---
title: "Automation"
description: "82 posts about Automation, summarised, each linking to the original."
---

# Automation
> 82 posts about Automation, summarised, each linking to the original.

## Articles

### [Introducing Custom Agents](https://yomu.fyi/post/introducing-custom-agents.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Akshay Kothari
- Published: Feb 24, 2026
- Type: Announcement

Notion has made Custom Agents available to Business and Enterprise plans as autonomous AI teammates for recurring work across Notion, Slack, Mail, Calendar, Figma, Linear, and custom MCP servers. Users describe a job and set triggers, while agents can answer questions, route tasks, compile updates, and run workflows across connected tools; setup includes an agent-written instruction set and tool configuration. The announcement describes enterprise controls including permissions, version control, usage analytics, logged runs, reversible changes, alerts, auto-pause, and administrative connection controls, while noting prompt-injection risks and planned guardrails. Custom Agents are free through 3 May 2026, then consume Notion credits based on work, with the seat price and other listed AI features unchanged; early testers have built over 21,000 agents.


### [The evolution of support starts now](https://yomu.fyi/post/the-evolution-of-support-starts-now.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Yohanna Andom
- Published: Feb 12, 2026
- Type: Announcement

Intercom introduces Resolution Bot, a machine-learning support chatbot designed to resolve customer issues rather than merely direct people to help-center articles. In the Intercom Messenger, it provides tailored resolutions, can use integrations such as Shopify to surface order status, and proactively suggests answers while customers type. The update adds six languages—Spanish, French, Italian, Brazilian Portuguese, Russian, and German—along with demographic targeting based on factors such as spend, business type, and location. New reporting shows answer-level sends and resolution rates, identifies underperforming answers, and lets teams filter conversation metrics for bot interactions. Intercom reports that the bot automatically resolves 33% of common support questions and saved businesses an average of 109 hours of customers’ time over the last year, positioning the release as a way to provide faster, more consistent support at global scale.


### [Defining customer support in 2025: Why it's key to your long](https://yomu.fyi/post/defining-customer-support-in-2025-why-it-s-key-to-your-long.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Declan Ivory
- Published: Feb 4, 2026
- Type: Explainer

Customer support has shifted from a perceived cost to a differentiator as expectations rise and companies focus on retention, advocacy, and product feedback. Modern support aims to resolve issues, troubleshoot problems, and help customers get more value through personal, contextual, knowledgeable, and proactive interactions. The post argues that human+AI partnerships can improve speed and efficiency: AI agent Fin handles common questions in more than 45 languages, while human teammates address complex queries empathetically. It also explains why ticketing became necessary for tracking asynchronous work, internal ownership, and customer updates within an all-in-one support platform. Examples from Hospitable and Rebag report faster responses, reduced response times, and higher NPS, while the broader guidance emphasizes clear expectations, robust processes, escalation paths, and a clear route to human help.


### [New research: Customer service team evolution](https://yomu.fyi/post/new-research-customer-service-team-evolution.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Emiliano Melchiorre
- Published: Jan 5, 2026
- Type: Explainer

An analysis of 166 interviews examines how customer service roles, workflows, and team structures changed after adopting Fin or similar AI agents. Using interviews with Intercom customers or prospects, the researchers cleaned conversation transcripts with Python and coded them through the OpenAI API against a closed codebook. Workflow disruption was reported by 94.58% of participants, while 82.53% reported changed responsibilities; 27.71% reported headcount or hiring effects, and 6.02% reported changed team structures or reporting lines. The findings describe hybrid human–AI operations in which AI handles triage, routing, translation, repetitive responses, and some refunds, while people increasingly oversee quality, testing, metrics, and complex or sensitive interactions, although organizational strategies and required skills remain uneven.


### [Steam, Steel, and Infinite Minds](https://yomu.fyi/post/steam-steel-and-infinite-minds.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Ivan Zhao
- Published: Dec 22, 2025
- Type: Explainer

The post frames AI as a new “miracle material” that could reshape knowledge work as steel and semiconductors reshaped earlier eras. It argues that coding agents already let one programmer orchestrate several AI coding agents, but broader knowledge work remains constrained by fragmented context across tools and weak verifiability. At the organisational level, it compares AI with steel and steam, suggesting agents could preserve workflow context, surface decisions, and reduce dependence on meetings and hierarchical approvals; Notion is described as using more than 700 agents alongside 1,000 employees for repetitive tasks. At economy scale, it predicts organisations spanning humans and thousands of agents, with continuous workflows and new rhythms, while acknowledging that this transition may be disorienting and requires redesign rather than simply adding chatbots to existing tools.


