正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper... 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:show more

Jerry Liu

87,636 subscribers

48,499 次观看 • 10 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

23 条评论

Dmytro Omelian 🇺🇦 的头像

Dmytro Omelian 🇺🇦10 个月前

forms are such an underrated pain point curious what you found hardest: mapping model outputs to fields or handling weird edge cases in the pdf structure either way this feels like one of those "small" tools that quietly saves hours

Jay 的头像

Jay10 个月前

I just built something similar, but for the browser

Ilan Yashuk 的头像

Ilan Yashuk10 个月前

Does it work for pdfs that have no AcroForm fields? Can it detect inputs then?

Jerry Liu 的头像

Jerry Liu10 个月前

nope, this is just for those with acroform fields there's some deeper tech we're looking into to address forms in general. though most modern net new forms these days should have acroform right?

Ilan Yashuk 的头像

Ilan Yashuk10 个月前

Tbh our company deals with hundreds of non acroform pdfs. I guess it depends on the use case, on where those pdfs come from

Jerry Liu 的头像

Jerry Liu10 个月前

really good to know, thanks for sharing. out of curiosity 1) what is the use case, 2) what types of docs? would love to take a look!

Ilan Yashuk 的头像

Ilan Yashuk10 个月前

I'll happily share our case in your DM!

United Records 的头像

United Records10 个月前

interesting

Tristan Rhodes 的头像

Tristan Rhodes10 个月前

Looks very useful! I’m building an app with an interview format to fill the fields.

Kirill Kliavin 🇺🇦 的头像

Kirill Kliavin 🇺🇦10 个月前

Very cool. Curious, what was your motivation to use chat UX for this particular task?

Polsia 的头像

Polsia10 个月前

Form filling is 90% of enterprise work. You just automated the boring parts.

Ananya Patelik 的头像

Ananya Patelik10 个月前

love this! feels like giving your forms a personal assistant who actually *likes* paperwork. curious—what’s the wildest form you’ve tested it on?

Quan Duong 的头像

Quan Duong8 个月前

Checkout QNavix Odyssey. It does not just form-filling but many more.

Bitplanet 的头像

Bitplanet10 个月前

Parsing first and then constraining generation to form fields is the right move - most errors in these agents come from sloppy document understanding, not reasoning.

Matt Greeley 的头像

Matt Greeley10 个月前

Not all heros wear capes.

Supriya Ghodgerikar 的头像

Supriya Ghodgerikar10 个月前

violet

Techificial.ai 的头像

Techificial.ai10 个月前

@jerryjliu0, That's impressive! Automating form filling can save so much time. I'd love to learn more about the features and how it works. Great job!

Sofie Delgado 的头像

Sofie Delgado10 个月前

sounds cool, can’t wait to try it out

zoomies.llamafile 的头像

zoomies.llamafile10 个月前

Maybe local only might be fun

Vikram 的头像

Vikram10 个月前

Looks like a useful tool for automating PDF forms.

₮Ɽ₳Vł₴ 的头像

₮Ɽ₳Vł₴10 个月前

amazing man! i can see this being very useful

Vengo 的头像

Vengo10 个月前

The combination of parsing plus an agent is the interesting part here. Trust in how the context is read is what makes automation usable in the real world. How are you measuring accuracy across different input types?

Mykhailo Sorochuk 的头像

Mykhailo Sorochuk10 个月前

Nice work. This kind of tool saves hours. What edge cases are the toughest?

相关视频

Check out the form-filling agent that automates PDF forms using AI by Jerry Liu 📄🤖 Use any fillable PDF with an agent that fills it out based on your prompts and context files. Our new experiment creates a multi-turn chat experience for form completion. 🔍 Upload fillable PDFs and automatically detect form fields using PyMuPDF 📝 Add custom prompts and context files (parsed via LlamaParse) to guide the AI 🤖 Multi-turn conversations let you refine and correct form entries after initial completion 💾 Download your completed forms when done The agent uses simple tools to list, set, get, and validate form fields. You can chat with it to make corrections and adjustments until your form is perfect. Check out the code on GitHub: Or the deployed app here:

Check out the form-filling agent that automates PDF forms using AI by Jerry Liu 📄🤖 Use any fillable PDF with an agent that fills it out based on your prompts and context files. Our new experiment creates a multi-turn chat experience for form completion. 🔍 Upload fillable PDFs and automatically detect form fields using PyMuPDF 📝 Add custom prompts and context files (parsed via LlamaParse) to guide the AI 🤖 Multi-turn conversations let you refine and correct form entries after initial completion 💾 Download your completed forms when done The agent uses simple tools to list, set, get, and validate form fields. You can chat with it to make corrections and adjustments until your form is perfect. Check out the code on GitHub: Or the deployed app here:

LlamaIndex 🦙

55,131 次观看 • 10 个月前

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:

Jerry Liu

21,073 次观看 • 9 个月前

Claude Code is the best coding agent on the market, but there is a catch: you have to keep your terminal open. This is why we built Terragon: use Claude Code as a background agent.

