Ché Wijesinghe

Today we are launching a new Cape product! 🚀 DirectiveIQ is the manifestation of months of customer-driven engineering to solve a very complex business problem to automate money movements for financial institutions. For MCP early access get in touch at info@cape.ai.

Excited to join @DivesTech from @Wedbush next Tuesday June 17th at 11am ET in a fireside chat to discuss how Cape.ai is enabling Financial Services companies to transform documents into actionable AI insights! 🔥 Register here 👉 TMTevents@wedbush.com

Cape puts AI to work. It's software combines LLM-powered Search across all of your data, autogenerating powerful Agentic Workflows to drive business outcomes. Get in touch to learn more! lnkd.in/e5fzpEz5 #work, #ai, #LLMs, #enterprise, #data, #search, #workflows

With Cape's #AI powered Knowledge Retrieval capabilities, connect and #search across all of your hashtag#enterprise datasources with your choice of hosted, or on-premise #LLMs. 🧠 🔥 Schedule a demo to learn more at capeprivacy.com/contact 🗓

There are very real #DataPrivacy benefits when deploying Cape's #AI on-premise/VPC, even when using a hosted model (e.g. GPT). Data often needs to be loaded into a vector store, which Cape does all locally and behind the firewall (embeddings, storage, and search).

We are #hiring! If you are an experienced technical engineer looking for a challenging role, working with a great #team and the latest #ai technologies, please take a look at our open positions! lnkd.in/eHTznXUX

With Cape's #AI Workflows and Knowledge Retrieval capabilities, your #compliance and #riskmanagement teams can significantly reduce their manually intensive reporting processes (including #KYC, #CDD, #EDD, #SOC). Integration to all of your data sources, privately and securely!

Nobody can compete with OpenAI. If you want to integrate a Large Language Model with your application, OpenAI wins every day. But the problem is that companies can't justify using OpenAI's API with their customer's private information. Here is a solution: The @capeprivacy team shared with me their new API. They redact private information from your content, so you don't have to worry about it. There are two ways you can use the API: First, you can de-identify your content. De-identification removes any Personally Identifiable Information from the input. You can use the redacted content with OpenAI's API or any other model. Second, you can use their Completions API, which handles de-identification and re-identification. It removes sensitive information, sends the redacted query to OpenAI, and re-identifies the content. The attached image shows how simple it is to use the API. If you are working with any sensitive information, this is a must. By the way, @capeprivacy tells me they detect and redact 50 types of sensitive entities, like emails, names, credit cards, and addresses. They use secure enclaves to do this so they can’t see any of the information. Here is a link to their documentation: docs.capeprivacy.com/getting-starte… Thanks to @capeprivacy for sponsoring this post.

Cape Privacy Analytics gives users important insights as to what sensitive data is being used with multiple #LLMs including #GPT, #Claude, #Cohere and #Llama2. Try it for yourself at app.capeprivacy.com

“Nobody can compete with Open AI” 👀 Very bold statement at this stage. As for @capeprivacy - great product and fantastic work here. Forward outlook will be that many organizations in Healthcare, Finance and Insurance will want to implement. 💡

We're excited to announce new features to the Cape API including support for multiple LLMs, secure vision and voice models, privacy analytics to monitor and measure confidential data. Learn more at capeprivacy.com #openai #anthropic #meta #azure #cohere #llms

Looking to use an LLM but concerned about the sensitivity of your data? The Cape API keeps your data private while using the LLM of your choice. Here's how you can get started:

The first fully confidential LLM!!

Get started with our new feature: docs.capeprivacy.com/tutorials/cape… Plus, access GPT 4, Claude 2, and Cohere Chat in one place, with auto-masking for sensitive information (PII, PCI, and PHI). Dive into the full documentation: capeprivacy.redoc.ly

Exciting update! 🎉 The Cape API now includes a confidential Llama 2 7B Chat, securely hosted within a dedicated enclave for added privacy. Enclaves preserve the confidentiality of both prompts and model responses during processing, making them invisible to all.

Excited to be featured in TheSequence today thesequence.substack.com/p/the-sequence… Thanks @jrdothoughts for the opportunity to talk LLM Privacy and our work at @capeprivacy

People may see something like this and think "couldn't you just run the computation client-side?", and that's true, but it's missing the point.. completely confidential server-side is a game changer. AND it's all code.. this doesn't require any special hardware

The Cape API now supports GPT-4 with 32k context!! This is deployed to Azure w/ 0 data retention (as opposed to 30 day data retention w/ OpenAI). Using Cape, all prompts are automatically de-identified of sensitive personal, financial, and health data. #tag/Azure-OpenAI-Completions" target="_blank" rel="nofollow noopener">api.capeprivacy.com/v1/redoc#tag/A…

People don't trust ChatGPT. What happens to the information you paste into their chat interface? Are you comfortable sharing sensitive data with them? Here is an excellent idea to use ChatGPT while keeping your information secure:

The team @capeprivacy showed me CapeChat, their solution to keep your information private: chat.capeprivacy.com It's pretty cool! They redact private information from your chats and documents and never show it to ChatGPT. ChatGPT's power without risking sensitive data.