Principle · MoneyYou cannot dump a massive amount of retrieved context back to your agent; you need a router and summarizer. The router sends incoming prompts to the right place at the beginning, deciding who should handle it. The summarizer takes data from synced context and live context, summarizes it, and sends it back to the agent that sent the prompt.
AI Engineer · Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge
Principle · MoneyThe definition of 'which customer was upset last week' can mean something very different to one company versus another. Companies need skills like 'how do we determine if a customer is happy' encoded in their context graph. Document company processes — e.g., what to do when a customer complains and how to route to the right place — as skills in the context graph.
AI Engineer · Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge
Principle · MoneyUse live MCP lookups for simple, single-action queries (e.g., a Stripe lookup for a specific customer). If you need semantic lookups or analysis beyond a simple lookup across a vast dataset, you have to sync a copy of the data. Prefer live API calls when you know you'll have simple lookups and retrievals because they're easier to build, easier to add on, and cheaper to run.
AI Engineer · Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge
Principle · MoneyEvery answer has to be traceable — never leave yourself in a position where your AI made a bad decision and you have no idea why. Making business-critical decisions on versioned or outdated data without provenance is dangerous: you need to know where data came from, when it was fetched, under what ID and scopes, who accessed it, what permissions were used, whether it was transformed, what it originally looked like, and what should invalidate it. Letting AI make decisions on data synced a year ago without checking provenance leads to bad business-critical decisions. Build provenance tracking into your platform so you can investigate when something goes wrong — dropping provenance tracking leaves you unable to investigate.
AI Engineer · Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge
Principle · MoneyViren Baraiya's take-away slide: the responsibility of a non-deterministic agent is to plan what should happen next — not to actually do things; the harness is the one that does the actual execution. The harness is a deterministic piece of code that actually understands what is involved in executing a piece of work. When the agent says a cluster is unhealthy and should be restarted, the harness should decide how to restart the cluster and what is involved in restarting it. This is the clear separation between, as he would like to call it, the brains and the hands: the LLM is the brain, the harness is the hands — the agent writes the plan, the harness executes the plan.
AI Engineer · Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Principle · MoneyViren Baraiya's operating rule: if the agent writes the plan, the harness executes the plan. When the LLM outputs steps for what should happen next, the harness executes them rather than the LLM doing it directly. Depending on how far ahead the agent can plan, you can execute multiple steps at a time.
AI Engineer · Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Principle · MoneyViren Baraiya argues that when determinism matters, the harness should deliver it rather than the LLM. If the LLM decides how to restart a cluster, you lose determinism and every restart could be different. When the agent plans a cluster restart, the harness executes it deterministically so every cluster restart is identical. Non-determinism slipping into critical operations like payments or cluster restarts costs you predictability and safety.
AI Engineer · Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Principle · MoneyThe last mile is where someone has to read the code, test the behavior, own the trade-offs, notice the missing requirements, and decide whether the thing deserves to be part of the system.
AI Engineer · Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
Principle · MoneyNot every line of code needs to be personally read, blessed, and understood in isolation — that has never really been the standard, and large systems have always contained more detail than any one person can hold in their head. But the logic has to be understood: the main flows, the boundaries, the data model, and product behaviors.
AI Engineer · Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
PrincipleFrom the beginning, the team's hypothesis has been that one of the big bottlenecks in automated materials discovery is automatic characterization: mixing powders is easy, but without automated characterization and analysis you can't intelligently decide the next step. Mixing powders randomly yields little benefit — the value comes from automatic characterization and closing the loop with simulations, so you can try many things, make informed decisions, and plan the next day.
Latent.Space · Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
PrincipleRather than training on the final output of science, train on the process of doing science — the process data is the scarce, valuable resource. Build reasoning traces over entire scientific campaigns, not individual experiments: capture the full lineage of conversations, intuitions, lab executions, computations, and code, stitched together. The team says this type of data basically doesn't exist anywhere else and that they spend much of their time getting the full lineage of the scientific process into the model.
Latent.Space · Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
PrincipleA classification algorithm can't be trained on all-positive samples — you need negative samples, which is why unpublished failed syntheses are a critical missing data source in materials science. The team deliberately seeks null results and learns from them: a null result means you intended to produce a structure and all evidence points to you not producing it, and sometimes the null reveals a previously unidentified structure. A string of negative results followed by a positive one is valuable 'process engineering' data — the iteration path to success is itself a training signal. They also run negative controls in materials experiments, because impurity phases can kill the property you're measuring, so controls are needed to distinguish real nulls from contamination.
Latent.Space · Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Principle · MoneyAs a product leader, the ideal time horizon to live in is two to three months out, not years. Predictions of the future years out are almost always wrong, so don't plan too far ahead. Tara keeps a personal doc of incorrectly predicted things she thought were going to happen and didn't, to remind herself of her inability to predict years out. If you build exactly for today, you're going to get left behind.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyTara Sesha's bar for the AI era: aim products at where the models will be in two to three months, rather than being overly anchored in the present or overly futuristic and unusable. The product should be valuable, cared about by users, surprisingly great, in line with model capabilities, and get out of the model's way.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyTara Sesha argues there are so many practical product considerations that the use case matters most in the single-vs-multi agent decision. Tactically, consider data access and permissions — e.g., switching between a service account or your account and how to manifest that understandably — and whether a single agent should have segmented memory, almost becoming a different agent when it joins a private Slack channel. Answer by going back to the specific use case and thinking through edge cases: how memory should behave, how it talks to each person, and whether it uses their credentials or a universal set.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyOpenAI thinks about ChatGPT as a platform and decides what functionality natively goes in versus what can be built by first-party or third-party developers as plugins or additional interfaces. The approach: structure capabilities in layers, exposing them as hooks developers can build cohesive experiences on; offer an array of different tools (e.g., a plugin to get all your meetings data and understand what to do next); and if pre-built or ecosystem tools aren't available for a task, computer use serves as a fallback layer so the user can still accomplish their task.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyWorking with research is quite different from working with engineering — a realization from coming to OpenAI. To collaborate: come with very specific use cases and a clear idea of what users want and their goals; bring sample readings — understand literally what the session was, what it looked like, and why the model didn't do what it needed to do; and learn to write good evals, writing them as much as possible — the most important thing. The ideal deliverable to post-training is showing that with a specific prompt and skills, a desired outcome was achieved, so the capability can be post-trained into the model from the beginning. Collaboration starts with understanding it's a wholly different way of working, then getting good enough at bringing specific user data so researchers trust you,
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyThe appropriate planning cadence depends on understanding the pace of the market you're in — it's not the same for every business. Stripe's business dynamics look largely similar to how they looked before, so Stripe PMs can model bull/bear/base cases and plan many months out — and still do their annual planning — unlike OpenAI's business. Given the pace and dynamics of your market, determine at what cadence you should be planning.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyTara Sesha describes OpenAI's quality bar: ship the product internally, have everyone use it, and check that it is retaining well, that people find something delightful or surprisingly great, that it unlocks a new use case of the models or does something novel, and that it is additive for users — unlocking additional value — before shipping externally.
endorsed
Lenny's Podcast · Stop planning for 2027: how OpenAI builds product 90 days at a time | Tara Sesha and Nan Yu (OpenAI)
Principle · MoneyMarc Lore advises building the business by offering customers the value proposition you know you'll be able to offer at scale, even before you achieve scale — which means accepting losses in the meantime.
Foundr · From $0 to $5 BILLION - The Blueprint for Building Billion-Dollar Startups