Enterprise AI transformation at startup speed. 🟪 https://teapawt.org/t.co/O9yVkOtwhM
Subscribe to our newsletter →
Joined May 2026
- Tweets1.5K
- Following542
- Followers13.2K
- Likes3.3K
Pinned Tweet
Some patterns we're seeing across our engineering clients that tell you where AI adoption is actually heading:
1. Companies are done spending blind on AI. A few months ago, most were approving unlimited API budgets for OpenAI and Anthropic with no tracking on where the tokens went. Today they're asking us to build governance layers and monitor every dollar. One client had three teams running up five-figure token bills before a single production agent shipped. Now they want dashboards that show exactly what's AI-generated, what it costs, and whether it's actually faster than adding headcount. That means more diagnostic work for us and meaningful savings for them.
2. Companies are accepting the real timeline. A few months ago, leadership expected to go AI-native over a few workshops and a handful of tool subscriptions. Now they're calling us because the codebase is seven years old and can't absorb automation without a full foundation phase first. Their developers are using AI at 60-70% adoption, but nobody's tracking what's generated vs. human-written. QA hasn't been touched. There's no governance. Going AI-native means rethinking org charts, handoffs, and process ownership across every department. Not a software purchase.
3. Companies are walking away from the big firms. The Accentures and McKinseys are all pitching AI transformations. Our clients keep showing up saying the same thing: "We paid seven figures for a strategy deck and nothing shipped." This is why firms like ours have a market. We operate at the engineering layer while having the business sense to map a process end to end, then build the agents to automate it. A year ago we had to explain this on every first call. Now prospects open the conversation with it.
In the last 90 days we've taken calls with PE firms, law firms, healthcare companies, VPN providers, construction platforms, and retail tech businesses. Some are direct competitors with each other. Nearly all came through referral.
AI SaaS won't transform your company. Giving every developer a Copilot subscription and calling it a strategy won't either. The only path to real operational ROI is combining a team that learns your business processes on the ground with engineering capacity to automate every manual workflow worth automating.
We built Limestone Digital around this thesis ten years ago. AI made it urgent. If you're looking to transform engineering delivery or automate business processes with production-grade agents, visit limestonedigital.com.
Limestone Digital retweeted
BREAKING: Claude Code can now build the eval suite that shows what your next prompt or model change breaks, before a customer does.
When Anthropic tested one change on a sample agent, the break showed up in only 1 of 2 runs. So this runs every case 3 times.
Here's the prompt:
BREAKING: Claude Code can now build the eval suite that shows what your next prompt or model change breaks, before a customer does.
When Anthropic tested one change on a sample agent, the break showed up in only 1 of 2 runs. So this runs every case 3 times.
Here's the prompt:
Once you've saved a baseline, /claude-api hillclimb can tune your prompt and model settings against it: one change per round, a random train and test split, and it reverts any change that regresses.
In Anthropic's 28 Sep 2026 write-up, a cheaper model on low effort plus a better prompt scored 90.5% on 14 held-out support tickets vs 78.6% for the original, at about a fifth of the cost.
Want to put AI to work in your operations next?
Get our free guide: how to pick your first workflow, measure the results and scale what works, with 3 case studies from healthcare, insurance and commercial lending.
thefoundation.limestonedigit…
Limestone Digital retweeted
If you want great Greek food, you go to the Greek place that has cooked the same 30 dishes for twenty years. You don’t order the moussaka off a 250-item menu at a chain that also does tacos, pasta and sushi.
I keep thinking about that when PE deal teams tell me about a new pitch from some of the bigger advisory firms: we’ll run your technical due diligence, then we’ll staff the remediation too. One contract, one relationship, and the team that found the problems already knows the codebase.
I get why that’s appealing. I’m still not sold, because diligence and delivery are different jobs done by different people.
A good diligence team reads a codebase it has never seen in a few weeks, finds what will break, puts a price on it, and writes it up so an investment committee can act. Then it moves on to the next deal.
A good delivery team moves into the portco’s stack, works next to the engineers who are already there, ships the fixes through their reviews and their CI, and is still there years later.
