Andrew Wong

54 posts

Andrew Wong banner
Andrew Wong

Andrew Wong

@41five

Sr. Developer Relations Engineer @ Box

San Francisco Katılım Nisan 2010
81 Takip Edilen25 Takipçiler
Andrew Wong
Andrew Wong@41five·
Excited to be part of this one. Come hang out if you’re curious about building better agent experiences over enterprise content. Files, agents, demos, controlled chaos, the whole nine 🫪
Carter Rabasa@crtr0

Want to learn how to build a company brain for your agents? 🧠 Join @chriskim_dev & @41five from the @box devrel team on July 28th at 4pm PT for our webinar on creating a governed memory layer with Box APIs and MCP. All code, no fluff, sign-up at: events.zoom.us/ev/AnJFdyO9sHq…

English
0
0
6
617
Andrew Wong
Andrew Wong@41five·
Practical and straightforward to set up. Thanks for sharing this with the team 🤙
Chris Kim@chriskim_dev

1) Every morning, @Box's DevRel team used to spend time manually pulling together what's new in AI. Last night I demoed how we killed that process at Agent-Led Growth / Agent Experience Demo Night, hosted by Sapient and sponsored by @auth0. Now my @NousResearch Herme agent writes the digest for us, automatically, every day.

English
0
0
4
986
Andrew Wong retweetledi
Box
Box@Box·
Grok 4.5 reviewed a full Credit & Security Agreement stored in Box — the kind of dense, multi-section facility document that typically requires significant counsel time. @Grok 4.5 used Box MCP to access the file securely, extract key terms across the agreement, identify potential conflicts with existing debt covenants, and compile a summary of items for counsel to review, and finally saved the memo back to the same folder. As frontier models keep leveling up, they are unlocking more opportunities for companies to automate and unlock their enterprise content. Check-out the generated report here: app.box.com/s/zfwfud9ojwbv…
SpaceXAI@SpaceXAI

Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency. x.ai/news/grok-4-5

English
60
81
551
1.5M
Andrew Wong
Andrew Wong@41five·
@ivanburazin This post is best viewed in Netscape Navigator at 800x600 resolution. Please sign my guestbook before you leave.
English
1
0
1
70
Ivan Burazin
Ivan Burazin@ivanburazin·
Someone used the word "webmaster" the other day, and I stopped what I was doing and thought about it for a couple of seconds. That used to be a legit job title. There were job postings, and people put it on their resumes with pride. Sometimes I genuinely feel old.
English
18
1
68
5.6K
Andrew Wong
Andrew Wong@41five·
Tiny bit of what’s happening under the hood: One @GeminiApp API request connects a Managed Agent to Box through MCP, gives the agent controlled access to the right Box content, and asks it to find and review a contract. The response includes Box tool calls, the generated risk report, and the report saved back into Box. Context window, meet content layer 🤠
Box@Box

AI agents need more than intelligence. They need trusted business context. With @GeminiApp Managed Agents now supporting remote MCP servers, developers can connect Gemini agents to governed content in Box, generate outputs from real enterprise files, and save the work back where teams already collaborate. Box MCP Server + Gemini API in action.👇

English
1
0
4
1.1K
Andrew Wong
Andrew Wong@41five·
An agent that hides its work is just a confident guesser 👀 On July 14, @bromann (@LangChain) and I are showing how to build agents that actually show their work - live tool calls, reasoning steps, and trusted context from Box. No black boxes, no vibes-based answers. Come see it live👇 events.box.com/box-webinars/b…
Andrew Wong tweet media
English
0
1
6
5.7K
Andrew Wong
Andrew Wong@41five·
AIEWF had that rare energy where the talks mattered, but the hallway conversations, weird demos, and accidental moments mattered just as much. And yes, somehow that includes a dancing lizard number - questionable in theory, unforgettable in practice 🦎
Carter Rabasa@crtr0

x.com/i/article/2074…

English
1
0
4
1.1K
Andrew Wong retweetledi
Carter Rabasa
Carter Rabasa@crtr0·
Thanks to everyone who showed up for our @aiDotEngineer AIEWF @Box raffle! You all had choices for your 1pm raffle, I'm honored you chose to be with us 💙 Want to run your own selfie raffle? Steal this app: github.com/box-community/…
Carter Rabasa tweet media
Andrew Wong@41five

If you're at @aiDotEngineer World’s Fair and you’re into AI, enterprise content, or deeply committed booth puns, swing by Box booth #S23 Enter the raffle for an X…@Box, and come say hi to @crtr0, @chriskim_dev, and me!

English
0
4
21
1.1K
Andrew Wong
Andrew Wong@41five·
If you're at @aiDotEngineer World’s Fair and you’re into AI, enterprise content, or deeply committed booth puns, swing by Box booth #S23 Enter the raffle for an X…@Box, and come say hi to @crtr0, @chriskim_dev, and me!
Andrew Wong tweet media
English
0
1
5
1.3K
Andrew Wong
Andrew Wong@41five·
A wiki becomes a lot more valuable when agents (and humans 👀) are grounding themselves in a trusted source of truth. Scoped to the right slice, of course.
Biswaroop Palit@bpalit

@hwchase17 s “wiki memory” really resonates with how we’ve been thinking about Enterprise Knowledgebases. Agent memory is still early, but one pattern we observe consistently: enterprises don’t need agents to retrieve raw documents, Slack threads or tickets at query time. They need to turn all of that messy source material into a durable, compact, inspectable knowledge layer that future agents can rely on. In the enterprise, memory cannot just be a folder of markdown files sitting somewhere. It needs to be governed, permission-aware, shareable across team members etc. This is where @Box plays a critical role. Box already sits on top of a huge amount of enterprise knowledge. The next step is making that content agent-ready: synthesize the raw source material into structured knowledge, keep it fresh as the underlying content changes, respect permissions etc. That turns Box from a system of record for enterprise content into a governed memory layer for enterprise agents. We wrote about this here x.com/Box/status/206… The future “Company Brain” in the enterprise will be built from trusted source content, agent-maintained synthesis, and enterprise-grade governance.