### [2026 customer service planning series: Vol. 05](https://yomu.fyi/post/2026-customer-service-planning-series-vol-05.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Declan Ivory
- Published: Dec 16, 2025
- Type: Explainer

AI-first customer service makes capacity planning less predictable because automation changes volume, work mix, human responsibilities, and performance over time. The proposed planning model puts automation rate—AI Agent involvement rate multiplied by AI Agent resolution rate—alongside inbound volume, human output for complex remaining work, and occupancy. It recommends ambitious automation assumptions only when backed by named ownership, content and systems investment, work-type targets, and staged improvement, while modeling lower cases closed per person and more time for off-queue work. Finance should treat the plan as a revisable set of assumptions, review it at least quarterly, and avoid cutting headcount before automation is proven. Surplus capacity should be redirected to AI improvement, product feedback, new channels, or proactive customer experience work rather than automatically reduced.


### [2026 customer service planning series: Vol. 04](https://yomu.fyi/post/2026-customer-service-planning-series-vol-04.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Declan Ivory
- Published: Dec 9, 2025
- Type: Explainer

After defining team roles, an operating model is needed to make progress part of customer-support work and keep an AI Agent improving over time. The stated goal is that “the first time you answer a question should be the last,” with each resolution improving the system so fewer issues repeat, quality compounds, and support scales. The post emphasizes clear ownership, risk-aware guardrails, feedback loops, and a culture that values improvement work; it identifies ambiguity as a common cause of performance plateaus. An AI ops lead, often located in support operations or developed from an existing role, owns performance and drives change, illustrated by Dotdigital’s dedicated specialist after resolution volume held at about 2,800 conversations per month for three months; lightweight governance is presented as a way to keep iterating without excessive bureaucracy.


### [2026 customer service planning series: Vol. 03](https://yomu.fyi/post/2026-customer-service-planning-series-vol-03.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Declan Ivory
- Published: Dec 2, 2025
- Type: Explainer

AI performance in customer support can drift without clear ownership, even when the underlying model is capable. This part of a 2026 planning series presents four roles: AI operations lead, knowledge manager, conversation designer, and support automation specialist. The roles cover monitoring and guardrails, structured and compliant knowledge, conversational tone and flow, and reliable action through backend systems, with the AI operations lead coordinating reporting and improvement. The post describes an operating loop in which performance patterns drive knowledge fixes, interaction changes, and expanded automation, while phased ownership moves from part-time assignments to formal roles and hiring. It says dedicated specialization becomes essential when AI handles 50–70% of incoming volume, and frames these roles as the backbone of an AI-first support organization.


### [How Ramp built an AI operating system for scalable work](https://yomu.fyi/post/how-ramp-built-an-ai-operating-system-for-scalable-work.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Drew Evans
- Published: Dec 2, 2025
- Type: Problem & solution

Ramp spent the last year building what operations and AI product leader Ben Levik calls an “AI operating system” for the company, with the goal of becoming more productive. Rather than waiting for tools to mature, Ramp promotes a “Builder” mindset and organizes adoption around Prompt, Knowledge, and Workflow. Employees refine vague requests by having AI ask clarifying questions, while a Notion knowledge base connected to other tools uses feedback loops in which AI drafts corrections and humans approve them. AI agents and connectors then automate tasks such as summarizing project updates from five sources and researching prospects for review-ready sales emails. About 90% of 1,200 employees use Notion AI monthly, and Ramp reports shipping 270 features in the first half of 2025, more than during all of 2024, shifting the bottleneck toward choosing what to automate next.


### [Social Media Posting Schedule: 9-Step Guide](https://yomu.fyi/post/social-media-posting-schedule-9-step-guide.md)
- Company: [Brandwatch](https://yomu.fyi/company/brandwatch.md)
- Author: Sandra Busch
- Published: Nov 27, 2025
- Type: Tutorial

Managing multiple social accounts makes consistency, timing, content mix, and collaboration difficult, so the guide presents a nine-step scheduling process. It recommends auditing active and dormant channels, defining goals and KPIs, studying audience behavior and platform differences, selecting a tool, and building a calendar around content pillars, campaigns, roles, and a two-to-four-week planning horizon. The process then covers batch creation, reusable assets, platform-specific captions, approval workflows, analytics, time zones, and flexibility for timely content; Brandwatch Publish is presented as an example supporting TikTok, Instagram, Facebook, X, LinkedIn, and Pinterest. It concludes that scheduling should create capacity for engagement and strategy without sacrificing authenticity, and advises regular audits, experimentation, and readiness to pause or adapt queued posts. The guidance also warns against excessive promotion, ignoring engagement, identical cross-platform posts, weak visuals, and over-reliance on automation.


