Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

.LangChain Deep Agents + a VFS sandbox + Box AI = vendor risk analysis that runs end to end in one command. PDFs go in. Three sandboxed subagents reason over them in parallel. A structured risk report — with metadata on every source file and a review task —... show more

Box

78,585 subscribers

429,137 views • 3 months ago •via X (Twitter)

News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

If your contracts don’t fit in a prompt window, your AI has to work at document scale. See how Google’s Gemini 3 Pro + Box AI API extract contract metadata and run multi-file risk analysis with the Box AI Ask API using your own governance docs.

If your contracts don’t fit in a prompt window, your AI has to work at document scale. See how Google’s Gemini 3 Pro + Box AI API extract contract metadata and run multi-file risk analysis with the Box AI Ask API using your own governance docs.

Box

30,545 views • 9 months ago

AI agents need a structured place to do their work and access relevant content. A filesystem provides a clear, navigable way to manage that context. Here’s how Box can back that abstraction in LangChain Deep Agents — preserving the simplicity of the filesystem interface while adding enterprise-grade security, permission controls, version history, and collaboration at the storage layer. Explore our implementation:

AI agents need a structured place to do their work and access relevant content. A filesystem provides a clear, navigable way to manage that context. Here’s how Box can back that abstraction in LangChain Deep Agents — preserving the simplicity of the filesystem interface while adding enterprise-grade security, permission controls, version history, and collaboration at the storage layer. Explore our implementation:

Box

1,018,021 views • 6 months ago

The Box CLI turns Box into a cloud file system for agents. In our demo, Claude Code uses it to: → extract metadata from docs → write it back to files → generate a summary spreadsheet All via simple prompts, directly in Box. npm install --global @box/cli

The Box CLI turns Box into a cloud file system for agents. In our demo, Claude Code uses it to: → extract metadata from docs → write it back to files → generate a summary spreadsheet All via simple prompts, directly in Box. npm install --global @box/cli

Box

720,513 views • 5 months ago

🆕SpaceXAI just launched Grok Bot, a personal AI assistant built for complex knowledge work. Connected to Box through the Box MCP server, Grok Bot can work across your governed enterprise content immediately, across any workflow and any industry. In our demo it tackles a credit committee review. Works across credit agreements, borrower financials, diligence materials, collateral documentation, and risk assessments. Reconciles key terms. Flags credit risks and inconsistencies. Produces a source-cited brief. Saves it back to Box with structured deal metadata applied. All your content. Any AI agent. Watch here. 👇

🆕SpaceXAI just launched Grok Bot, a personal AI assistant built for complex knowledge work. Connected to Box through the Box MCP server, Grok Bot can work across your governed enterprise content immediately, across any workflow and any industry. In our demo it tackles a credit committee review. Works across credit agreements, borrower financials, diligence materials, collateral documentation, and risk assessments. Reconciles key terms. Flags credit risks and inconsistencies. Produces a source-cited brief. Saves it back to Box with structured deal metadata applied. All your content. Any AI agent. Watch here. 👇

Box

1,399,288 views • 14 days ago

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.

Box

316,999 views • 13 days ago

GPT-5.6 Sol is a breakthrough in complex reasoning and data analysis. Here, it analyzes hundreds of pages across a lending deal, reconciles terms across agreements, financials, diligence, collateral, and risk materials, flags issues, and saves a source-cited report to Box.

GPT-5.6 Sol is a breakthrough in complex reasoning and data analysis. Here, it analyzes hundreds of pages across a lending deal, reconciles terms across agreements, financials, diligence, collateral, and risk materials, flags issues, and saves a source-cited report to Box.

