Cassidy Agents

Turn your business knowledge into AI Agents anyone can build

Create Agents in minutes with natural language—no code, no technical skills required. Let the people closest to the work build the AI that supports it. Grounded in your sources, trained on your brand, deployed where you work.
Cassidy insurance workflow automation platform interface
/ Trusted by the world's leading organizations
1
Describe
Describe your Agent
Tell Cassidy your Agent’s purpose in plain language. Define what it does and who it helps.
2
Improve
Give it context
Connect knowledge, set guidelines, and add tools. Configure your Agent with what it needs to get it right.
3
Deploy
Deploy to your teams
Launch to Slack, Teams, or the browser. Agents are always available wherever work happens.
AI teammates anyone can build

Grounded in your business, not generic training data

Your Agents pull from the same sources your best people use—documents, wikis, transcripts, and more. Responses reflect your brand voice and cite the exact source. Pair your knowledge with the best AI models from OpenAI, Anthropic, and Google—and switch as better ones arrive.

From idea to Agent without writing a line of code

Meet your AI building partner. Cassidy's Copilot helps you configure Agents by working alongside you—refining prompts, suggesting structure, and dialing in the details. Start from templates or build from scratch. No developers, no delays, no handoffs.
No-code building

Agents that reason, search, and execute with human-level quality

Cassidy Agents go far beyond chat. They can search the web, read your Knowledge Base, analyze data, and trigger Workflows across your apps. Set instructions so every Agent behaves exactly as you'd expect—consistent, accurate, on-brand.

Embed Agents across your existing tech stack

Get answers in Slack, Teams, or Google Chat without pinging a teammate. Draft in Word, respond in Outlook, analyze in Excel. Cassidy Agents live inside the tools your team uses every day.

Additional ways to customize, control, and scale your Agents

Integration tools
Chat with live data from Salesforce, HubSpot, Airtable, and more—right inside your Agent conversations
Version & chat history
Monitor past chats, publish updates to improve performance, and roll back changes when needed
Sharing & permissions
Control who can view, use, edit, or deploy each Agent—from org-wide to private
Call Workflows
Trigger multi-step Workflows directly from a conversation to take action across your stack
Data analysis
Upload spreadsheets and let Agents analyze, interpret, and visualize your data
Brand voice
Train Agents on your style guides and sample content so every response sounds like you

Real use cases powered by Cassidy’s Agents

Automate the critical and the mundane work that keeps your best people from focusing on what only they can do.
Meeting prep briefs
Builds client meeting briefs from past calls, CRM records, and project data so every meeting starts with full context
Marine Cargo Underwriting Assessment
Checks commodities, values, and trade routes against underwriting criteria and researches vessel and shipowner loss history.
Searchable Deal Memory
Ask about any deal and get cited answers on past calls, next steps, buyers, and open MEDDICC gaps without rewatching recordings.
Technical Product Q&A
Field sales teams answer technical product questions on the spot from spec sheets and product documentation.
Client Deliverables
Turns coverage, claims activity, and last year’s report into an editable stewardship report or proposal deck in your firm’s template.
RFP Gap and Risk Review
Flags missing info, unmet requirements, risky terms, and items that need legal or executive sign-off in any incoming RFP.

Connect to the tools your team already uses

Pull context from anywhere. Take action everywhere.
Deploy where your team works.
Cassidy  /  OneDigital
/ Featured case study

Secure, governed, and ready for enterprise

Cassidy supports enterprise security, privacy, and governance requirements, with controls for identity, access, data protection, and organizational oversight.
SOC 2 type II
Attested
GDPR
Compliant
HIPAA
Compliant
CASA
Validated
No model training on your data
Your information stays private and is never
used for training
Single sign-on (SSO)
Connect your identity provider for secure,
centralized access
Advanced RBAC user permissions
Fine-grained control over access across
teams and roles
Advanced data security
Row-level security and granular access controls protect against unauthorized access
Choose your model
Select from leading models from OpenAI,
Anthropic, and Google
Organization-wide instructions
Set guardrails and rules that apply across every Agent and Workflow

FAQ

Find answers to common questions about the platform, security, and getting started. Still have questions? Talk to our team!
Is my data used to train AI models?

No. Your data stays private. Cassidy never uses your Knowledge Base content or Agent conversations to train AI models—it's used solely to provide context for your Agents and Workflows. All data is encrypted in transit and at rest.

Which AI models do Agents use?

Cassidy supports leading models from OpenAI, Anthropic, and Google. You choose the best model for each Agent based on the task—whether it's writing, research, or complex reasoning. As new models are released, they're available in your workspace so your Agents stay current without rebuilding.

Can I control who has access to specific Agents?

Yes. Cassidy supports granular, role-based permissions so you can control which users or teams can view, use, edit, or deploy specific Agents. Share an Agent org-wide, limit it to a department, or keep it private. Access controls also extend to knowledge—Agents only retrieve information users are authorized to see.

Where can I deploy Agents?

Anywhere your team already works. Deploy to Slack, Microsoft Teams, Google Chat, or embed directly on your website. Access Agents via Chrome or Edge extensions, or integrate through the API for custom applications. Agents also work inside Microsoft Word, Excel, and Outlook—both online and desktop versions—so your team gets answers and takes action without switching tools or breaking focus.

What can Agents do beyond answering questions?

Agents reason through complex, multi-step requests and take real action. They can search the web for real-time information, read and analyze documents from your Knowledge Base, process data in spreadsheets, and trigger Workflows across your connected apps. You define what tools and actions each Agent has access to—so they do exactly what you need, nothing more.

How do Agents stay accurate and on-brand?

Agents pull from your Knowledge Base and cite their sources, so every response is traceable to your actual business knowledge. Citations are deep-linked—your team can click through to see the exact source in context. You can also train Agents on your brand voice by uploading style guides, sample content, or tone guidelines—so responses match how your company actually communicates. Set instructions, guidelines, and guardrails to ensure Agents follow your terminology and company policies consistently.

Do I need technical skills to build an Agent?

No. If you can describe what you need, you can build it. Cassidy's Copilot works alongside you—helping you configure prompts, connect knowledge, and refine behavior using plain language. Start from 80+ templates or build from scratch. No code, no developers, no IT tickets required.

What are Cassidy Agents?

Agents are context-aware AI teammates you can build for any role or function. They answer questions, complete tasks, and take action across your tools—grounded in your Knowledge Base and trained on your company's guidelines. Think of them as always-available experts: a sales rep who knows every deal, a support lead who's read every ticket, or an HR specialist who never forgets a policy. Deploy them to Slack, Teams, or the browser and they're ready to work alongside your team.

Move from idea to production with Cassidy