Cisco wished to make generative AI out there to each single worker in a safe, cost-optimized manner. To do that, Cisco IT developed an inner AI-powered assistant — purpose-built with safety — designed to raise how staff worok. Extra than simply one other software, Cisco’s inner AI assistant drives important effectivity and frictionless experiences for workers – with 73% of customers reporting elevated productiveness and a mean time financial savings of 5 hours per week.
As AI instruments like ChatGPT emerged within the market, we noticed each alternative and danger. Whereas Cisco acknowledged the transformative energy of AI and the outcomes these instruments may allow for our group, the growing utilization of public AI options additionally raised vital security and safety considerations for enterprises.
Seven in ten executives consider generative AI within the enterprise introduces new safety dangers for firm knowledge and are involved about staff inputting personally identifiable info (PII), consumer knowledge, or propriety info into engines like ChatGPT and Google Gemini (Salesforce, 2023). Counting on exterior AI companies may expose delicate Cisco knowledge to public coaching units — a danger we weren’t keen to take.
We wanted an answer that made generative AI out there to each single worker, regardless of the place they work from, whereas preserving Cisco knowledge safe and inner.
First steps to a safe answer
From day one, our precedence was preserving Cisco’s knowledge safe and in-house, not in another person’s coaching set. The unique structure Cisco’s Improvement Staff launched in April 2023 was designed to supply a safe atmosphere for workers to securely experiment with AI instruments. It was an enterprise-wide answer powered by Azure OpenAI fashions that maintained a dialog immediate retailer, audited prompts in actual time, and mechanically redacted personally identifiable info (PII) previous to processing.
Eight months after launch, the Cisco IT design group stepped in to reinforce consumer expertise and drive broader adoption. Initially, solely 30% of the workforce — primarily technical staff — have been utilizing the software. The objective was to make sure all staff, no matter their technical background, may benefit from it.
The group took a user-centric and data-driven strategy, conducting foundational and generative analysis to completely perceive what staff wanted from this software. By leveraging all of the out there knowledge about consumer ache factors, figuring out what staff have been looking for, and evaluating it with the highest areas of friction, the design group constructed out key use instances for the assistant. These included options to assist staff brainstorm, code, translate, generate content material, study Cisco merchandise, and extra — finally lifting the load of on a regular basis work.
This analysis revealed that the primary factor staff have been in search of was IT help — which means the true potential of Cisco’s inner AI assistant may very well be unlocked via ingesting Cisco knowledge. This grew to become the very best precedence.
Shifting ahead to help staff
We began by ingesting Cisco Individuals and Communities and Assist Zone knowledge (articles, web sites, and studies) into the software. We had Retrieval Augmented Technology (RAG) options constructed for Cisco.com and SalesConnect (inner content material portal for all gross sales assets) purposes earlier. The identical capabilities have been added to the interior AI assistant as nicely to gauge the wants of gross sales customers — a target market our group wished to handle.
With this high-quality Cisco knowledge ingested within the software, staff can use AI for help case troubleshooting, artistic writing, knowledge evaluation, questions, and even technical duties like community monitoring and configuration. It may well additionally streamline the onboarding course of for brand spanking new hires by supporting laptop computer or cell phone setup and answering questions on expense studies.
Establishing an ongoing working mannequin
Cisco’s inner AI assistant was constructed for fast integration, sturdy safety, and actionable insights, all at a world scale. That is supported by an ongoing working mannequin the place our group repeatedly displays consumer suggestions and delivers options with agility, creating an iterative, full-circle course of.
To design an inner assistant greatest fitted to Cisco’s international workforce, we developed a layered structure round these parts:
- AI agent, MCP, and enterprise search platform: The AI Agent and Mannequin Context Protocol (MCP) platform hosts all of the AI brokers and MCP servers developed utilizing open-source AI frameworks. Its modular, plug-and-play structure provides the Enterprise AI/ML engineering group the power to onboard new AI brokers and search purposes with out operational overhead. The platform additionally supplies LLM-as-a-service and RAG-as-a-service providing to over 4300+ groups throughout Cisco.
- Enterprise AI agent registry and MCP registry: This registry permits staff to register and join all distant AI brokers and distant MCP servers developed by groups throughout the enterprise with standardized agent and MCP safety, agentic protocols and entitlements in order that staff can securely entry this related agentic mesh from the interior assistant.
- Hybrid multi-cloud mannequin and AI agent orchestration: Utilizing a federated strategy, our inner AI assistant connects to a number of Cisco AI brokers and main AI fashions resembling Azure OpenAI, Claude, Google Gemini and Cisco’s inner massive language mannequin — Deep Community Mannequin. The platform mechanically routes every request to one of the best out there AI mannequin for deployments primarily based on workload, latency, reliability, and use-case. This ensures customers at all times get quick, correct outcomes.
