---
title: "LLMs"
description: "673 posts about LLMs, summarised, each linking to the original."
---

# LLMs
> 673 posts about LLMs, summarised, each linking to the original.

## Articles

### [GPT-5 is now available in Cursor](https://yomu.fyi/post/gpt-5-is-now-available-in-cursor.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Aman Sanger
- Published: Aug 7, 2025
- Type: Announcement

Cursor has made OpenAI’s GPT-5 available to users, presenting it as a coding-focused model based on an initial internal evaluation. Five engineers report using it for long-running tasks with Background Agents, parallel foreground agents, complex debugging, and Stripe-query latency optimization, while noting that explicit instructions improved its steerability. One engineer adjusted GPT-5’s verbose default style and follow-up behavior through rules. In a monorepo with separate frontend and backend submodules, GPT-5 built a backend API endpoint and corresponding React component, regenerated protobufs, and corrected resulting type errors in one shot. During launch week, paying users receive free credits, and the announcement characterizes GPT-5 as well suited to coding and tool calling.


### [Building financial operations agents with Hypermode and Stripe](https://yomu.fyi/post/building-financial-operations-agents-with-hypermode-and-stripe.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: William Lyon
- Published: Aug 6, 2025
- Type: Tutorial

Hypermode Agents and Stripe can be combined to create domain-specific financial operations agents from natural-language descriptions rather than conventional code. The workflow uses Hypermode’s Concierge to generate a system prompt, then connects the agent to Stripe through the Stripe Model Context Protocol (MCP) server and optionally to services such as Notion, Slack, and Google Calendar. With a restricted Stripe API key and sandbox data, the agent can retrieve policies, inspect customer and transaction history, apply refund rules, process payments, create invoices, and analyze subscriptions for metrics such as MRR. The examples describe partial refund decisions, onboarding workflows, campaign suggestions, and populated test environments, while the guidance recommends prompt iteration, human approval for high-value transactions, and monitoring and logging for compliance and improvement.


### [Leveraging multimodal LLMs for Shopify’s global catalogue: Recap of expo talk at ICLR 2025](https://yomu.fyi/post/leveraging-multimodal-llms-for-shopify-s-global-catalogue-recap-of-exp.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: Jul 16, 2025
- Type: Explainer

Shopify’s Global Catalogue addresses fragmented, multilingual, multimodal product data that makes semantic search, faceting, matching, and AI-driven discovery difficult across millions of merchants. The system combines product data, understanding, matching, and reconciliation layers to standardize metadata, identify duplicate listings, and create canonical records with Universal Product IDs. Shopify fine-tunes vision large language models for multiple tasks per catalogue entity, while streaming infrastructure processes more than 10 million product updates daily and serves 40 million multimodal LLM-powered inferences. The resulting data supports merchant-admin suggestions, search, recommendations, embeddings, and conversational commerce, although scalability, accuracy, latency, model consolidation, graph reasoning, and continuous retraining remain active challenges.


### [How To Build Agents Users Can Trust](https://yomu.fyi/post/how-to-build-agents-users-can-trust.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: CJ Enright, Will Koh, Felix Zhang
- Published: Jul 10, 2025
- Type: Explainer

Ramp describes how it built and shipped LLM-backed agents for expense management, focusing on the trust risks created by low-quality or unexpected finance outputs. It recommends choosing ambiguous, high-volume problems with asymmetric upside, then combining reasoning and citations grounded in product or user-provided context with an explicit “Needs review” path when the agent is unsure. The policy agent uses expense policies to approve, reject, or escalate expenses, while deterministic rules such as dollar limits, vendor blocklists, and category restrictions constrain autonomy. Ramp reports that more than 65% of approvals are fully handled by the agent, while users can progressively move from suggestions to autonomous actions through workflow-based controls and evaluation.


### [Augmented commerce: Machine learning at Shopify](https://yomu.fyi/post/augmented-commerce-machine-learning-at-shopify.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: Jul 4, 2025
- Type: Explainer

Shopify frames commerce as a complex, continuous optimization problem in which merchants have different definitions of success and need support across the business lifecycle. Its machine-learning work uses a historical dataset covering millions of businesses to optimize product metadata, transaction fraud assessment, merchant assistance, product discovery, capital decisions, behavioral modeling, and search query rewriting. The systems include fine-tuned Qwen multimodal models, LLaMa models and MCPs for Sidekick, Nomic embeddings for billions of products, a tabular transformer for forecasting merchant GMV, and experiments with HSTU sequence models. To support this work, Shopify partners with GCP, Nebius, CentML, and Toloka, while providing access to GPUs, data services, frontier models, and internal tooling; the post also presents these efforts as part of its hiring pitch.