You hire for those two skills differently, you train for them differently and you pay for them differently. A firm that tries to be great at both usually ends up with one strong practice and one more item on the menu.
The bigger problem I see is the handoff. The report lands, the deal closes, and the findings sit in a folder because nobody owns the fix.
So let the diligence specialists do diligence. Then hand the report to a team that builds for a living. That’s where our work starts: we take the findings, staff them and work them down inside the portco after close.
Operating partners: on your last deal, who owned the fixes once the diligence report landed?
Limestone Digital retweeted
A CTO at a healthcare software company asked us to build AI agents that enroll doctors with insurance companies, a job where one missed field means the doctor doesn't get paid.
The first thing they told me was why they were sceptical. "I could build an AI demo in about four seconds for any one of them," they said. "And then it would be completely useless in the product. It doesn't work even on the one payer."
They described the industry as complex. But no single task is hard, there are just a huge number of them, and every insurer, specialty and provider type wants something slightly different. Miss one and the claim bounces.
In the CTO's words, "This isn't compliance. Your providers either can't work or don't get paid. It's top line."
They also had a framework decision hanging over them, which tool to build the agents on, and whether to wait until they'd exposed everything properly to agents first. My answer was not to overthink it. The work that makes agents useful, the rules, the examples and the tests, moves with you whichever framework you pick.
We'd build inside the cloud they already run, and connecting through the systems they already have is enough to start.
I also wanted to know something else. They had a team doing these enrolments by hand every day. "Was there any record of how that team actually does the work?". Because that's where the real rules live, and the more of that variation you capture early, the less the agent has to guess.
The last thing the CTO said is the one I wish more buyers said out loud.
They didn't want to end up dependent on us. They wanted to walk out "with a team that's stronger" than the one they had before, as opposed to just being handed an application.
An agent that only works while the vendor is in the room doesn't do anything for the business long term.
Limestone Digital retweeted
PE-backed roll-ups keep asking the same question: do we need to fix our data before we can use AI?
Most of the proposals they receive say yes. I don't agree that fixing everything has to come first.
A PE investor described one of their platform companies to me: a home-services business that had grown through acquisitions. Each business brought its own systems. Reporting was fragmented, month-end close was manual, and someone consolidated the books by hand.
The usual AI proposal starts with a migration. Move everything into one data lake, build clean data products, then give the models access. That's a year of work before anyone sees an agent do something useful.
Those systems already run the business, and the business makes money using them. We can leave the systems of record in place and build what's needed around them: controlled access, a model gateway and logging for every call.
Then choose one workflow, such as month-end reconciliation, and work across the existing systems.
That still requires data work. I'd make it specific to the workflow:
- Source mapping: which system holds each required field, and how do customer or account identifiers line up?
- Metric definitions: do the companies mean the same thing by revenue, bookings or a completed job?
- Data quality checks: which missing or inconsistent values prevent this workflow from running?
- Permissions: what can the agent read, propose or change?
- Reconciliation: how will finance check the output against the underlying records?
- Exceptions: where does uncertain or conflicting information go for human review?
That is a bounded integration problem. You can define what has to be true for the first workflow without redesigning the entire data estate.
Consolidation may still be worthwhile. You will make a better decision about it after seeing which data the workflow actually needs and where the recurring problems are.
If the first AI proposal for one of your portfolio companies starts with a migration, ask what ships in month one.
Limestone Digital retweeted
BREAKING: Claude Code can now audit its own logs and find the 3 habits burning your usage limit, for about 0.2% of our week.
The usual version overcounted our usage 2.4x and missed a third of it. This one fixes both.
Here's the prompt, plus the built-in check to run first:
Limestone Digital retweeted
Avoid hiring an AI consultancy.
Avoid hiring an AI consultancy.
Avoid hiring an AI consultancy.
Avoid hiring an AI consultancy.
Avoid hiring an AI consultancy.
Avoid hiring an AI consultancy.
