Skip to main content
NIRA AI Research Assistant
NIRA (NimbleBrain Research Assistant) is your AI copilot that transforms how you build automations. Simply describe what you want to accomplish in plain English, and NIRA handles the complexity of configuring tools, orchestrating workflows, and deploying playbooks.

What is NIRA?

NIRA is an intelligent assistant built into NimbleBrain Studio that understands your business requirements and automatically builds working automations. Instead of manually configuring playbooks, selecting MCP servers, and writing instructions, you have a conversation with NIRA about what you need—and it does the rest.

🗣️ Conversational

Describe your automation needs in natural language—no technical expertise required

🧠 Intelligent

Understands context, selects the right tools, and structures complex multi-step workflows

⚡ Fast

Build automations in minutes that would take hours to configure manually

🔄 Iterative

Refine and adjust automations through continued conversation

Why Use NIRA?

Traditional Playbook Building vs. NIRA

TaskManual ApproachWith NIRA
Understanding RequirementsTranslate business needs to technical specsDescribe needs in plain English
Tool SelectionBrowse catalog, research capabilitiesNIRA auto-selects optimal tools
ConfigurationWrite instructions, set parametersNIRA generates configuration
IntegrationConnect multiple tools manuallyNIRA orchestrates multi-tool workflows
Time to DeployHours or daysMinutes
Perfect for non-technical users! NIRA makes automation accessible to everyone on your team, not just developers.

Key Features

Conversational Automation Building

Chat naturally with NIRA about what you want to automate. No need to understand technical details—just explain your business process.

Intelligent Playbook Generation

NIRA analyzes your requirements and automatically generates complete playbooks with proper tool selection and workflow logic.

Automatic Configuration

NIRA handles the technical details: selecting MCP servers, structuring instructions, and setting optimal parameters.

Multi-Tool Orchestration

NIRA seamlessly coordinates multiple MCP servers to accomplish complex, multi-step automations.

Natural Language Understanding

Understands context, business terminology, and implicit requirements to build automations that truly match your needs.

Guided API Setup

NIRA identifies required credentials and walks you through adding API keys for each tool.

How NIRA Works

Building an automation with NIRA is simple:
1

Describe Your Automation

Tell NIRA what you want to accomplish in plain English. Be as detailed or high-level as you like—NIRA will ask clarifying questions if needed.Example: “I need a daily report that shows all new support tickets from Zendesk, categorizes them by priority, and posts a summary to our #support Slack channel every morning.”
2

NIRA Analyzes & Designs

NIRA understands your requirements and:
  • Selects the appropriate MCP servers from the catalog
  • Designs the workflow structure
  • Generates playbook instructions
  • Identifies required API credentials
3

Add Your API Keys

NIRA prompts you for the necessary API keys and credentials. Simply add them when requested—NIRA knows exactly what’s needed.
Your API keys are encrypted and stored securely. They’re never visible to NIRA or logged anywhere.
4

Review the Playbook

NIRA shows you the generated playbook with:
  • Selected MCP servers
  • Workflow instructions
  • Configuration parameters
  • Expected behavior
You can ask NIRA to make adjustments before deploying.
5

Click GO to Deploy

Once you’re satisfied, click the GO button and NIRA deploys your automation immediately. Your playbook is ready to run!
It’s that simple! Most automations are built and deployed in under 5 minutes.

Getting Started with NIRA

Accessing NIRA

  1. Navigate to your NimbleBrain Studio workspace
  2. Look for the NIRA button in the main navigation or dashboard
  3. Click to open the NIRA chat interface
NIRA chat interface

Your First Automation

Try this simple automation to get familiar with NIRA:
1

Open NIRA

Click the NIRA button in Studio
2

Say Hello

Start with: “Hello NIRA, I’d like to create my first automation”
3

Describe Something Simple

Try: “Send me a weather forecast for San Francisco every morning at 7am via email”
4

Follow NIRA's Guidance

NIRA will guide you through adding the necessary API credentials and reviewing the playbook
5

Deploy

Click GO when ready, and you’re done!

