Agents you can actually rely on. Built specifically for accountants. Join us https://xitter.cf/t.co/opwj4XyvS9
New York
Joined January 2023
- Tweets94
- Following6
- Followers3.2K
- Likes150
Basis retweeted
We’ve had a blast learning with you, and now we’re scaling up every piece of what we do.
With the support of @trybasis, we’re going all in on our mission to become NYC’s home for designers and builders.
In this next chapter, we’ll be focused on producing industry-shaping events and media for our community here in NYC and our friends beyond.
Our own @falcone_design talked with @simoncorry and @mitch_troy about Basis betting on Double Diamond, and the power of new media and real community.
(00:00) John and Simon join Basis to build Labs
(00:34) The origin of Double Diamond
(04:06) Why Basis is supporting Double Diamond
(07:55) Why traditional recruitment is dead
(11:46) Becoming a meat proxy
(16:13) Babysitting Claude vs becoming prolific
(25:21) Leading users to the future
(31:34) Design systems are not solved
(37:46) Nobody cares about accounting
(42:12) Accounting as the foundation of capitalism
Basis retweeted
Excited for this come join to chat about the real work that happens when deploying long horizon and proactive agents to the real economy
Announcing @mitch_troy, Co-Founder of Basis, at AI Engineer New York.
“Process Supervision for Agents That Do Long-Horizon Work” tackles how to evaluate research and tool use without mistaking a correct answer for a reliable process.
Oct. 12–14
→ ai.engineer/nyc/2026
Basis retweeted
☀️ AI:AM is live.
Today: @mitch_troy, co-founder of @trybasis, on running long-horizon agents on real money, 9:30a PT.
Then Jay Dawani, co-founder & CEO of Lemurian Labs, on whether CUDA's moat is really a software problem, 10:15a PT.
xitter.cf/i/broadcasts/1aKbdEopl…
Basis retweeted
Excited to announce the Basis End-to-End Tax Platform, the first production deployment I’m aware of built around truly proactive agents.
By proactive agents, I mean agents that operate against goals and jobs without needing a human to constantly give them work.
I think this is the next logical evolution of long-horizon agents.
Basis agents take responsibility for the entire first pass. They gather the required information and evidence from clients, prepare and review the return, and bring in accountants when an issue requires judgment.
The agents keep the work moving. Accountants can inspect every step and control every decision.
The future of tax is end-to-end intelligence.
Today at Basis Tax Day, we hosted leaders from 30 of the Top 100 accounting firms to explore what changes when Basis takes the first pass on complex returns.
We launched Basis End-to-End Tax for that future. So accountants get out of data entry and start with review.
The 2027 busy season will feel very different with Basis.
Basis retweeted
Nobody wants to be an accountant anymore. Basis CEO Matt Harpe thinks he can help.
Founded in 2023 by Harpe and @mitch_troy, Basis builds AI agents for accounting firms, automating hours of number crunching and copy-paste into a review process that takes minutes.
@trybasis already works with 25% of the top 150 firms in the U.S. and reached a valuation of $1.15B in February.
And far from eliminating jobs, Harpe believes his startup will help human accountants get paid.
"It will increase how valuable accountants are, because they will be able to accomplish so much more," he says.
On The Upstarts Podcast, Harpe shares:
▪️how Basis can stay ahead of the big labs like Anthropic and OpenAI in its vertical
▪️why outcome-based pricing is nice work, if you can get it
▪️how he pitches top AI talent in New York on building accounting tools, of all things.
Plus, he shares his Upstart Moment: resisting calls to chase short-term revenue until his product felt ready for primetime.
TIMESTAMPS
00:00 Introduction
01:47 The basis for Basis
07:25 Why no one wants to be an accountant any more 14:37 CEO Matt Harpe's founder journey
19:46 "The home for applied AI talent in New York"
22:58 Winning over skeptical accountants as customers
28:41 A big bet on agents from the start
31:31 Outcome-based pricing and its challenges
35:52 Competing with the big AI labs like OpenAI
41:11 Making human accountants more valuable
A big thanks to our season sponsor, @Rippling, for supporting founder stories like this 🫡
Enjoy!
Basis retweeted
I have long felt the diminishing effectiveness of LLM-as-a-judge for agents, and one day over coffee @mitch_troy gave me a rant that helped clarify why. The ground truth for an agent isn't its output, it is how the agent should behave.
This is important for two reasons:
(1) it is very difficult to generate good ground truth values
(2) to effectively debug why an agent produced invalid outputs, you need to introspect its behavior.
Mitch then walked through why this is so hard for their team's tax agents. The behaviors themselves are subtle, hard-earned lessons from analyzing lots of failures in their traces in Braintrust, and to effectively flag them, you must effectively document them.
That discussion led us to build behavior specs: a new open standard we're releasing with @trybasis that documents how agents should behave. The repo includes a definition of the spec along with open examples for how to write good specs, evaluate agents using it, and more.
Clear, human-articulated prose is the highest leverage way to drive agentic systems to produce great outcomes. Behavior specs provide a framework to do that with evals. I'm super excited to work on this in the open, and would love to get feedback from others on how we can make this spec maximally useful.
Please try it out, and share your thoughts!
agentbehavior.dev/
Out of the box, long-horizon agents struggle to accurately perform end to end work in the real economy (outside of coding) because those tasks are not easily verifiable, the data is hard to scale, and going from inputs to real outcomes can actually take many days.
