Yup, I managed. 1,018,735,820 to be exact. Any of you measured tokens per day spent?

let's see if I can crack 1B tokens first time today. it's looking good so far.

just crossed $1k spend on tokens today. should I be worried?

LinkedIn is going to be *pissed* when they find out about Fable next week

Physicians and front-desk spend hours every day typing replies to patient messages. Our new Draft Assist reads each incoming message, figures out what it's actually about, and writes a ready-to-send reply including all necessary details. Staff  just review, insert, and send.

just discovered @cc_usage and I absolutely love it! check your token usage today

Let @tabflows organize your patient roster into smart segments based on contextual data. Some use cases include creating list for certain clinical values, trends, allergies and social demographics.

was expecting something like this:

Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. The longer and more complex the task, the larger Fable 5’s lead over our other models.

No shiny objects - just build one thing and make it really great

It's 4pm. You've got 12 patient messages waiting and a full schedule. You don't want anyone sitting there just to hear back. @tabflows reads the thread, pulls the patient's context, and drafts the reply. You review and send. Inbox cleared before you leave, because you care.

We just released Draft Assist in Tabflows. One click and the assist read's the patient's conversation and medical history, and practice internal information to draft an accurate reply ready for review, tweak and send.

Introducing 30 days of AI. For the next 30 weekdays, I’m going to share one observation per day from the frontlines of AI. I have the privilege of co-running an enterprise AI transformation firm, where I experience the edges of this technology, see the biggest challenges the biggest companies are facing, and have deep relationships with companies on the frontier (Anthropic, OpenAI, Lovable, Cursor, Perplexity, Vercel). I get to live in the future for free, and I want to bring that future to those trying to disrupt themselves before they get disrupted. There’s just two rules: 1) Each observation is actionable & understandable to the non-technical leader. 2) I can’t miss a day. Post 1 coming soon.

Your patient's full story shouldn't be scattered across five different systems ‼️ Here is a quick look at the Patient view we built at Tabflows. The place that pulls together everything that matters about a patient, no matter which system it lives in. Have a good weekend ☀️

My advice to founders in 2026: spend tokens, not headcount. Record everything. Make your company queryable. Build self-improving loops. Before long, AI won’t just help you operate your company. It will make it self improving. Don't think AI adoption, think AI transformation. This is the biggest shift in how startups get built since cloud computing.

Today, we laid the invisible groundwork to enable our users to create AI-curated lists of patients using natural language 🧱

We are now linking even more patient information on @tabflows 🚀

Dictate feature coming to Assist in @tabflows