Box

780,198 views • 1 month ago

.Manus and Box CLI working together on a real workflow. Here's what that looks like. Your vendor documents like SOC2 reports and DPAs serve as the source of truth. HubSpot pulls in deal context. Manus analyzes everything, identifies risks and gaps, and saves a structured summary with recommended next steps right alongside the original files. Box is the end to end secure AI file system improving user productivity for real-life workflows. Watch here. 👇

.Manus and Box CLI working together on a real workflow. Here's what that looks like. Your vendor documents like SOC2 reports and DPAs serve as the source of truth. HubSpot pulls in deal context. Manus analyzes everything, identifies risks and gaps, and saves a structured summary with recommended next steps right alongside the original files. Box is the end to end secure AI file system improving user productivity for real-life workflows. Watch here. 👇

Box

1,338,225 views • 4 months ago

The base64 approach to binary file transfer is corrupted at 175KB and fails entirely at 20MB. The Box MCP server handles both in under 30 seconds. See it in action working end to end in Anthropic's Claude. Summarize an annual report PDF, add a key takeaways page, and re-upload as a new version. Signed URLs. No binary data in the LLM context. Full audit trail. Watch here. 👇

The base64 approach to binary file transfer is corrupted at 175KB and fails entirely at 20MB. The Box MCP server handles both in under 30 seconds. See it in action working end to end in Anthropic's Claude. Summarize an annual report PDF, add a key takeaways page, and re-upload as a new version. Signed URLs. No binary data in the LLM context. Full audit trail. Watch here. 👇

Box

203,602 views • 2 months ago

With Codex and Box, you can automate a lot of knowledge worker tasks. A single file in Box turns into structured data, tracked work in Linear, and a live update in Slack. No handoffs. No follow-ups. Just flow. Watch it in action.👇

With Codex and Box, you can automate a lot of knowledge worker tasks. A single file in Box turns into structured data, tracked work in Linear, and a live update in Slack. No handoffs. No follow-ups. Just flow. Watch it in action.👇

Box

6,291,433 views • 4 months ago

Your contract review agent can read an NDA and summarize the key terms. But ask it "what are the risky clauses?" and you get a different answer every time. Neither gets solved by a bigger model. Here's a deep dive of the Box AI Extract NDA risk workflow. The agent calls POST /2.0/ai/extract_structured with a fixed five-field schema: governing law, term, termination, confidentiality period, liability cap. Confidence scores and source references included. A transparent rule set scores each clause automatically. The Deal Risk Summary saves back to Box as a companion file alongside the source document. Same output shape every time, regardless of how the document is written. Extract, don't prompt.

Your contract review agent can read an NDA and summarize the key terms. But ask it "what are the risky clauses?" and you get a different answer every time. Neither gets solved by a bigger model. Here's a deep dive of the Box AI Extract NDA risk workflow. The agent calls POST /2.0/ai/extract_structured with a fixed five-field schema: governing law, term, termination, confidentiality period, liability cap. Confidence scores and source references included. A transparent rule set scores each clause automatically. The Deal Risk Summary saves back to Box as a companion file alongside the source document. Same output shape every time, regardless of how the document is written. Extract, don't prompt.

Box

508,031 views • 21 days ago

With OpenAI's GPT-5 now available in Box AI Studio, transform mixed invoices – PDFs, smartphone photos, handwritten scans – into perfectly structured metadata to push straight into any workflow. Automate extraction, tagging, and downstream syncing of any unstructured document

With OpenAI's GPT-5 now available in Box AI Studio, transform mixed invoices – PDFs, smartphone photos, handwritten scans – into perfectly structured metadata to push straight into any workflow. Automate extraction, tagging, and downstream syncing of any unstructured document

Box

39,379 views • 1 year ago

AI agents can read any file the user has access to. That is a much larger surface than most security teams realize. Classification-based access policies in Box now give admins read access control for AI agents. Restrict which agents can read which content based on Box Shield classifications. Enforced automatically across every agent, regardless of which AI tool is making the request. This demo shows it in action.

AI agents can read any file the user has access to. That is a much larger surface than most security teams realize. Classification-based access policies in Box now give admins read access control for AI agents. Restrict which agents can read which content based on Box Shield classifications. Enforced automatically across every agent, regardless of which AI tool is making the request. This demo shows it in action.