### [What’s new with Fin 3: The best AI Agent for complex queries across every channel](https://yomu.fyi/post/what-s-new-with-fin-3-the-best-ai-agent-for-complex-queries-across-eve.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Declan Ivory
- Published: Oct 30, 2025
- Type: Announcement

Fin 3 is presented as an AI Agent for customer service focused on increasing automation rate by handling complex queries end-to-end across more channels. Procedures combine natural-language instructions with data connectors, conditional steps, code snippets, and approval checkpoints, allowing teams to encode standard operating procedures with varying levels of control. Simulations provide multi-turn testing for different customer segments and scenarios, while Fin Voice, Slack, and Discord expand deployment options. Insights upgrades add CX Score Reasons, Topic Trends, and AI-powered Suggestions that surface quality changes, topic shifts, and content improvements. The announcement says Fin 3’s broader goal is to increase the share of overall support workload it handles, beyond a resolution-rate metric that had reached 66% on average across more than 6,000 customers.


### [Navigating the AI storm: How to harness the power of AI without being crushed by it](https://yomu.fyi/post/navigating-the-ai-storm-how-to-harness-the-power-of-ai-without-being-c.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Chris Murray
- Published: Sep 18, 2025
- Type: Explainer

Support leaders are being asked to preserve customer experience and operational performance while becoming AI experts and leading high-lift, cross-functional implementations. Before AI, support was often treated as a cost center; now executives may demand aggressive AI metrics without understanding the resources, risks, and work still required. The proposed response is to harness the change by learning AI deeply, testing multiple vendors through trials, choosing a durable partner, and defining benchmarks and phased implementation plans. Support leaders should also explain why deflecting 50% of inquiries does not justify cutting staffing by 50%, given coverage, service-level redundancy, growth, attrition, and work beyond direct inquiries. The article ultimately argues that visible ownership, concise project management, and weekly or bi-weekly executive updates can reposition support as a value driver rather than a cost center.


### [Toyota, Affirm, Mercury, and more get faster business results with certified Notion Solutions Partners](https://yomu.fyi/post/toyota-affirm-mercury-and-more-get-faster-business-results-with-certif.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Published: Sep 15, 2025
- Type: Explainer

Notion’s certified Solutions Partners help organizations replace fragmented tools, connect workflows, and build systems that can scale. At Affirm, Notion State used a five-phase deployment strategy across multiple departments, helping achieve 95% knowledge-management adoption, reduce tool seats, and create a unified workspace. NorthSand helped Toyota’s Future Creation Center add custom automations, approval workflows, and centralized scheduling, making key workflows three times faster and cutting meeting-preparation time in half. MegazoneCloud supported JOYCITY’s migration from Jira, Confluence, and Microsoft by running parallel systems, focusing new projects in Notion, and providing on-site training, while Optemization archived more than 63,000 of Mercury’s pages and established a standardized information architecture. The examples position partner expertise and ongoing support as ways to improve adoption, trust, collaboration, and scalability.


### [Heroku Postgres Upgrade Guide: Simplify Your Move to Version 17](https://yomu.fyi/post/heroku-postgres-upgrade-guide-simplify-your-move-to-version-17.md)
- Company: [Heroku](https://yomu.fyi/company/heroku.md)
- Author: Kavya Premkumar
- Published: May 29, 2025
- Type: Tutorial

Heroku Postgres 17 is now available, and the platform introduces a simplified, self-service path for upgrading managed databases. The new heroku pg:upgrade:\* commands cover preparation, manual execution, cancellation, dry runs, and progress tracking, while email notifications report major stages and detected issues. Essential-tier databases can be upgraded directly with pg:upgrade:run; Standard-tier and higher databases can use a dry run, schedule an upgrade for the next maintenance window, or run it manually, with followers upgraded automatically. The in-place workflow uses an internal replica, leaves DATABASE\_URL and other config vars unchanged, and typically reduces downtime to about five to ten minutes. The legacy heroku pg:upgrade command will be deprecated soon, although the traditional follower approach remains available.


### [eBay Reduces the Time to List on Mobile With New Simplified Selling Tool, Now Featuring Magical Listing AI Technology](https://yomu.fyi/post/ebay-reduces-the-time-to-list-on-mobile-with-new-simplified-selling-to.md)
- Company: [Ebay](https://yomu.fyi/company/ebay.md)
- Author: eBay News Team
- Published: Apr 9, 2025
- Type: Announcement

eBay has introduced a simplified, mobile-friendly listing flow that integrates its “magical listing” AI technology to reduce the effort required to create high-quality listings. Sellers start with photos and a title, while AI uses image matching and inference to suggest item specifics and categories through guided pages where sellers can review and approve the content. Early testing in the U.K. found a 50% reduction in total listing steps and faster listing times, while eBay says item-specific accuracy will continue improving through updates made during the year. The tool is available in the eBay mobile app for private sellers across all categories in the U.S., U.K., and Germany, and eBay plans to expand it to sellers using business tools.


