Build a legal document chatbot with Laravel’s new AI SDK
Here's a step-by-step guide to building a RAG system (yeah, RAG isn't completely dead yet lol) for legal documents using Laravel's new first-party AI SDK.
The example: a Sale and Purchase Agreement. The kind of document where hallucinated clause numbers aren't just wrong, they're a liability.
What the tutorial covers:
- pgvector setup with Docker/Sail
- Clause-level document chunking with definition enrichment
- Vector similarity search via Eloquent
- An AI agent that cites section numbers (or admits when it can't find the answer)
- Streaming chat UI with Livewire
https://t.co/lsIAqkwbeV
Unfortunately after 27 days and 9 hours. My long running @OpenAI Codex Goal must come to an end. It has been an absolute pleasure watching this run for 27 days straight and seeing it progress to build something great.
Thank you @OpenAIDevs for this experience!
I can’t believe people treat hermes/openclaw as a coding agent on par with the major players.
I too can prompt a slackbot to make changes and it’s garbage for productivity. There’s a reason harnesses are converging back to IDE design.
Devin Desktop is our first product launch that’s fully agent-neutral. You can run your own custom background agents directly from the desktop app, Devin, or even Claude Code / Codex. Part of Cognition being the Independent Agent Lab is working well with all of the agents - excited to do more in this direction.
I've been using /goal for a lot of different tasks and have experimented with both helpful and ridiculous goals.
Here are some learnings/tips from that 👇
Super excited to host our first OpenAI Developer Office Hours tomorrow!
We’ll cover everything new across Codex and the OpenAI platform - /goal, mobile, plugins, Amazon Bedrock and more!
Followed by a live AMA.
Come with questions. Come with ideas. Come one, come all!
Measuring someone's productivity by their token usage is a horrible idea. Giving everyone the same fixed token budget isn't much better. So what's the right way to roll out AI across your org?
We built a system to measure how many productive engineering hours every Devin task is worth, validated against a dataset of real engineers’ times estimates. The goal is to answer the fundamental question that companies are grappling with: how much real value are you getting from each of your agent sessions?
On top of that, we're giving an AI productivity guarantee! Now if Devin delivers less engineering value than you're paying for, we fund your usage until it does.
The whole industry needs to move from measuring activity to measuring output. We hope to see more AI companies taking this approach.
More of the iOS app loop, now inside Codex.
The Build iOS Apps plugin lets Codex view and test your iOS app in the in-app browser, open SwiftUI previews, and hot reload edits without leaving Codex.
Codex can now deploy and host websites for you using Sites! 🎉
This includes storage for data and files using D1 and R2 💥
We started rolling out to Business and Enterprise customers before rolling out more broadly.
More details 👇
Cloudflare now supports self-managed OAuth clients. Build third-party apps that integrate securely with Wrangler and granular scopes.
https://t.co/khO8inrmOL
We’re making Codex more useful for your work by expanding plugins beyond individual tools.
These plugins turn Codex into a specialist for a specific role with a single install, no coding required.
Codex can access 62 popular apps and 110 skills for work across sales, data analytics, creative production, product design, and public equity investing.
https://t.co/nunrYP2uMI
Today we're excited to launch Devin Desktop.
It's compatible with Codex, Claude Agent, OpenCode, and any other ACP-compatible agent.
With this launch, the @DevinAI platform covers all major surface areas - Cloud, CLI, Desktop, Automations, Testing, and Review - the platform tackles the full SDLC.
We're proud to support great models and great agents wherever they come from, because the best work happens when you're free to pick the right tool for the job.
Excited to keep building here. ⚡️
Building apps has never been easier.
With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL.
Rolling out to Business and Enterprise plans, before expanding more broadly.
Introducing Devin Desktop: the next generation of Windsurf
Manage fleets of local and cloud agents from one surface
Support for any ACP-compatible agent
With a full IDE for when you need to jump into the code
GPT-5.5 is #1 on DeepSWE, a hard long-horizon coding benchmark 🔥
70% pass@1 vs 58% for Claude Opus 4.8.
And GPT-5.5 gets there with:
~2x faster runs
~1/2 the cost
~1/3 the output tokens
Literally, better intelligence per dollar, per minute, per task.
We’re continuing to grow, invest, and hire in APAC - 🇦🇺🇮🇳🇯🇵🇸🇬🇰🇷 32 open engineer roles 🫡
> Developer Experience Engineers (I’m baised - join me!)
> Forward Deloyment Engineers
> AI Deployment Engineers
> AI Success Engineers
> AI Support Engineers
> Solution Engineers
> Security Engineers
> Infra Engineers