Even if you had a reliable way to verify outcomes at scale (and weren’t bothered by the multi-hour iteration loops), the sheer volume of decisions by the agent that occur in a multi-hour job makes it hard to know whether performing well will generalize to production.
Over the last two years at @trybasis, we've been solving this problem by supervising the process our agents take to get to outcomes, rather than just looking at whether the outcome itself is correct.
We think this is the key to building production agents at scale.
It's what has allowed us to run agents in production that operate for hours, sometimes days, and reliably perform tasks like entire complex tax returns end to end.
Today, alongside @braintrust, we're open sourcing a standard for defining, evaluating, and eventually rewarding agent behaviors.
Thread below with all the details on how we’re scaling behaviors to close the loop for long-horizon agents.
Basis retweeted
The term harness is too bloated. Everything is a “harness”. I propose a new concept: operating environment.
A harness is the execution layer. The code that orchestrates the model, memory etc. so Claude code is a “harness”
An operating environment is the totality of the world the agent lives in. This includes the harness BUT also includes all of the context the model learns from in the course of a trajectory. (Or as I like to think of it “runtime training data”)
So Claude Code or Codex would be a harness, but the Basis codebase when Codex runs on it is an operating environment.
Arguably this distinction is even more important for applied ML companies like Basis that own the operating environment for our agents and need to be very thoughtful on that context and meta behavior engineering
Basis retweeted
@trybasis is an incredible place to work, and these kind of messages are really rewarding for me personally. Our motto has always been:
"We don't care about the perception of winning, we care about actually winning."
Buuuut perceptions matter. So we're hiring a a Narratives & Comms Lead! JD below.
Basis retweeted
What our practice-wide @trybasis hackathon means for clients:
✓ Monthly close: 15 days → 5 days
✓ Real-time financial insights vs weeks of waiting
✓ Accountants focused on strategy vs data entry ✓ Capacity that scales with your growth
Better service. Better outcomes.
Basis retweeted
Learn a bit about how we think at @trybasis. Maybe listen on 0.5x speed...
Ontologies, Evals & Deployed Intelligence: Building Real AI Agents - @mitch_troy, co-founder of @trybasis
0:04: Intro /Meet Mitch Troyanovsky
2:20: What is an AI Agent, actually?
4:07: The Gap Between LLMs and Embodied Intelligence
5:25: Why Ontology is the Missing Piece of Agent Design
8:10: Evals, Evals, Evals
9:57: Building a Deployed Intelligence Team
11:35: The Path to Being a Good AI Agent Builder
From our most recent #DataDrivenNYC
Basis retweeted
. @vkhosla and I had a great afternoon with Matt and Mitch @trybasis HQ
They’re building a world class team in NYC and hiring across the board. If you’re interested in joining a 🚀 changing how accountants work by giving them AI agents they can actually trust, reach out to @mitch_troy
Basis retweeted
Next Data Driven NYC (event #118) - Wed Sept 17
* @mitch_troy, founder, @trybasis (agents for accountants)
* @GabeStengel, founder, @RogoAI (Generative AI for financial firms)
* @TheEthanDing, founder, @textql (enterprise data agents)
RSVP: see reply post below
Basis retweeted
@trybasis is hiring our first Account Executive!
We're currently the leader in providing agents to accountants and if you're wondering how we've gotten so far with no sales team.. the product is just that good.
Great opportunity to build out a function from scratch. JD below.
Basis retweeted
Next #BillionDollarStartups listee Basis makes AI accounting software that can do clerical work in minutes, streamlining data entry tasks like transferring information from receipts. trib.al/B9jEsYG trib.al/B9jEsYG
Basis retweeted
If you used to work at an NYC tech company and want free 10k:
Just DM me a note with top 5 people you've worked with in eng/product. No intro needed. just 5 names and if we hire any of them in the next 12 months I will pay you 10k. You don't need to do any work.
Basis retweeted
Left the office tonight around 9 and Adnan, our very Serbian building manager, stopped me
“How many u still got up there??”
“Like 15? Good amount”
“Every night with this. 6:30/7 I understand but this. You guys need lives”
Basis retweeted
@trybasis is hiring a founding talent lead to own the talent function
- Build talent from the ground up
- Work with a team that treats talent as a core competency
- Work directly with founders
- In office NYC. Whiteboards > meetings
- Team size growing fast = enormous responsibility
- Revenue growing 10x last couple months
- AI doing work in the real world
Basis retweeted
Excited to improve the speed, accuracy and accessibility of accounting via AI!
We’ve raised $34m to accelerate our goal of equipping every accountant with a team of AI agents.
Led by Keith Rabois at Khosla Ventures with Nat Friedman & Daniel Gross and continued participation from Better Tomorrow Ventures, BoxGroup, and Avid Ventures.
Excited to also welcome:
Aaron Levie, Adam D’Angelo, Amjad Masad, Azeem Azhar, Clem Delangue, Claire Hughes Johnson, Jack Altman, Jeff Dean, Jeff Wilke, Kyle Vogt, Larry Summers, Lenny Rachitsky, Michele Catasta, Noam Brown and others
Basis retweeted
Excited to announce our partnership with @wissllp to bring integrated, end-to-end AI to accounting workflows.
The Wiss team have been instrumental to bringing these new capabilities to accounting, and we are really excited to continue working closely for the coming decade.
Basis retweeted
@trybasis is hiring for our first generalist business role to work alongside our technical and accounting staff
If you're really sharp, want to work hard, willing to get your hands dirty, and looking to join an AI seed company that is taking off shoot me a note
