DEV Community: IRFAN ULLAH

I Cut My Marketing Time from 4 Hours to 45 Minutes Using Free AI Tools

IRFAN ULLAH — Fri, 20 Mar 2026 06:09:03 +0000

A real system, real tools, zero paid subscriptions — and the workflow that made it stick.

Last March, I almost quit freelancing.
Not because I wasn't getting clients. Not because the work was bad. I almost quit because I was spending more time talking about my work than actually doing it.
Every Monday looked the same: coffee at 8am, emails by 9, and then somehow it's 1pm and I've written exactly one Instagram caption and an intro paragraph for a newsletter that still isn't finished. The "marketing" part of running a one-person business was eating the business alive.
Sound familiar?

The Real Problem Nobody Talks About

Here's the thing nobody tells you when you go solo: marketing isn't one task. It's twenty tasks wearing a trench coat, pretending to be one.
You have to:

Research what your audience actually cares about
Write content across multiple platforms (each with its own tone)
Turn blog posts into tweets, emails into carousels, webinars into clips
Stay consistent—every single week—even when you're slammed with client work

For a team of five, that's manageable. For one person? It's a part-time job stacked on top of your actual job.
I tried hiring a VA. The onboarding alone took three weeks. I tried content calendars. I filled them out diligently for exactly eleven days. I tried "batching" my content on Sundays—until Sunday became my least favorite day of the week.
Something had to change.

The Shift That Changed Everything

The shift wasn't discovering one magic tool. It was realizing I was doing this backwards.
I was trying to create content and then distribute it. What I needed was a system that let me capture one idea and multiply it — automatically, or close to it.

"The goal isn't to do more marketing. The goal is to need less time to stay consistent."

Think of it like audio engineering. You don't record every instrument separately every time you want a song. You record the main track once and let the process do the rest.
Once I reframed the problem that way, building the workflow became obvious.

The Workflow at a Glance

Step-by-Step: How I Actually Do It

Step 1 — Write the "Source" Post (Monday, ~45 min)

Everything starts with a single core piece—a 600–800 word blog post or a long LinkedIn post. I write this myself. Every time.
Why manually? Because this is the part that requires me. The opinions, the weird analogy only I would make, and the example from a real client call last Tuesday. This is the soul of the content. Everything else is distribution.
Tool: Notion (free) — one content board, one card per week, nothing fancy.

Step 2 — Repurpose with Claude (~10 min)

Once the source post is done, I paste it into Claude (free tier) with a prompt like

"You are a content repurposing assistant. Given this blog post, extract 5 key insights as standalone Twitter/X threads, 4–5 tweets each. Keep my voice — direct, slightly sarcastic, and no buzzwords."

Two minutes later: five ready-to-schedule threads. Not perfect, but 80% there. I edit quickly and move on.
Same source post, different prompt:

"Rewrite this as a short LinkedIn post (under 150 words) that ends with a question to drive comments."

Done. Two platforms handled in under 10 minutes.

Step 3 — Draft the Email Newsletter (~15 min)

I use Mailchimp's free plan to send a weekly email to ~400 subscribers. The email used to take me a full hour.
Now I use this Claude prompt:

"Turn this blog post into a conversational email newsletter. Open with a personal hook (I'll fill that in), include 3 takeaways, and end with a CTA to reply with their biggest challenge this week."

I get a clean draft. I add two sentences at the top that make it feel personal. I send it. Fifteen minutes, start to finish.

Step 4 — Create Visuals with Canva AI (~20 min)

I'm not a designer. That used to mean graphics were either skipped or outsourced.
Canva's free plan includes Magic Design. I paste in my LinkedIn post text, ask it to generate a carousel layout, pick the one that fits, swap in my brand colors, tweak the copy, and export.
A five-slide carousel that used to take me 90 minutes now takes 20.
For quick quote graphics, Adobe Express (free) is faster and cleaner for single images.

Step 5 — Schedule Everything in One Sitting (~15 min)

All content goes into Buffer's free plan (3 channels, 10 posts per channel). Every Wednesday afternoon, I block 15 minutes and schedule the whole week.

LinkedIn post → Thursday 8am
Twitter/X thread → Tuesday 9am
Email newsletter → Friday morning

That's it. The week is locked in. I won't touch it again.

