlighted in gray]

### 00:06:20–00:06:40

# System Prompt Design
[Diagram showing three stages of system prompt design. The first stage shows a small prompt with few tools and many examples. An arrow points to the second stage, a large prompt with many tools and many examples. Another arrow points to the third stage, a smaller prompt with tool search and no examples.]
Small system prompt, few tools, lots of examples
Large system prompt, lots of examples, many tools
Smaller system prompt, tool search, no examples

### 00:06:40–00:07:00

# System Prompt Design

Small system prompt, few tools, lots of examples

Large system prompt, lots of examples, many tools

Smaller system prompt, tool search, no examples

[Diagram illustrating the evolution of system prompt design, from a small prompt with few tools and many examples, to a large prompt with many examples and many tools, and finally to a smaller prompt with tool search and no examples.]

### 00:07:00–00:07:20

# System Prompt Design
Small system prompt, few tools, lots of examples
Large system prompt, lots of examples, many tools
Smaller system prompt, tool search, no examples

[Diagram illustrating three stages of system prompt design: 1. A small document icon with a few tool icons and three small example document icons. 2. A large document icon with many tool icons and two small example document icons. 3. A medium document icon with a magnifying glass over a tool icon, and no example document icons.]

### 00:07:20–00:07:40

# AskUserQuestion

- **Opus 4**: Could call it
- **Opus 4.5**: Could interview you
- **Opus 4.8**: Could build the interview

Engineering the future of AI

[Three icons illustrating a progression: a single document, multiple stacked documents, and a dashboard with a bar chart and network diagram]

### 00:07:40–00:08:00

# AskUserQuestion

- **Opus 4**: Could call it
- **Opus 4.5**: Could interview you
- **Opus 4.8**: Could build the interview

## Engineering the future of AI

[Three icons illustrating a progression: a single document with a question mark, a stack of three documents with a question mark, and a document displaying a bar chart and a network graph.]

### 00:08:00–00:08:20

# How Claude communicates: Markdown to HTML

### Engineering the future of AI

[Diagram showing a three-step process: 1. A document with a checklist, labeled "Markdown for itself". 2. An arrow pointing to a document with text lines and a person icon, labeled "Markdown for you". 3. An arrow pointing to a document with a bar chart and line graph, labeled "HTML for decisions".]

### 00:08:20–00:08:40

# How Claude communicates: Markdown to HTML
- Markdown for itself
- Markdown for you
- HTML for decisions

[Diagram showing a three-step process: a document with a checklist, an arrow, a document with text and a person icon, an arrow, and a dashboard with a bar chart and line graph.]

### 00:08:40–00:09:00

> It's closer to a **biology**, than a **physics**.

On the Biology of a Large Language Model
Anthropic · transformer-circuits.pub

[Icon of a stylized

### 00:09:00–00:09:20

# It's closer to a **biology**, than a physics.

## On the Biology of a Large Language Model
Anthropic · transformer-circuits.pub

[Icon of a stylized atom or circuit diagram next to the paper title]

### 00:09:20–00:09:40

# The Map is not the Territory
[Abstract illustration showing a winding path with various geometric shapes (circles, triangle) on a grid within a large white circle, set against a dark background.]

### 00:09:40–00:10:00

# The Map is not the Territory
[Stylized illustration of a map with a winding path, a triangle, and various circular markers on a dark background]

### 00:10:00–00:10:20

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

### 00:10:20–00:10:40

# The Unknown Matrix

### KNOWN KNOWNS
What do I want?

### KNOWN UNKNOWNS
What haven't I figured out yet?

### UNKNOWN KNOWNS
What's so obvious I'd never write it down?

### UNKNOWN UNKNOWNS
What haven't I considered at all?

## Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

### 00:10:40–00:11:00

# The Unknown Matrix

## KNOWN KNOWNS
What do I want?

## KNOWN UNKNOWNS
What haven't I figured out yet?

## UNKNOWN KNOWNS
What's so obvious I'd never write it down?

## UNKNOWN UNKNOWNS
What haven't I considered at all?

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

[A 2x2 matrix illustrating the "Unknown Matrix" framework with four quadrants: Known Knowns, Known Unknowns, Unknown Knowns, and Unknown Unknowns, each with a guiding question.]

### 00:11:00–00:11:20

## Blindspot pass
> "I'm working on adding a new auth provider but I know nothing about the auth modules in this codebase. Can you do a **blindspot pass** to help me figure out my relevant **unknown unknowns** and help me prompt you better."

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

### 00:11:20–00:11:40

## Blindspot pass
> “I’m working on adding a new auth provider but I know nothing about the auth modules in this codebase. Can you do a **blindspot pass** to help me figure out my **relevant unknown unknowns** and help me prompt you better.”

