CGO @docsbotai | Leveraging AI to help businesses scale quickly.
Phoenix, Az
Joined February 2009
- Tweets2.1K
- Following463
- Followers586
- Likes1.6K
Joshua Dailey retweeted
Walls of text are so 2025.
DocsBot Week day #2: Dynamic UI
Joshua Dailey retweeted
♥️ For my European friends and colleagues who haven't attended a PressConf (or formerly related Pressnomics) event, you will NOT want to miss this event.
This event is where the "business of building the web" (with WordPress) sets the direction for the years that follow.
🚨News alert: the #PressConf fam is growing 🫶
We’re beyond excited to let you know we’re meeting this autumn in Barcelona, Spain!
Our very first PressConf Europe edition will take place on October 27-30, 2026.
“Europe has held a special place in my heart for a long time, and so has its WordPress community worldwide. PressConf is one of the most meaningful things I’ve created for this ecosystem, and bringing it to Europe feels like a beautiful way to give some of that love back. It’s a space built for the kind of candid, unrecorded conversations and meaningful connections that can shift ideas, relationships, and what comes next. I cannot wait to see this event unfold.”- @raquel__karina
Stay tuned, more great news to come 🗞️ 🗞️
Joshua Dailey retweeted
People paste personal info into your chat widget.
DocsBot now redacts it in the visitor’s browser, before it reaches your chat logs or AI context.
The bot can still help. It just never sees the raw value.
docsbot.ai/article/client-si…
Joshua Dailey retweeted
I just rebuilt DocsBot's LLM API pricing calculator from the ground up.
The old page had all the data, but it made you dig for a useful answer. I wanted the calculator to answer the question that actually matters:
"Given my workload, which models are actually worth considering?"
The new flow starts with realistic presets for customer support, document summaries, and coding-agent turns. From there you tune input/output tokens, cache hit rate, request volume, and billing period to watch real cost estimates move.
A few details:
• Latest models show by default, with quick filters for all models, open models, and major providers.
• Long-context pricing kicks in automatically when a model's per-request threshold gets crossed.
• Table and graph views.
• Pin models and compare them side by side.
• Shareable calculation URLs.
• Audio and embedding models sit right alongside chat models.
The presets come from real workload shapes too. Support requests carry way more input than output thanks to conversation history and retrieved context. Summaries rarely reuse cache. Coding workloads lean hard on cache reuse.
Joshua Dailey retweeted
On a sales call today, prospect said they were referred to us
I asked how, and they said "ChatGPT" gave us a glowing recommendation 🤯
Joshua Dailey retweeted
When I first saw Docsbot about 2 years ago I thought "Perfect timing, but we'll see how long this lasts." The amazing thing about @uglyrobot is his ability to keep ahead of the curve.
Docsbot is not a simple chatbot; it's grown and matured to real solutions-oriented infrastructure.
Try it out, and really dig into all the features, especially these Actions, and you'll see tons of ways it can improve your business and your overall Customer Experience. I'm a fan.
Most AI support bots aren't actually solving problems.
They're assigning homework.
Customer:
"I need an invoice."
AI:
"Go to Billing → Settings → Invoices."
Customer:
😑
That's not resolution.
That's directions.
The new shift happening in AI support isn't better answers.
It's agents that can actually finish the job.
Instead of telling customers what to do, they can:
• retrieve invoices
• process refunds
• cancel subscriptions
• book meetings
• capture leads
• run approved workflows
• look up live context from your systems
The challenge isn't capability.
It's control.
Giving an AI agent access to customer systems without guardrails is a nightmare.
That's why I built AI Actions and Skill Builder for DocsBot.
Your agent only gets the tools, permissions, and workflows you explicitly approve, scoped to the customer it's helping.
The goal isn't smarter chatbots.
The goal is fewer unresolved tickets.
What's the first support task you'd trust an AI agent to complete end-to-end?
Joshua Dailey retweeted
Playing with Remotion skill in Codex to make motion graphics videos. Not too bad from a series of prompts. It stole and adapted styles and graphics from my landing page html as reference.
Joshua Dailey retweeted
Miss the Skill Builder announcement at the Live Build? Watch the replay and start creating your own actions.
#DBW26
youtu.be/EPj1cU2qppw
Joshua Dailey retweeted
Businesses don’t have an AI problem. They have a change problem.
Revenue models are shifting. Client expectations are rising. Tools change every week.
The companies that win won’t be the ones “using AI” the loudest, they’ll be the ones turning it into real operational valu
Joshua Dailey retweeted
This is our first true subagent. It can evaluate your refund guardrails out of band if the customer conversation with full billing context for the customer so that they can’t prompt-inject a refund haha
Still answering “Where’s my invoice?” or “How do I update my card?”
Stripe Actions lets your DocsBot handle it. Look up invoices, send to billing portal, refund (with rules), and cancel subscriptions.
Fewer tickets, faster resolutions.
docsbot.ai/register
Joshua Dailey retweeted
"What clients really want is outcomes, not AI this and AI that." - @uglyrobot 100% AGREE!
Come join the fun: summit.atarim.io