THE FIRST REASON IS:
BREAKING: Claude Code can now audit its own logs and find the 3 habits burning your usage limit, for about 0.2% of our week.
The usual version overcounted our usage 2.4x and missed a third of it. This one fixes both.
Here's the prompt, plus the built-in check to run first:
On Codex, run /usage weekly first. Then use the same prompt with Codex in place of Claude Code, and replace the <logs> block: logs are in ~/.codex/sessions and ~/.codex/archived_sessions (dated folders of rollout files, each thread counted once). Usage is in token_count events: count last_token_usage only when total_token_usage went up. Fresh input is input_tokens minus cached_input_tokens, reasoning is part of output, the weights come from OpenAI's prices for your model, and the rules go in AGENTS.md.
Want to put AI to work in your operations next?
Get our free guide: how to pick your first workflow, measure the results and scale what works, with 3 case studies from healthcare, insurance and commercial lending.
thefoundation.limestonedigit…
Limestone Digital retweeted
3 mistakes I see even great CEOs make with AI:
1. Expecting AI to understand a business nobody has written down.
You buy seats, open a blank chat and ask how to improve margins. But the model has never seen a contract, read a customer complaint or heard why you lost your biggest account last year. You wouldn't hand pricing decisions to a smart stranger without explaining the business. Someone has to write down how it works and give AI that context before the answers become useful.
2. Letting every leader use it alone.
Your CFO has a great prompt for the board pack, sales has built its own, and ops hasn't started. Nobody shares what they've learned, so the lessons stay buried in individual chat histories. Ask each leader to show the team how they're using AI to get work done. Our engineers work from one shared knowledge base and one set of skills, and we can see who uses which skill and how often.
3. Chasing every new model instead of building what compounds.
A new model ships, and your leadership team spends a week comparing it with the last one. It's easy to get caught in that whirlwind when whatever you choose this quarter will be replaced next quarter. Meanwhile, the pages you write about how you price, why customers leave and what good work looks like in your business become more valuable every month, whichever model reads them.
Models are replaceable. Swap them the day a better one ships.
Your context and your judgment aren't. Spend your time there.
Limestone Digital retweeted
Every PE call I've had this quarter ends up at the same AI problem: nothing is getting shipped.
I've heard it from operating partners, CFOs, a holdco's AI lead and someone about to join a portco board.
- One fund now puts its own engineers inside each portco and calls them "almost special ops"
- a CFO sees more pull requests than ever and a codebase that isn't getting any better.
- a holdco learns the same lesson from zero in every company it buys.
- plenty of portcos have one technologist who has decided that makes them the AI strategy.
- a new board member's whole brief is choosing which AI firms to trust.
None of them are doing anything wrong but AI moved faster than their operating models did.
What helps is one workflow, shipped and measured, then taken to the next company.
That's what we've done for clients for 10 years.
Limestone Digital retweeted
BREAKING: Stanford researchers had AI agents debate stock portfolios across 35 market scenarios, and the one fix that significantly improved risk-adjusted returns was stopping the agents from agreeing with each other.
We turned their setup into one Claude Code prompt that runs a 6-agent paper-trading desk on free data:
Limestone Digital retweeted
Every week another "AI transformation partner" turns up with "agentic" in their tagline and case studies from clients nobody can name.
A CTO at a financial software company told our team about the ones who'd already pitched them. They'd sorted them into four groups before we asked.
First, the "AI-powered" outsourcers. In the CTO's words, they "talk a big game" and then it's "offshore people clicking AI buttons."
Then the "AI experts," who "come in and can talk but don't seem to do anything at all."
Then the "Applied AI" startups with their own platform, who wanted a regulated company to move its whole stack onto something that isn't SOC 2 certified yet.
And the "AI engineer" placement firms, whose plan was seven hires at $300,000 a year each.
What the CTO actually cared about came out a few minutes later: "If you guys don't produce, I just blew the rest of my year."
None of those pitches had an answer for that.
We've been an engineering firm for 10 years, since long before anyone called it "Applied AI."
I replied: "If we don't deliver, you don't pay."