Step 6—Mine Old Ideas with NotebookLM (~10 min/month)

This is the hidden weapon.
Google's NotebookLM (free) lets you upload past blog posts, newsletters, and notes as sources — then query them like a research assistant.
"What themes keep coming up across my last 20 posts?"
"Generate three new post angles based on patterns in what I've already written."
It's like having a second brain that actually remembers everything. Old content becomes new content. I never truly run out of ideas.

The Full Stack at a Glance

Task	Tool	Weekly Time
Core post drafting	Notion	45 min
Social repurposing	Claude (free)	10 min
Email newsletter draft	Claude + Mailchimp	15 min
Visual content	Canva / Adobe Express	20 min
Scheduling	Buffer	15 min
Idea mining	NotebookLM	10 min/month
Total	All free	~1h 45 min

Before this system: 3–4 hours a day just thinking about what to post, writing half-drafts, and feeling perpetually behind.

Honest Results After 90 Days

I want to be real here because too many automation articles promise overnight life changes.
Here's what actually happened:

Email open rate up 8%—because I was finally sending consistently
LinkedIn followers grew by ~340—not viral, just steady and compounding
Stopped dreading Mondays—which, honestly, was the biggest win
One newsletter led directly to a $3,200 client project—because I was visible during a stretch when I would have otherwise gone quiet

None of this is "post went viral" success. It's the quiet, compounding kind—which, in my experience, is the only kind that's real and repeatable.

The Takeaway

You don't need more tools. You need a system that works even when you're tired, busy, or not motivated.
That's the difference between posting occasionally… and building something that compounds.
Write once. Distribute everywhere. Let AI handle the rest.

If you try any part of this workflow, I'd genuinely love to hear what clicks (and what doesn't). Drop a comment — the best ideas in this system came from conversations exactly like that.

# 10 AI Productivity Tools for Remote Teams That Actually Improve Workflow

IRFAN ULLAH — Sat, 14 Mar 2026 10:40:47 +0000

Remote teams deal with a real set of problems every single day—messages that fall through the cracks, meetings that could've been an email, and tasks that nobody knows the status of. When your team is spread across time zones, even small communication gaps can cost hours of lost productivity.

AI tools are changing how distributed teams work. Not by replacing people, but by handling the repetitive stuff so your team can focus on what actually matters.

Why AI Productivity Tools for Remote Teams Are Becoming Essential

Remote collaboration has always been harder than in-person work. You can't just tap someone on the shoulder. You can't read the room in a Slack message. And you definitely can't see what's blocking a project unless someone speaks up.

Traditional productivity tools like spreadsheets and basic task boards helped at first, but they don't solve the core problem: too much manual work, too little visibility. Most teams end up chasing status updates instead of doing actual work.

AI productivity tools for remote teams close that gap. They automate the repetitive tasks, surface what needs attention, and keep everyone aligned without requiring a meeting for every little thing.

How AI Productivity Tools for Remote Teams Improve Collaboration and Efficiency

The practical benefits of AI tools for remote work aren't theoretical. Teams are using them right now to cut meeting time, reduce back-and-forth, and actually ship faster.

Here's what AI makes possible for distributed teams:

Repetitive task automation — scheduling, follow-ups, data entry, and routine updates run themselves
Meeting summaries — AI captures what was said and what was decided, so no one falls behind
Intelligent scheduling — tools like Motion figure out the best time for deep work versus meetings
Task prioritization — AI flags what's urgent before it becomes a crisis

When your tools handle the overhead, your team gets more hours back for the work that moves the needle.

Key Takeaways: AI Productivity Tools for Remote Teams

AI meeting assistants remove the need for manual notes
AI automation tools eliminate repetitive workflows
AI scheduling tools optimize work across time zones
AI project management tools improve visibility across distributed teams

10 Best AI Productivity Tools for Remote Teams That Improve Workflow

Notion AI – AI Productivity Tools for Remote Teams Knowledge Management

Notion AI turns your team's wiki into an intelligent workspace. It can draft documents, summarize long pages, answer questions based on existing notes, and generate action items from meeting notes.

Remote teams use it to build a shared knowledge base that actually stays up to date. Instead of hunting through old Slack threads for context, someone new can ask Notion AI and get a useful answer in seconds.

Real-world use case: A product team uses Notion AI to auto-summarize customer research sessions and tag them by theme — cutting documentation time by over half.