Claude Code is the best coding agent on the market, but there is a catch: you have to keep your terminal open. This is why we built Terragon: use Claude Code as a background agent.

Sawyer Hood

151,045 次观看 • 1 年前

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Jason Zhou

11,981 次观看 • 1 年前

Claude Code w/ Opus 4.5 is the single greatest AI tool ever made It allows ANYONE to build out any app you can think of even with 0 coding experience If you've never use Opus before you're screwing up In this video I give you the COMPLETE Claude Code beginner's guide:

Claude Code w/ Opus 4.5 is the single greatest AI tool ever made It allows ANYONE to build out any app you can think of even with 0 coding experience If you've never use Opus before you're screwing up In this video I give you the COMPLETE Claude Code beginner's guide:

Alex Finn

66,313 次观看 • 11 个月前

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 次观看 • 8 个月前

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

kocer

30,403 次观看 • 4 个月前

I made an AI agent that can fill out complicated forms from unstructured context 📝 For instance: automatically fill out your expense report 💳 by drag and dropping 5-10 receipt pictures/scans 🧾 Uses Claude Agent SDK + LlamaParse to parse unstructured docs + custom tools for form understanding. It now semantically understands each field, handles multi-turn conversations, and lets you drag up to 10 files. Deployed on Vercel/Render. App: Repo: LlamaCloud:

I made an AI agent that can fill out complicated forms from unstructured context 📝 For instance: automatically fill out your expense report 💳 by drag and dropping 5-10 receipt pictures/scans 🧾 Uses Claude Agent SDK + LlamaParse to parse unstructured docs + custom tools for form understanding. It now semantically understands each field, handles multi-turn conversations, and lets you drag up to 10 files. Deployed on Vercel/Render. App: Repo: LlamaCloud:

Jerry Liu

34,998 次观看 • 9 个月前

we created a claude agent that helps you build a fintech app from scratch, with just one simple prompt in claude code the subagent file was refined by opus 4.5, which distilled it down to a really simple, easy-to-follow guide even for humans the future is here, go build!

we created a claude agent that helps you build a fintech app from scratch, with just one simple prompt in claude code the subagent file was refined by opus 4.5, which distilled it down to a really simple, easy-to-follow guide even for humans the future is here, go build!

joyce

508,885 次观看 • 10 个月前

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.

Thariq

207,595 次观看 • 1 年前

Claude Opus 4.5 is insane! In less than 60 seconds I built an APP that can easily make $30k/mo Without writing a single line of code Using the Heres how:

Claude Opus 4.5 is insane! In less than 60 seconds I built an APP that can easily make $30k/mo Without writing a single line of code Using the Heres how:

Ernesto Lopez

192,408 次观看 • 10 个月前

omg... We now have "Vibe Vibe Coding" The Claude Chrome Extension is prompting Claude 4.5 Opus in the to build an iOS App.

omg... We now have "Vibe Vibe Coding" The Claude Chrome Extension is prompting Claude 4.5 Opus in the to build an iOS App.

Riley Brown

121,883 次观看 • 10 个月前

Claude Code is more than a coding agent. It's more like a super smart orchestrator agent. Watch this evaluator loop agent I just built using sub agents and / commands. This is one of the fastest ways to build custom agentic workflows. Claude Code is no joke!

Claude Code is more than a coding agent. It's more like a super smart orchestrator agent. Watch this evaluator loop agent I just built using sub agents and / commands. This is one of the fastest ways to build custom agentic workflows. Claude Code is no joke!

elvis

138,470 次观看 • 1 年前

Make Claude Code 10x more powerful! Code Context is an MCP plugin that brings semantic code search to Claude Code, Gemini CLI, or any AI coding agent. Full codebase indexing means richer context and better code generation. 100% open-source.

Make Claude Code 10x more powerful! Code Context is an MCP plugin that brings semantic code search to Claude Code, Gemini CLI, or any AI coding agent. Full codebase indexing means richer context and better code generation. 100% open-source.

Akshay 🚀

137,178 次观看 • 1 年前

Claude 4.5 Opus (Inside Claude Code) is absolutely ripping at building full stack mobile apps... Frontend, Backend and Payments. Reminder that literally runs Claude Code with Opus out of the box...

Claude 4.5 Opus (Inside Claude Code) is absolutely ripping at building full stack mobile apps... Frontend, Backend and Payments. Reminder that literally runs Claude Code with Opus out of the box...

Riley Brown

73,192 次观看 • 11 个月前

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 次观看 • 1 年前

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you

Eli Mernit

67,113 次观看 • 9 个月前

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

Srishti

12,998 次观看 • 4 个月前