Skip to content
lindy-upgrade-migration logo

Lindy Upgrade & Migration

lindy-upgrade-migration

Manage Lindy agent configuration changes, platform updates, and migrations.

SKILL.md

Full skill instructions

Lindy Upgrade & Migration

Overview

Lindy is a managed platform — agents run on Lindy's infrastructure. "Upgrades" mean reconfiguring agents for new capabilities, migrating agents between workspaces, or adapting to platform changes. Key concern: agents with webhooks, Lindymail, and phone numbers require reconfiguration after migration.

Prerequisites

  • Admin access to source and target Lindy workspaces
  • Inventory of all agents, triggers, and integrations
  • Migration window scheduled for customer-facing agents

Instructions

Step 1: Inventory Current Agents

Document every agent before making changes:

Agent NameTrigger TypeActionsIntegrationsWebhook URLPhone #
Support BotEmail ReceivedGmail Reply, Slack NotifyGmail, SlackN/​AN/​A
Lead RouterWebhookSheets Update, Slack DMSheets, Slackhttps://public.lindy.ai/​...N/​A
Phone ScreenerCall ReceivedTransfer, Agent SendPhoneN/​A+1-555-0100

Step 2: Export Agent Configurations

For each agent, document:

  • Prompt: Copy full text from Settings > Prompt
  • Model: Which AI model is selected
  • Skills/​Actions: List all action steps and their configurations
  • Trigger filters: Copy filter conditions
  • Knowledge Base: Note all sources (files, URLs, integrations)
  • Memories: Export any persistent memories
  • Exit conditions: Copy all condition text

Step 3: Plan Migration Order

Phase 1: Internal-only agents (no customer impact)
  → Migrate, test, verify for 24-48 hours

Phase 2: Low-risk customer-facing agents (email triage, notifications)
  → Migrate during low-traffic window
  → Monitor for 24 hours

Phase 3: Critical agents (phone, live chat, lead routing)
  → Migrate with rollback plan ready
  → Keep old agent active in parallel for 48 hours

Step 4: Migrate Agent to New Workspace

Option A — Template sharing:

  1. In source workspace: Share agent as Template
  2. In target workspace: Import template
  3. Reconfigure integrations (OAuth tokens are NOT transferred)
  4. Re-authorize all connected services

Option B — Manual recreation:

  1. Create new agent in target workspace
  2. Paste saved prompt
  3. Recreate trigger with same configuration
  4. Re-add all actions and configure fields
  5. Upload knowledge base files
  6. Re-create memories

Step 5: Reconfigure Webhooks, Email, and Phone

These require special attention — they are NOT automatically transferred:

Webhooks:

  • New agent gets a NEW webhook URL
  • Update all calling systems with the new URL
  • Generate new webhook secret
  • Update all clients with new Bearer token

Lindymail (Lindy-assigned email addresses):

  • New agent gets a new Lindymail address
  • Update forwarding rules and any published email addresses

Phone numbers:

  • Phone numbers may need to be re-provisioned ($10/​month each)
  • Update IVR systems and published phone numbers
  • Test call quality and language settings

Step 6: Parallel Run & Cutover

Day 1-2: Both old and new agents active
  → Route test traffic to new agent
  → Compare task completion rates and output quality

Day 3: Gradual cutover
  → Redirect 50% of traffic to new agent
  → Monitor error rates and credit consumption

Day 4: Full cutover
  → Route 100% to new agent
  → Keep old agent paused (not deleted) for 7 days

Day 11: Cleanup
  → Delete old agent after 7-day safety window

Step 7: Verify Post-Migration

  • All triggers firing correctly
  • All actions completing successfully
  • Knowledge base returning relevant results
  • Webhook URLs updated in all calling systems
  • Phone numbers tested (inbound and outbound)
  • Credit consumption within expected range
  • Team members have correct access in new workspace

Common Migration Scenarios

Scenario: Consolidating Multiple Agents

When you have too many single-purpose agents:

  1. Identify agents with overlapping triggers
  2. Merge prompts into sections (use ## Billing, ## Technical, etc.)
  3. Add conditions to route based on content
  4. Reduce total active agents → lower costs

Scenario: Upgrading Agent Capabilities

When Lindy adds new features (new actions, new models):

  1. Review Lindy Changelog
  2. Update model selection if better options available
  3. Replace workaround actions with new native actions
  4. Test thoroughly — model changes affect output quality

Scenario: Environment Promotion (Dev to Prod)

  1. Share dev agent as Template
  2. Import in production workspace
  3. Re-authorize all production integrations
  4. Update webhook URLs to production endpoints
  5. Verify trigger filters match production requirements

Error Handling

IssueCauseSolution
Webhook URL changedNew agent gets new URLUpdate all callers with new URL
Integration auth failedOAuth not transferredRe-authorize in new workspace
Knowledge base emptyFiles not re-uploadedUpload files to new agent's KB
Phone number unavailableNot re-provisionedPurchase new number in settings
Memory lostMemories not exportedManually re-create critical memories

Resources

Next Steps

Proceed to Pro tier skills for advanced CI integration, deployment, and performance.

More DevOps & CI/CD skills

Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.

6K 472.6K
View

Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.

6K 472.6K
View

Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.

1.5K 454.3K
View
azure-kubernetes logo
DevOps & CI/CD

azure-kubernetes

Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.

1.5K 447.1K
View

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

92.7K 354.9K
View
just-scrape logo
DevOps & CI/CD

just-scrape

Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.

69 245K
View

Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.

462 159.7K
View

Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.

462 159.1K
View
deploy-to-vercel logo
DevOps & CI/CD

deploy-to-vercel

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

31.9K 146.6K
View
programmatic-seo logo
DevOps & CI/CD

programmatic-seo

Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.

53.3K 140.1K
View

Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.

63 123.5K
View

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

31.9K 116.1K
View

Coding & apps AI tools

Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View
Imagica logo
Coding & apps

Imagica

Build a no-code AI app in minutes.

Freemium
View
E
Coding & apps

Emergent.sh

An IDE for code migration from legacy to modern frameworks through coding agents.

Freemium
View
Wonder Dynamics logo
Coding & apps

Wonder Dynamics

Automate CGI animation in live-action scenes

Paid
View
M
Coding & apps

Mixo

Launch a website in seconds with AI.

Paid
View
AI Code Convert logo
Coding & apps

AI Code Convert

Streamline Your Coding Experience with AI Code Helper

Free
View