Key benefit: Reduces the time spent searching for context or writing from scratch.

Slack AI – Communication AI Productivity Tools for Remote Teams

Slack AI adds a layer of intelligence to your team's main communication hub. It can summarize channel activity, recap threads you missed, and surface the most relevant messages when you return after a long break or a different time zone shift.

For remote teams where async communication is the norm, Slack AI means you're never fully out of the loop — even if you're eight hours behind.

Real-world use case: A distributed engineering team uses Slack AI to catch up on overnight discussions without reading 200 messages manually.

Key benefit: Faster async communication with less FOMO across time zones.

ClickUp AI – Project Management AI Productivity Tools for Remote Teams

ClickUp AI is built into one of the most popular project management platforms. It writes task descriptions, generates subtasks, summarizes project updates, and even helps draft stand-up notes.

Remote teams use it to reduce the admin work around managing projects. Instead of writing out every task from scratch, you describe what needs to happen and ClickUp AI fills in the details.

Real-world use case: A startup uses ClickUp AI to auto-generate sprint tasks from product requirements docs — saving their PM two hours per sprint cycle.

Key benefit: Faster project setup with less manual task management.

Motion AI – Scheduling AI Productivity Tools for Remote Teams

Motion is an AI task and calendar manager that automatically schedules your work based on deadlines and priority. It rearranges your day in real time when something changes.

For remote teams juggling multiple projects and time zones, Motion removes the guesswork around when to work on what. It treats your to-do list like a real constraint, not just a wish list.

Real-world use case: A freelance developer uses Motion to block focused coding time automatically while protecting client call slots — without manually managing a complex calendar.

Key benefit: Automatic time-blocking that keeps deep work protected.

Otter AI – Meeting Transcription AI Productivity Tools for Remote Teams

Otter AI records, transcribes, and summarizes meetings in real time. It works across Zoom, Google Meet, and Microsoft Teams. After the meeting, everyone gets a full transcript with key highlights.

Remote teams use it so that people in different time zones can review what happened without watching a full recording. It also means your team stops spending mental energy on note-taking.

Real-world use case: A marketing agency uses Otter to share client call summaries with team members who weren't on the call — keeping everyone aligned without extra meetings.

Key benefit: Every meeting becomes searchable and shareable documentation.

Fireflies AI – Meeting Intelligence AI Productivity Tools for Remote Teams

Fireflies goes further than transcription. It analyzes meetings, identifies action items, tracks topics across multiple calls, and provides conversation intelligence over time.

Remote teams using Fireflies get a searchable database of everything that's been discussed. You can search across all your meetings to find when a decision was made and why.

Real-world use case: A sales team uses Fireflies to automatically log call notes to their CRM and flag follow-up tasks — cutting post-call admin from 20 minutes to two.

Key benefit: Meetings turn into structured, actionable data automatically.

Grammarly AI – Writing AI Productivity Tools for Remote Teams

Grammarly AI helps remote teams communicate clearly in writing — which is literally how distributed teams do most of their work. It goes beyond spell-check to suggest better phrasing, adjust tone, and rewrite entire paragraphs when needed.

Since remote work is writing-heavy (Slack, email, docs, proposals), better writing means fewer misunderstandings and less back-and-forth.

Real-world use case: A remote customer success team uses Grammarly to keep their client emails consistent in tone and professional — regardless of who's writing them.

Key benefit: Consistent, clear written communication across the whole team.

Zapier AI – Workflow Automation AI Productivity Tools for Remote Teams

Zapier has always been the go-to for connecting apps. With AI, it can now build automations based on plain language descriptions. Tell it what you want to automate, and it suggests the workflow.

Remote teams use Zapier to eliminate repetitive busywork — moving data between tools, sending notifications, creating tasks from form submissions — without writing a single line of code.

Real-world use case: A remote operations team uses Zapier to automatically create onboarding tasks in ClickUp whenever a new hire is added to their HRIS — saving an hour of manual setup per hire.

Key benefit: Connects your entire tool stack and automates the gaps between them.

Trello AI – Task Management AI Productivity Tools for Remote Teams

Trello's AI features help teams manage tasks more intelligently. It can suggest labels, spot bottlenecks on boards, and help write card descriptions based on project context.

For remote teams that love a visual kanban approach, Trello AI adds just enough intelligence to keep boards clean and tasks moving without overcomplicating things.