- Constructed-in safety, knowledge governance, and observability: Safety is woven into each layer of the software, guaranteeing our office stays resilient in opposition to evolving threats whereas enabling innovation. Cisco’s AI Protection guardrails are used to scan consumer prompts and MCP server instruments for malicious code and hidden or neglected threats.
- Superior knowledge operations and AI-driven enterprise affect: Area particular AI brokers have been developed to allow clever automation of enterprise processes by leveraging AI prepared enterprise knowledge.
This platform, alongside our ongoing working mannequin, allows us to deploy new options and effectively and constantly refine our roadmap — guaranteeing we keep on the forefront of AI innovation.
“Designed with a security-first mindset, our inner AI assistant has highly effective guardrails that mechanically detect and redact delicate knowledge earlier than it’s despatched to a public AI mannequin — giving our staff an clever associate they will belief.” – Sujith Joseph, Principal Engineer, Cisco
Driving larger effectivity throughout our workforce
Since its launch, Cisco’s inner AI assistant has dealt with greater than 21 million interactions, serving 100,000+ customers throughout our international workforce.
Cisco’s inner AI assistant is greater than only a chatbot. It has shortly grow to be essentially the most broadly used AI software at Cisco, facilitating a mean of 156,000 each day interactions and driving larger effectivity as 73% of customers reported elevated productiveness and a mean time saved of 5 hours per week.
That is made doable by options and developments at the moment out there within the software, together with:
- Entry to the most recent AI fashions
- AI brokers and LLM orchestration
- Knowledge and picture evaluation
- PowerPoint technology
- Private RAG (RAG on consumer’s private knowledge in OneDrive, and so forth.)
- Limitless Deep Analysis (Analysis studies utilizing Cisco inner knowledge and internet knowledge)
- Knowledge evaluation AI agent
- Enterprise AI Agent and Connector Registry (Integration of distant AI brokers and MCP servers)
Classes realized alongside the best way
AI instruments are solely ever as dependable as the information they’re skilled on. One problem we confronted early on was guaranteeing that we have been solely ingesting clear, high quality, and structured knowledge into the software. Something much less may actually lower the standard of the responses and the usefulness of the answer. The Dev Staff performed continuous and rigorous testing to assist be sure that the assistant doesn’t hallucinate and constantly supplies updated and correct responses.
Moreover, driving adoption throughout our international workforce offered challenges, particularly amongst AI-cautious or non-technical staff. Regardless of the answer’s approval for extremely confidential Cisco knowledge, there was a degree of apprehension surrounding its use and potential misuse. This spurred an effort to upskill our staff by creating efficient demos, enablement assets, and growing basic AI consciousness.
Our user-driven, design-led strategy was essential for navigating these challenges and allowed us to construct a software that caters to the wants of our various workforce. We proceed to finish generative analysis to grasp how our staff use the AI assistant and the way it will resonate with them of their day-to-day work.
From product to platform
AI is reworking industries at an unprecedented fee. Whereas most organizations acknowledge the pressing have to undertake AI applied sciences and instruments, many aren’t totally ready to successfully leverage AI. At Cisco, we all know that AI is not a futuristic idea. We’re repeatedly innovating internally — creating AI-powered instruments, securing them, and finally empowering our staff to do their greatest work day-after-day.
Constructing on its sturdy basis, Cisco is targeted on evolving the AI assistant from a product right into a dynamic platform, empowering staff to have a hand in shaping their AI expertise. The Agent Registry and upcoming Agent Builder options will allow customers to tailor the software to greatest match their wants at work. Not solely will this improve the general usefulness and worth of the AI assistant, however it is going to additionally assist upskill our workforce, constructing a extra technically proficient and AI-fluent worker inhabitants.
As a dedication to Cisco’s funding in AI, the Cisco Automation and AI Middle was not too long ago created to concentrate on increasing the adoption of AI. Wanting forward, the imaginative and prescient for the interior AI assistant is to grow to be a dependable, always-on associate that may seamlessly combine into each workflow, anticipate wants, and allow groups to concentrate on what issues most.
The interior AI assistant isn’t simply altering how we work at Cisco; it’s a cornerstone of constructing a future-proofed office that’s safe, adaptable, and prepared for what’s subsequent.
Extra assets:
Report: 77% of Staff Share Firm Secrets and techniques on ChatGPT Compromising Enterprise Insurance policies