Use Cases

Business Operations

Request: “Generate a daily sales report from Salesforce showing closed deals, total revenue, and top performers. Send it to #sales-team on Slack every morning at 9am.”What NIRA Does:
  • Installs and configures Salesforce MCP server
  • Installs Slack MCP server
  • Creates playbook to query yesterday’s deals
  • Formats data into readable summary
  • Schedules daily execution
Request: “When a new high-priority ticket is created in Zendesk, notify the on-call engineer via PagerDuty and post details in #urgent-support Slack channel.”What NIRA Does:
  • Sets up Zendesk webhook integration
  • Configures PagerDuty alerting
  • Creates Slack notification workflow
  • Implements priority filtering logic
Request: “Check weather forecast for our warehouse locations. If severe weather is predicted, send alerts to logistics team and update delivery schedules in our system.”What NIRA Does:
  • Integrates weather API for multiple locations
  • Creates alert logic based on severity
  • Configures email/SMS notifications
  • Sets up system API updates

Data & Analytics

Request: “Combine data from Google Analytics, Stripe, and HubSpot to create a weekly executive dashboard showing traffic, revenue, and conversion rates.”What NIRA Does:
  • Connects to all three platforms
  • Aggregates and correlates data
  • Generates formatted report
  • Schedules weekly delivery
Request: “Monitor our database for unusual query patterns. If response times spike above 2 seconds, investigate and send a diagnostic report to #engineering.”What NIRA Does:
  • Sets up database monitoring
  • Implements threshold detection
  • Creates diagnostic data collection
  • Configures alerting workflow

Developer Workflows

Request: “When a pull request is opened in GitHub, run our test suite, check code coverage, and post results as a comment. Auto-approve if all checks pass and coverage improves.”What NIRA Does:
  • Sets up GitHub webhook
  • Configures test execution
  • Implements coverage analysis
  • Creates conditional approval logic
Request: “After successful merge to main branch, deploy to staging, run smoke tests, and if everything passes, notify team in Slack with deployment summary.”What NIRA Does:
  • Creates deployment pipeline
  • Integrates testing framework
  • Sets up Slack notifications
  • Implements conditional logic

Example Conversations

You: "Create a daily report that pulls sales data from Salesforce and sends it to our #sales-team Slack channel every morning at 9am"

NIRA: "I'll create a playbook that:
1. Connects to Salesforce using the Salesforce MCP server
2. Queries yesterday's closed deals and calculates total revenue
3. Formats the data as a summary report with top performers
4. Sends to Slack channel #sales-team at 9:00 AM daily

You'll need to provide:
- Salesforce API credentials (Consumer Key and Secret)
- Slack workspace token

Ready to add these credentials?"

You: "Yes, let's set it up"

NIRA: "Great! First, let's add your Salesforce credentials..."

Writing Effective Automation Requests

Be Specific About Outcomes

Good: “Send me a daily summary of GitHub pull requests that need review, organized by priority, every morning at 9am”
Vague: “Do something with GitHub”

Include Timing Requirements

Good: “Check for new invoices in Stripe every hour and sync them to QuickBooks immediately”
Missing Info: “Sync Stripe invoices to QuickBooks”

Mention All Systems Involved

Good: “When a support ticket is marked urgent in Zendesk, create a task in Asana and notify the team lead via Slack”
Incomplete: “Do something when tickets are urgent”

Specify Conditions and Filters

Good: “Monitor Twitter for mentions of our brand with negative sentiment and create Zendesk tickets for customer service follow-up”
Too Broad: “Monitor Twitter mentions”
Don’t worry about being too detailed! NIRA will ask clarifying questions if it needs more information.

Best Practices

Begin with a basic version of your automation and ask NIRA to add complexity:
  1. “Create a daily sales report from Salesforce”
  2. Once working: “Add revenue trends compared to last week”
  3. Then: “Include top 3 performing sales reps”
  4. Finally: “Send to executives in PDF format”
This iterative approach ensures each piece works before adding more.
NIRA understands business processes better than technical jargon:Good: “When a customer’s trial ends, send them pricing information”Unnecessarily Technical: “Trigger webhook on trial_end event to execute email_send function with pricing payload”
Providing context helps NIRA build better automations:Better: “We need to track inventory levels because we’ve had stockouts. Alert purchasing when items drop below 20 units so they can reorder in time.”Basic: “Alert when inventory is below 20 units”The context helps NIRA include relevant details in alerts.
After NIRA builds your automation, test it:
  1. Run the playbook manually first
  2. Check that outputs match expectations
  3. Verify notifications go to the right places
  4. Ask NIRA to adjust if needed
NIRA knows which MCP servers work well together. Ask for suggestions:
  • “What’s the best way to automate customer onboarding?”
  • “How can I monitor our application performance?”
  • “What integrations are available for e-commerce?”