Box

105,605 views • 28 days ago

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

Box

227,348 views • 6 months ago

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

Box

627,810 views • 4 months ago

🆕Google DeepMind's Gemini 3.7 Flash dropped this morning, and our evals showed it scored higher and ran about 37% faster than Gemini 3.6 Flash, with the largest gains on the most challenging analytical tasks. Here's how it performs on one of those tasks: private credit work. In this Box Agent demo, Gemini 3.7 Flash reviews 15 documents in a borrower package, catches an outdated leverage limit, applies the amended 5.50x threshold, corrects for $4M in restricted cash and a $1.5M unsupported add-back, flags a potential covenant exception at 5.58x, and saves a cited review back to Box for the portfolio team. Customers can use Gemini 3.7 Flash in Box AI Studio to build custom agents grounded in their enterprise content.

🆕Google DeepMind's Gemini 3.7 Flash dropped this morning, and our evals showed it scored higher and ran about 37% faster than Gemini 3.6 Flash, with the largest gains on the most challenging analytical tasks. Here's how it performs on one of those tasks: private credit work. In this Box Agent demo, Gemini 3.7 Flash reviews 15 documents in a borrower package, catches an outdated leverage limit, applies the amended 5.50x threshold, corrects for $4M in restricted cash and a $1.5M unsupported add-back, flags a potential covenant exception at 5.58x, and saves a cited review back to Box for the portfolio team. Customers can use Gemini 3.7 Flash in Box AI Studio to build custom agents grounded in their enterprise content.

Box

3,817,973 views • 12 days ago

Box AI integrates seamlessly with OpenAI's new o3 model. See how the Box AI API can extract invoice metadata in bulk and answer image questions 👀👇

Box AI integrates seamlessly with OpenAI's new o3 model. See how the Box AI API can extract invoice metadata in bulk and answer image questions 👀👇

Box

178,573 views • 1 year ago

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.

Box

1,693,466 views • 1 month ago

Grok 4.6 just dropped, and we put it to work on Box content immediately. Using Cursor and the Box MCP server, Grok reviewed six documents in a commercial property underwriting workspace. It found a $3.2M mismatch in insured values, an omitted $212K loss, stale loss runs, and a coastal location outside appetite. It also cleared apparent issues the evidence resolved. Then it saved a cited underwriting triage summary with a referral recommendation back to Box. Box MCP server lets teams use the models and agents they choose with secure, governed enterprise content.

Grok 4.6 just dropped, and we put it to work on Box content immediately. Using Cursor and the Box MCP server, Grok reviewed six documents in a commercial property underwriting workspace. It found a $3.2M mismatch in insured values, an omitted $212K loss, stale loss runs, and a coastal location outside appetite. It also cleared apparent issues the evidence resolved. Then it saved a cited underwriting triage summary with a referral recommendation back to Box. Box MCP server lets teams use the models and agents they choose with secure, governed enterprise content.

Box

1,285,787 views • 13 days ago

Your research agent can search the web in English. But the evidence that should shape your answer is in French film institute reports, Japanese trade publications, Brazilian creator communities, and Polish cinema data. That is not a model problem. It is a retrieval and orchestration problem. Neither gets solved by a bigger model. Here's a deep dive of the Temporal, OpenAI, and Box AI research agent we built. The agent plans multilingual queries, searches concurrently across four markets, synthesizes a cited master report, publishes localized briefs to Box with retry-safe versioning, and asks Box AI to compare the external findings against your internal governed content. End-to-end durable research.

Your research agent can search the web in English. But the evidence that should shape your answer is in French film institute reports, Japanese trade publications, Brazilian creator communities, and Polish cinema data. That is not a model problem. It is a retrieval and orchestration problem. Neither gets solved by a bigger model. Here's a deep dive of the Temporal, OpenAI, and Box AI research agent we built. The agent plans multilingual queries, searches concurrently across four markets, synthesizes a cited master report, publishes localized briefs to Box with retry-safe versioning, and asks Box AI to compare the external findings against your internal governed content. End-to-end durable research.

Box

34,452 views • 25 days ago

Work doesn’t happen in structured fields alone — it lives in contracts, forms, images, and documents. Box AI Agents help teams unlock critical insights from unstructured data, automate tasks, and move faster with agentic reasoning and enterprise context. Learn more:

Work doesn’t happen in structured fields alone — it lives in contracts, forms, images, and documents. Box AI Agents help teams unlock critical insights from unstructured data, automate tasks, and move faster with agentic reasoning and enterprise context. Learn more:

Box

1,019,240 views • 4 months ago