I've been building loads of personal software in the loop where I just build the app directly on top of claude code. No agent framework. Just smash claude code into exe dev machine, send stuff to it via claude code signals and let it vibe code whatever helpers it needs to create a good looking UI. Full personal context is the most important part here. If the agent can just do whatever you can do from your computer your personal vibe coded apps become a super power.

I have always considered @milesgrimshaw one of the smartest investors in venture. I remember Sept 2023, Miles came to our recording studio in London having just joined the @benchmark partnership. At the time, he had done one deal; a small company called @LangChain. Unknown to many but Miles raved about the founder @hwchase17. His excitement for the company was palpable. Today the company is worth $1.2BN and serves 35% of the Fortune 500. The other day I sat down with Harrison to discuss the big questions of the day and he allowed me to add my notes from the discussion below. -- 1. What Percent of Developer Salary Do You Spend on Coding Tools and How Has It Changed? LangChain spends roughly 30% of its engineering salary on coding tools, a share that has fallen over the last two months even as token usage has gone up. The team tracks coding agent usage in LangSmith, sets budgets the VP of engineering can raise, and controls the harness. Its in-house cloud coding agent uses prompt caching and routing to cut costs. What will this be in 12 months @BrendanFoody? 2. What Will Happen to the Inference Market? Harrison says he underestimated the demand for inference and for coding agents, both far bigger markets than he expected three or four years ago. Echoing Eric Vishria's line that "Everything just works," he believes any inference provider will work, and he does not expect demand to drop anytime soon. What does no one see about the inference market that everyone should see @spdholakia? 3. Why Harnesses Need to Be Neutral Companies want to be able to switch models, but the harness can be tightly tied to a model, and context today is intricately linked to the harness. The harness connects the model to data, APIs and memory. If memory is built in a way that is linked to the harness, and the harness is linked to the model, the company ends up stuck. Love to hear your thoughts on this one man @EnoReyes 4. Why the Memory Layer Will Become More and More Important and How Instinct Crushed It Memory is rare in agents today but will be incredibly common in the next few years. Instinct and Muse have nailed personalization and learning, so the product feels like it is for the individual user, through its tone or proactive follow-ups. Harrison still sees memory as super early. What does no one see that everyone should see about the state of memory and where it goes @noahrshinn @mvernal? 5. Will We Have One Horizontal Agent or Tons of Vertical Agents in the Consumer Realm? Consumers will have both, with horizontal agents interacting with vertical ones. Most apps should have a vertical agent because they can learn more about how a user interacts with them than a general agent can. Wrapping an app's many APIs in a single natural language agent also gives horizontal agents a better experience than raw APIs. Love to hear your thoughts on this @FDavidsonT 6. What Do Large Enterprises Care Most About Today? Cost has risen as a concern for large enterprises, though it still ranks below accuracy and above latency. Security is a bigger concern for large enterprises but still sits below accuracy and cost. 7. Why Is Benchmark the Best Fund? Benchmark invested in LangChain when it was just Harrison and Ankush, and the founders treated the firm as a third co-founder. As the company grew from two people to around 400, Benchmark has been its most consistent partner. @chetanp what does no one know about how Benchmark works with founders that everyone should know?

The threat of AI surveillance is underrated. AI gets better the more you share - it makes sense out of the mess of data we give it. That also means it’s easier for companies and governments to surveil specific people. We’re likely only a couple years away from governments having the ability to query data on individuals as easy as asking ChatGPT.

The future is open memory, open context.

Ontology Is All You Need

Ready to make the switch? claude.com/import-memory

Context is king for AI agents. There’s going to be a massive premium in the future on having up-to-date context for all your most important best practices, decisions, roadmap items, specs, marketing materials, and other critical knowledge across your company. People get a lot of context “for free” in a company. They know where they work, they have people next to them they work with, they can remember the rough outline of the company’s most recent quarterly goals to know if something seems good or bad to work on. AI agents, on the other hand, come in overly eager and ready to work on whatever you give them. At one moment they’re a lawyer for one company and an engineer for the next. This is why context remains absolutely critical for them to execute well on what you want. The teams and companies that take this seriously will have huge leverage and be steps ahead of those that don’t.

My feeling is that we will need AI personal assistants. But the model in which you provide access to your email, calendar and files is broken. Your secretary (if you have one) has access you your email and calendar? Usually not. An AI assistant entry point should be WhatsApp/Telegram and email. And it will then have it's calendar and private file system, and can message people on your behalf, but with a clearly distinguished account. Like a secretary.

What if technology didn’t feel so… hollow? Some friends and I just released a manifesto about a world where tech leaves us feeling nourished (along with an evolving list of theses about how we can build it) resonantcomputing.org