English
0
0
4
294
Andrew Wong
Andrew Wong@41five·
The fable is real (again) 🙌
Box@Box

We're excited to see that @claudeai Fable 5 has been reinstated. It will be available to Box customers in Box AI Studio soon. Watch as the model parses complex vendor agreements and earnings reports across multiple documents and exhibits, and outputs structured, source-grounded analysis that catches inconsistencies a human reviewer shouldn't miss.

English
0
0
4
717
Andrew Wong
Andrew Wong@41five·
@Box Turns out “just point the AI at all your files” is not, in fact, an enterprise strategy. You gotta make that content trusted, governed, and usable.
English
0
0
0
15
Box
Box@Box·
If you're building agentic enterprise workflows, you've probably hit this wall: agents need trusted knowledge to act on, but most enterprise content is scattered, ungoverned, and impossible to verify at scale. We break down how to solve it using Box as a governed knowledge layer: → Claude connects to Box through the Box MCP server to review uploaded content, extract metadata, and flag issues like stale dates or missing owners → Box Automate routes it through a human approval workflow → Once approved, it lands in a curated Box Hub where agents answer questions from Slack and cite the source files. Simple as that. Get the step-by-step here. 👉 bit.ly/4ak1HSZ
English
3
3
11
1.2K
Andrew Wong
Andrew Wong@41five·
@Box Turned yesterday’s thread into a fuller write-up on the blog. Same idea, more words: how enterprise content becomes *trusted* knowledge for AI agents. blog.box.com/how-enterprise…
English
0
0
0
31
Andrew Wong
Andrew Wong@41five·
Been playing with a workflow for a problem that comes up a lot with agents: They can search a bunch of content, but should they? In real company folders, you’ve got approved docs, stale decks, draft notes, random pricing sheets, etc. So I made a quick demo using: - @Box for the content + permissions - Box Automate so a file upload can kick off the whole review flow, without me running a webhook server - Box MCP via @SlackHQ Slackbot, so context shows up where my team's already talking Mostly just trying to make agent context more like “use the stuff the team actually trusts” and less “search everything and hope” 🙃
English
1
5
13
1.8K
Andrew Wong
Andrew Wong@41five·
In SF for AI Engineer World’s Fair? Come visit us at Box booth # S23 Our CTO, Ben Kus, is also hosting a session on “The Half Life of Agent Infrastructure.” See you there 🤙
Andrew Wong tweet media
English
0
1
6
3.1K
Andrew Wong retweetledi
Box
Box@Box·
Loan origination workflows are document-heavy by nature. Driver's license. W-2. Paystubs. Bank statements. Purchase agreements. Stitching those steps together without building a fragile custom pipeline is the hard part. Learn how to build a Next.js loan origination app using Box UI elements for document upload, Box AI to classify uploaded files automatically, and Box Sign to capture credit authorization without the borrower ever leaving the app. Full breakdown here 👇 blog.box.com/building-smart…
English
0
2
9
2K
Chris Kim
Chris Kim@chriskim_dev·
If you want to stay on top of agentic workflows for teams, give @41five a follow. Andrew is a 7+ years veteran developer educator and the man shipped 60+ dev videos for @Box in the last 6 months.
Andrew Wong@41five

Been playing with a workflow for a problem that comes up a lot with agents: They can search a bunch of content, but should they? In real company folders, you’ve got approved docs, stale decks, draft notes, random pricing sheets, etc. So I made a quick demo using: - @Box for the content + permissions - Box Automate so a file upload can kick off the whole review flow, without me running a webhook server - Box MCP via @SlackHQ Slackbot, so context shows up where my team's already talking Mostly just trying to make agent context more like “use the stuff the team actually trusts” and less “search everything and hope” 🙃

English
1
0
2
733
Andrew Wong
Andrew Wong@41five·
Loving this weekly curated digest man 🤙
Chris Kim@chriskim_dev

I built a @NousResearch Hermes workflow that my team at @Box uses to track AI trends. Every day at 7am, it researches what's happening across the AI ecosystem and generates a brief for our team. We use it to identify: • AI trends worth paying attention to • Open source projects gaining momentum • New tools developers are adopting • Content opportunities to work on next I've been building agentic workflows for months, and this is one I've actually integrated into my team's daily workflow. Here's how I built it:

English
0
0
1
34
Andrew Wong
Andrew Wong@41five·
@BoxPlatform My favorite bit: the agent knows when *not* to answer It uses the Hubs it can access, then flags legal/finance review instead of guessing from restricted content
English
0
0
0
11
Box Developers
Box Developers@BoxPlatform·
Enterprise AI agents are only as good as the knowledge layer behind them. The challenge is making sure agents use trusted knowledge, respect permissions, cite sources, and route sensitive decisions to humans. In this demo, Box Hubs, Box AI, and Box MCP power an agent-accessible knowledge vault for a vendor risk workflow. Curated knowledge. Permission-aware access. Human review. Reusable organizational memory. Watch the demo 👇
English
2
4
17
950