### 00:11:40–00:12:00

## Blindspot pass
> "I'm working on adding a new auth provider but I know nothing about the auth modules in this codebase. Can you do a **blindspot pass** to help me figure out my relevant **unknown unknowns** and help me prompt you better."

### 00:12:00–00:12:40

## Brainstorms and prototypes

> "I want a dashboard for this data but I have no visual taste and don't know what's possible. Make me an **HTML page with 4 wildly different design directions** so I can react to them."

### 00:12:40–00:13:00

## Interviews
> "Interview me one question at a time about anything ambiguous — **prioritize questions where my answer would change the architecture**."

### 00:13:00–00:13:20

## References
> "This Rust crate in vendor/rate-limiter implements the exact backoff behavior I want. **Read it and reimplement the same semantics** in our TypeScript API client."

### 00:13:20–00:13:40

# References
> "This Rust crate in vendor/rate-limiter implements the exact backoff behavior I want. **Read it and reimplement the same semantics** in our TypeScript API client."

### 00:13:40–00:14:00

# Implementation notes
> "Keep an `implementation-notes.md` file. If you hit an edge case that forces you to deviate from the plan, pick the conservative option, *log it under 'Deviations'*, and *keep going*."

### 00:14:00–00:14:20

## Quizzes
> “I want to make sure I understand everything that’s happened in this change. Give me a HTML report on the changes for me to read and understand with context, intuition, what was done, etc. **and a quiz at the bottom on the changes that I must pass.**”

### 00:14:20–00:14:40

# Field Guide to Fable
## The most important part of working with Fable is **staying in the loop**

[Diagram showing a circular loop between a person icon and a terminal/code icon, with arrows indicating flow]

### 00:14:40–00:15:00

## Part 3
# Dealing with the Grief

Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

[Illustration of a stick figure walking towards a glowing opening in a dark, narrow passage, holding a bucket.]

### 00:15:00–00:15:20

# The past is a foreign country
2019-2024 · a 30-person YC startup, ~12 engineers

[Line drawing illustration of two people working at desks with laptops, and a third desk with a document]

### 00:15:20–00:15:40

> You do in **hours** what might have taken weeks, how can you not **laugh**, how can you not almost **cry**?

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

[Illustration of an hourglass with blocks falling from the top chamber to the bottom, where a red lightning bolt symbol is shown]

### 00:15:40–00:16:00

You do in **hours** what
might have taken weeks,
how can you not **laugh**,
how can you not almost
**cry**?

[Illustration of an hourglass with blocks in the top chamber and a red lightning bolt in the bottom chamber]

### 00:16:00–00:16:20

# Most projects fail, most startups go bankrupt.

> We are so used to failure, it is like water to us.

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

### 00:16:20–00:16:40

# The only way out is *through*

## Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

[Line drawing of a person swimming in water towards a rising sun]

### 00:16:40–00:17:00

# Tradeoffs are not real
[Line graph showing a decreasing dotted line with points intersecting an increasing dashed line]

### 00:17:00–00:17:20

# Tradeoffs are not real
[Line graph with two dotted trends: one decreasing with grey points, and one increasing with a highlighted red point]

### 00:17:20–00:17:40

# Good, Fast, Cheap
— Pick Three

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

[Diagram of a triangle with "Good", "Cheap", and "Fast" at its vertices, each with a checkmark. A red line crosses out the edge between "Good" and "Cheap".]

### 00:17:40–00:18:00

# Good, Fast, Cheap
— Pick Three

[Triangle diagram with vertices labeled "Good", "Cheap", and "Fast", each with a checkmark. A red line crosses out the segment between "Good" and "Cheap", illustrating that you can only pick two.]

### 00:18:00–00:18:20

# The only way to prove that agents work is to do the best work of our lives — **faster than ever** before.

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

### 00:18:20–00:18:40

The only way to prove that agents work is to do the best work of our lives — **faster than ever** before.

### Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROPIC

### 00:18:40–00:19:00

# Building is easier, generating value is still hard

[Diagram with two rows of dots, one red dot, and one outlined red dot, likely indicating progress or a conceptual scale]

### 00:19:00–00:19:20

# Go explore. Make it real.
## Field Guide to Fable
Thariq Shihipar / Member of Technical Staff ANTHROP\C

[Diagram showing a path from a starting point within a circular area with triangles, leading to a grid of dots where one is circled and two are highlighted in red.]

### 00:19:20–00:19:40

# AI Engineer
## World's Fair

[https://ai.engineer](https://ai.engineer)