Real-world use case: A small design team uses Trello AI to auto-label incoming project cards by type and priority — so the team always knows what to pick up next.

Key benefit: Smarter task organization without adding complexity.

ChatGPT – AI Assistant Productivity Tools for Remote Teams

ChatGPT is the Swiss Army knife of AI productivity tools for remote work. Teams use it to draft emails, brainstorm ideas, write code, summarize documents, answer questions, and much more.

It's not a dedicated project tool, but it's incredibly versatile. Remote teams that embed ChatGPT into their daily workflow get a productivity boost across nearly every role.

Real-world use case: A remote content team uses ChatGPT to generate first drafts from bullet points, then refines them — cutting content production time by 40%.

Key benefit: A flexible AI assistant that adds value across every function on your team.

How to Choose the Right AI Productivity Tools for Remote Teams

Not every tool fits every team. Here's how to think through it:

Team size — Smaller teams benefit from flexible all-in-one tools like Notion AI. Larger teams may need specialized tools for each function.

Integrations — Your AI tools need to talk to the apps you already use. Check whether the tool connects natively with Slack, Google Workspace, or your CRM before committing.

Automation depth — Some tools automate at the surface level; others can handle complex multi-step workflows. Know how deep you need to go.

Pricing — Many AI tools charge per seat. For distributed teams that scale fast, make sure pricing won't punish growth.

Scalability — Pick tools that grow with you. A tool that works great at 10 people shouldn't break at 50.

AI Productivity Tools for Remote Teams vs Traditional Productivity Tools for Remote Work

Traditional tools give you a place to organize work. AI tools help you get the work done faster.

Factor	Traditional Tools	AI Productivity Tools
Efficiency	Manual, repetitive	Automated, adaptive
Collaboration	Passive storage	Active, real-time support
Decision making	Relies on human input	Surfaces insights automatically
Automation	Rule-based, limited	Context-aware, flexible

The gap is growing. Teams that still rely on traditional tools alone are working harder for the same output. AI tools don't replace your team's judgment — they just remove the friction that slows it down.

Final Thoughts on AI Productivity Tools for Remote Teams

Remote work isn't going away. If anything, distributed teams are becoming the default for tech companies and startups that want to hire globally. The challenge is making those teams just as productive as in-person ones.

AI productivity tools for remote teams are the practical answer to that challenge. They cut the overhead, surface what matters, and keep everyone moving in the same direction — regardless of where they're logging in from.

Teams adopting these tools now are building a real productivity advantage. They're shipping faster, communicating better, and spending more time on actual work instead of chasing updates.

The sooner your team builds AI into daily workflows, the faster remote work starts feeling less chaotic and more scalable.

Want to keep exploring? This 2026 complete AI tools guide covers the full landscape — from productivity to automation to AI writing tools — all in one place.

How AI Chatbots Are Transforming Customer Support in 2026

IRFAN ULLAH — Tue, 10 Mar 2026 12:21:43 +0000

Think back to what "customer support" looked like ten years ago. A phone number, maybe a contact form, and if you were lucky, a live chat widget staffed nine-to-five on weekdays. The experience was slow, inconsistent, and expensive to scale.
Fast forward to 2026, and the gap between then and now is staggering. AI chatbots have moved from awkward novelty to critical infrastructure. They handle millions of customer interactions every day — across industries, channels, and time zones — and they're doing it with a level of fluency that rule-based bots of even five years ago couldn't touch.
This isn't hype. It's a structural shift in how businesses think about customer service. Here's what's driving it, how it actually works, and where the real edges and limitations still are.

The Growing Challenges in Customer Support

The problems modern support teams face didn't appear overnight, but they've compounded in ways that make the old playbook increasingly unsustainable.
Response time expectations have fundamentally shifted. Customers who once accepted a 24-hour email turnaround now expect answers in minutes. That's not unreasonable in a world where messaging is instant—but it's genuinely hard to staff for at any reasonable cost.
Volume is unpredictable and expensive to absorb. A product launch, a billing glitch, an outage — any of these can triple your inbound ticket volume overnight. Hiring to handle peak load means overstaffing during normal periods. There's no elegant solution to that math with humans alone.
Most support tickets are repetitive by nature. Research consistently shows that somewhere between 60% and 80% of incoming queries are variations on the same handful of questions. Password resets. Order status. Billing clarifications. Cancellation requests. These are necessary to answer, but they don't require human judgment — and routing them to skilled agents is a waste of everyone's time.
Support roles burn people out. Customer-facing support has chronically high turnover. The constant rehiring and retraining cycle doesn't just cost money — it erodes the institutional knowledge that makes a support team effective. Every departure is a small setback.
These are the pressure points that AI customer service tools are being built to address.