When to Use NIRA vs. Manual Playbooks

Use NIRA When:

You’re new to automation or NimbleBrain Studio
You need to build something quickly
You’re not sure which MCP servers to use
Your automation involves multiple systems
You want to describe requirements in business terms
You’re prototyping or experimenting with ideas

Use Manual Playbooks When:

  • You need very specific, custom instructions
  • You’re building a template for others to reuse
  • You want fine-grained control over every parameter
  • You’re an experienced user who knows exactly what you need
You can always start with NIRA and then refine manually if needed. NIRA generates standard playbooks that you can edit.

Frequently Asked Questions

NIRA currently works best with English, but can understand other major languages. Responses are always in English.
No. NIRA only has access to:
  • Your workspace configuration
  • Available MCP servers in the catalog
  • Playbook templates and examples
NIRA never sees your actual data, API responses, or execution results.
NIRA will ask clarifying questions to better understand your needs. If it still can’t help, it will suggest breaking down the request or provide guidance on how to rephrase.
Yes! NIRA generates standard playbooks that you can view, edit, and customize just like manually-created ones.
NIRA is included with your NimbleBrain Studio subscription. You only pay for playbook executions and MCP server usage, just like manual playbooks.
Absolutely! If a playbook isn’t working as expected, describe the issue to NIRA and it will help diagnose and fix problems.
NIRA remembers the context within a conversation session. Over time, patterns in your workspace (like frequently used MCP servers) help NIRA make better suggestions.

Advanced Features

Context-Aware Suggestions

NIRA learns from your workspace:
  • Suggests MCP servers you’ve used before
  • Remembers your notification preferences
  • Adapts to your organization’s naming conventions
  • Understands your scheduling patterns

Workflow Optimization

NIRA can optimize existing playbooks: Say: “Make my sales report playbook faster” NIRA will analyze the playbook and suggest optimizations like:
  • Parallel tool execution
  • Reduced API calls
  • Caching strategies
  • Simplified logic

Building Agents with NIRA

When your automation requires multiple steps or data sources, NIRA will suggest creating an Agent:

Example:You: “I need to pull sales data from Salesforce, get market trends from Finnhub, analyze both with AI, and send a report to Slack every Monday morning”NIRA: “This requires multiple data sources working together. I recommend creating an Agent with 4 playbooks:
  1. Salesforce Data - Pull weekly sales data
  2. Market Trends - Fetch relevant market data
  3. AI Analysis - Analyze combined data and generate insights
  4. Slack Report - Format and send to your team
These will run sequentially on Mondays at 9 AM. Would you like me to set that up?”
NIRA handles the complexity of:
  • Determining which playbooks are needed
  • Setting up the execution order (sequential or parallel)
  • Configuring data passing between playbooks
  • Scheduling the agent to run automatically
Ready for multi-step workflows? Learn how Agents coordinate multiple playbooks → Learn more about Agents

Limitations

Current Limitations:
  • NIRA cannot access MCP servers that aren’t in the NimbleBrain registry
  • Very complex custom logic may require manual refinement
  • NIRA cannot directly modify running playbooks (you must redeploy)
  • Conversation context is limited to the current session

Tips for Success

  1. Be conversational - Talk to NIRA like you would a colleague
  2. Provide examples - Show NIRA what output you want
  3. Ask questions - NIRA can explain how things work
  4. Iterate - Refine automations through conversation
  5. Test early - Deploy simple versions first, then enhance
  6. Give feedback - Tell NIRA if results aren’t what you expected

Get Started with NIRA Today

Ready to build your first automation? Click the NIRA button in your Studio workspace and start a conversation!
Pro Tip: Start with “Hi NIRA, show me what you can do” to see example automations and get inspired!