### [Propel Your SaaS Apps Into the Future at Oktane](https://yomu.fyi/post/propel-your-saas-apps-into-the-future-at-oktane.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Michael Palermo
- Published: Sep 26, 2024
- Type: Announcement

Okta invites SaaS application builders to Oktane 2024, held at Caesars Forum in Las Vegas from October 15–17, to discuss how identity and user lifecycle platforms can support secure B2B SaaS applications. The announcement frames identity as increasingly complex, with a growing protection surface expected to influence SaaS roadmaps and developer priorities. Attendees can join three breakout sessions, visit the Dev Hub, attend hands-on labs, and connect at a B2B SaaS builders happy hour or the Okta Workflows community meetup. Lab topics include moving Okta app configurations from PowerShell into Terraform, signing users out across apps with one API, and identifying inactive users with Okta Workflows. Some activities require Oktane attendance, while labs have limited, first-come-first-served capacity and the happy hour is invitation-based.


### [New Social Caption Generator Uses AI to Help Sellers Post More Easily](https://yomu.fyi/post/new-social-caption-generator-uses-ai-to-help-sellers-post-more-easily.md)
- Company: [Ebay](https://yomu.fyi/company/ebay.md)
- Author: eBay News Team
- Published: Dec 18, 2023
- Type: Announcement

For eBay sellers, social media promotion can make listings more visible, but composing effective captions may be difficult. Its new generative AI feature adds a “Use AI Caption” button in the Social page of Seller Hub, where it drafts item-focused posts with hashtags and emojis. Sellers can ask for rewrites, manually keep or remove those extras, and publish posts containing listing links and item images. The capability is fully available in the US, UK, Germany, and Australia for sharing individual listings, categories, promotions, and stores, while an announced auto-posting option will later automatically publish new listings when they go live. The company reports a positive response from early users.


### [Enterprise Maturity Workshop: Automate with no](https://yomu.fyi/post/enterprise-maturity-workshop-automate-with-no.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Max Katz
- Published: Sep 15, 2023
- Type: Tutorial

This tutorial shows how to extend a SaaS Todo application with a weekly organizational report using Okta Workflows, a no-code automation platform. It adds an API service to the application, exposes the local app through a tunnel, and configures a scheduled flow to retrieve all todo items. A helper flow processes the returned list with a Reduce card, carrying accumulated text in a memo field before producing one summary for the Gmail Send Email card. The report is sent automatically by email after the items are combined. The workshop concludes by enabling both flows and testing the automation, while noting that the local setup is for demonstration and that a real-world application would be deployed in the cloud.


### [How to Take Your Enterprise](https://yomu.fyi/post/how-to-take-your-enterprise.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Aaron Parecki
- Published: Jun 29, 2023
- Type: Announcement

This installment in a Devday23 presentation series addresses how to move an enterprise-ready SaaS application beyond its MVP. It focuses on the functionality needed to help an application stand out to enterprise customers, including user provisioning and automation that can scale. The stated goal is to support growth from a working MVP toward enterprise adoption. Aaron Parecki shared material on Okta Workflows, provisioning, SaaS application maturity, and SCIM, with links to a SCIM developer video and Workflow Connector Builder tutorials. The broader series also points to upcoming coverage of authentication mechanisms and deployment automation, positioning enterprise readiness as an ongoing progression rather than a single feature.


### [What Does It Mean to Be Enterprise Ready: Devday23 Keynote](https://yomu.fyi/post/what-does-it-mean-to-be-enterprise-ready-devday23-keynote.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Team Okta
- Published: Jun 13, 2023
- Type: Announcement

What makes a SaaS application ready for enterprise customers when identity is involved? This Devday23 keynote introduces enterprise readiness as a concern spanning application security, user onboarding, scalable authentication, identity, user management, and automation. Arnab Bose, Chief Product Officer for Workforce Identity Cloud at Okta, leads the presentation’s “Why” and “What” questions in a half-day virtual conference hosted at WIC Devday 23. The keynote is positioned as the opening of a series covering enterprise customer expectations, building an enterprise-ready MVP, moving beyond MVP, authentication considerations, user management, and stronger authentication mechanisms; a related “Setting the Bar for Enterprise-Grade Identity” whitepaper provides benchmarks for secure SaaS management.


[Newer posts](https://yomu.fyi/topic/automation/page/3.md) · [Older posts](https://yomu.fyi/topic/automation/page/5.md)