What Modern AI Chatbots Actually Do

Before getting into outcomes, it's worth being precise about the technology—because "AI chatbot" still means very different things depending on what you're looking at.
The foundation is natural language processing (NLP). Modern chatbots built on large language models (LLMs) can understand what a user is asking even when the phrasing is vague, grammatically rough, or domain-specific. "My thing won't let me in" gets correctly interpreted as an authentication issue. That kind of flexibility simply wasn't possible with older pattern-matching systems.
Beyond understanding intent, today's AI-powered support tools can:

Connect to CRM platforms like Salesforce or HubSpot to pull customer context in real time
Trigger backend workflows—resetting credentials, issuing refunds, updating subscription tiers
Detect when a query is outside their competence and hand off to a human agent with full conversation context attached
Operate simultaneously across web chat, email, SMS, and messaging apps like Slack or WhatsApp
Use retrieval-augmented generation (RAG) to pull answers from a company's own documentation rather than generating from scratch

That last point matters a lot. RAG-based architectures ground chatbot responses in a company's actual knowledge base, which dramatically reduces the risk of the model generating confident but incorrect answers.
What separates modern conversational AI from legacy rule-based bots is the ability to handle ambiguity. Decision-tree bots break the moment a user goes off-script. LLM-powered chatbots can follow a conversation across topic shifts, ask clarifying questions naturally, and handle responses they've never been explicitly trained on.
For teams building their own implementations, frameworks like LangChain and Rasa provide solid starting points for connecting LLMs to business logic and retrieval pipelines. Managed options like Intercom Fin and Dialogflow CX handle more of the infrastructure if you'd rather not build from scratch.

Key Ways AI Chatbots Are Transforming Customer Support

Always-On Coverage Without Staffing Overhead

The most obvious win is availability. AI chatbots handle off-hours support without any marginal cost per conversation. For companies with international customers, this isn't optional—it's table stakes. A user in London or Tokyo shouldn't have to wait until 9 AM Pacific to get a response.

Instant Response Regardless of Volume

Unlike human queues, AI systems don't back up. Whether there are ten active conversations or ten thousand, response time stays consistent. That consistency is especially valuable during the exact moments when support volume spikes—outages, launches, end-of-month billing—when fast responses matter most.

Deflecting Repetitive Tickets at Scale

Automating the high-volume, low-complexity queries is where the ROI shows up most clearly. When 70% of tickets follow predictable patterns and can be resolved automatically, your human agents spend their time on the 30% that actually need them. The work becomes more interesting and more impactful.

Measurable Cost Reduction

Companies that have deployed mature AI customer support automation workflows report cost-per-contact reductions in the 30–60% range. Some of that is direct headcount efficiency; some comes from faster resolution times that reduce repeat contacts and escalations.

More Consistent Customer Experiences

Human agents vary—in knowledge, in mood, in how they interpret a policy. A well-trained chatbot is consistent by definition. It gives the same accurate answer at 2 PM on a Tuesday and at 11 PM on a Saturday. For customers, that reliability builds trust in a quiet but meaningful way.

Real-World Business Use Cases

eCommerce and Post-Purchase Support

DTC and retail brands deal with enormous volumes of order-related queries. Chatbots integrated with order management systems can handle "Where's my order?", address changes, return initiations, and refund requests end-to-end—without any human touchpoint. For high-volume merchants, this kind of customer support automation isn't optional; it's survival.

SaaS Onboarding and Feature Guidance

New user activation is one of the most fragile moments in the SaaS lifecycle. AI chatbots can walk new users through setup flows, answer contextual feature questions, and surface documentation—without users having to hunt through help centers or file a ticket. That kind of in-product guidance measurably improves activation rates.

Appointment Scheduling and Reminders

Healthcare practices, legal services, and home service companies are using conversational AI to handle booking, rescheduling, and appointment reminders in real time. The bot checks availability, confirms slots, and sends follow-ups — work that previously required dedicated front-desk staff.

Lead Qualification for Sales Teams

Marketing and sales teams use AI chatbots to engage website visitors, ask qualifying questions, and route warm leads to the right rep. The bot captures company size, use case, and timeline before any human gets involved — compressing sales cycles and reducing wasted SDR time on unqualified leads.

Technical Troubleshooting and First-Line Dev Support

Infrastructure tools and developer platforms train chatbots on their documentation and known issue libraries to handle first-line technical questions. The bot walks users through common error resolutions, identifies patterns that suggest known bugs, and escalates with full context when the issue genuinely needs an engineer's attention.

AI Chatbots vs. Traditional Support Systems

The difference between old-school bots and modern AI-powered ones is worth being explicit about, because a lot of organizations have been burned by the former and are skeptical of the latter.
Rule-based chatbots follow fixed decision trees. They're reliable within a narrow, predefined scope — but the moment a user goes slightly off-script, they fail. They also require constant manual maintenance: every new product feature and every policy change means someone has to update the decision tree by hand.
Modern AI-driven chatbots handle open-ended conversation. They can follow context across a multi-turn exchange, ask clarifying questions when something is ambiguous, and handle queries they weren't explicitly programmed for. They still need maintenance — but it's about improving the knowledge base, not rewriting logic flows from scratch.
The short version: rule-based bots are brittle and predictable; AI-powered ones are flexible and probabilistic. For general customer support, the advantages of the latter are hard to argue with.

Challenges and Limitations

Any honest account of AI chatbots has to cover what they still can't do well.
Complex and emotionally charged interactions remain hard. When a customer is upset about a situation that had real consequences — a missed delivery that ruined an event, a billing error that overdrafted their account — they need a human who can respond with genuine empathy and situational judgment. AI can detect negative sentiment and escalate, but it shouldn't be the terminal point for high-stakes emotional situations.
Output quality is only as good as the knowledge base behind it. Poorly documented products, inconsistent internal wikis, and outdated information all degrade chatbot performance in proportion to how bad the underlying content is. The technical architecture matters, but the content quality matters more.
Hallucination is a real risk that requires active mitigation. LLMs can produce confident-sounding but factually incorrect answers. In a customer support context, that's a liability issue, not just a UX problem. RAG architectures and rigorous QA processes are necessary safeguards, not optional ones.
Human oversight can't be an afterthought. The best implementations treat AI as a tool that amplifies human capacity — not a replacement for it. Monitoring chatbot performance, auditing edge cases, and maintaining clear escalation paths are ongoing operational requirements, not one-time setup tasks.

The Future of AI Customer Support

Predictive and Proactive Support

Rather than waiting for users to report problems, AI systems are beginning to identify behavioral signals that suggest friction — and reaching out before a ticket is ever filed. Expect this to become standard practice as more companies invest in product instrumentation and real-time analytics.

Voice AI and Phone Automation

Natural-sounding voice interfaces have improved dramatically, and phone support — still the preferred channel for large portions of the population — is becoming a serious frontier for customer support automation. The latency and accuracy problems that made earlier voice bots so painful are largely solved.

Deeper CRM and Product Context Integration

The future isn't a chatbot that knows your name — it's one that knows your plan tier, your recent activity, your last three support interactions, and the known issue that's most likely relevant to what you're experiencing right now. Tighter integration between AI layers and product data is what makes that possible.

Privacy-Focused and On-Premise Models

Not every enterprise wants customer conversations routed through third-party APIs. Smaller, more efficient models deployable on private infrastructure are becoming genuinely viable — particularly for healthcare, fintech, and other sectors with strict data governance requirements. The gap between hosted and self-hosted quality is narrowing fast.

Conclusion

AI chatbots have earned their place in the modern support stack — not because they're flashy, but because the underlying economics and user experience have genuinely improved to the point where the case for them is hard to argue against.
The companies extracting the most value from chatbots for businesses aren't the ones replacing their teams with automation. They're the ones using AI to absorb volume, cut costs, and free up human agents to focus on the interactions that actually require human judgment, empathy, and expertise.
That reframing — AI as a multiplier, not a replacement — is the frame worth holding onto as these tools continue to mature and the support landscape keeps shifting beneath our feet.

If you're building with conversational AI tools or exploring what AI customer service looks like at your company's scale, drop a comment — always interested in what's working in the real world.