### [Introducing Roast: Structured AI workflows made easy](https://yomu.fyi/post/introducing-roast-structured-ai-workflows-made-easy.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: Jun 18, 2025
- Type: Announcement

Shopify’s Augmented Engineering Developer Experience team built and open-sourced Roast to make AI-assisted developer workflows more reliable than free-form agents operating across large codebases. Roast is a convention-oriented orchestration framework that combines non-deterministic AI behavior with ordinary code execution through YAML workflows, Markdown prompts, shell commands, Ruby steps, and parallel or conditional control flow. Its shared context, built-in tools, Claude Code integration through CodingAgent, and automatic session replay support workflows that are version-controlled, testable, resumable, and adaptive within defined guardrails. Shopify reports using it to analyze test quality at scale, add Sorbet annotations through the Boba workflow, aggregate competitive intelligence, and research code history, while the project is distributed as a Ruby gem and supports AI providers through Raix.


### [How Ramp Fixes Merchant Matches with AI](https://yomu.fyi/post/how-ramp-fixes-merchant-matches-with-ai.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Chami Lamelas, Anton Biryukov
- Published: Jun 16, 2025
- Type: Problem & solution

Ramp describes the difficulty of mapping payment-processor card acceptor data to useful merchant records when names, MCCs, and locations are vague, misleading, or affected by rebranding. Users can submit a replacement merchant name, website, and category, but deciding whether the request is legitimate and whether to update an existing record or create one requires additional context from related receipts, extracted line items, and transaction memos. Ramp addresses this with an AI agent built around an LLM, embeddings, rapid online analytical processing queries, multimodal retrieval-augmented generation, and guardrails that constrain permitted changes. The agent handles requests in under 10 seconds, and monitoring indicates it improves nearly 99% of transaction classifications, while fewer than 10% receive a second correction request. The same flow has also been extended to batch remapping and credit-card statement matching.


### [Yes, You Can Use AI in Our Interviews. In fact, we insist](https://yomu.fyi/post/yes-you-can-use-ai-in-our-interviews-in-fact-we-insist.md)
- Company: [Canva](https://yomu.fyi/company/canva.md)
- Author: Simon Newton
- Published: Jun 11, 2025
- Type: Announcement

Canva has updated its technical hiring process to require backend, machine learning, and frontend engineering candidates to utilize artificial intelligence tools such as Copilot, Cursor, and Claude during interviews. The transition addresses the limitations of traditional computer science fundamentals tests, which focused on writing algorithmic code from scratch even though AI assistants can generate complete solutions in seconds. To better evaluate on-the-job engineering capabilities, the company replaced its legacy screening with an AI-assisted coding competency that features complex, ambiguous product challenges such as designing an airport control system. Interviewers assess how candidates clarify requirements, guide tools on subtasks, debug flawed output, and verify that AI-generated code meets production quality standards. Candidates receive advance notice of these expectations, helping ensure prospective hires demonstrate strong engineering judgment when collaborating with assistive coding technologies.


### [Odysseus to AI: Matt Greenwood on the Dev Interrupted Podcast](https://yomu.fyi/post/odysseus-to-ai-matt-greenwood-on-the-dev-interrupted-podcast.md)
- Company: [Two Sigma](https://yomu.fyi/company/two-sigma.md)
- Author: Emily Majewski
- Published: May 27, 2025
- Type: Explainer

Matt Greenwood, Chief Innovation Officer at Two Sigma, outlines strategies for managing technological change, integrating artificial intelligence into systematic investment, and building supportive engineering organizations. Greenwood describes sustained innovation through the S-curve using an epsilon and omega approach, combining small iterative steps with a broad long-term vision. To direct resources amid rapid advances in machine learning and large language models, he presents a functional framework categorizing AI roles into advisory insights, oracle outcome validation, operational task automation, and agentic coordination. This categorization aims to automate routine workflows while keeping human creativity, control, and higher-level thinking at the center of the investment process. Additionally, the organization fosters employee engagement through initiatives such as an internal hacker lab where cross-disciplinary teams build projects ranging from robots to racing simulators.


### [From failure to success: The birth of GrabGPT, Grab’s internal ChatGPT](https://yomu.fyi/post/from-failure-to-success-the-birth-of-grabgpt-grab-s-internal-chatgpt.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Wenbo Wei
- Published: May 19, 2025
- Type: Problem & solution

In March 2023, an effort to reduce repetitive questions overwhelming Grab’s ML Platform support channels began as a chatbot for platform documentation and became GrabGPT, an internal ChatGPT-like tool. The initial chatbot used chatbot-ui and more than 20,000 words of Q&A documentation, but GPT-3.5-turbo’s 8,000-token limit forced summaries below 800 words; embedding search also performed poorly, so the approach was abandoned. The pivot extended existing frameworks, added Google login, and deployed a tool through Grab’s catwalk model-serving platform, later named GrabGPT. It reached 300 registered users on day one, more than 3,000 users and 600 daily active users by month three, and nearly all Grabbers according to the post, with private routing, global accessibility, multi-provider model support, and auditable interactions cited as reasons for adoption.


### [Streamlining RiskOps with the SOP agent framework](https://yomu.fyi/post/streamlining-riskops-with-the-sop-agent-framework.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Fujiao Liu
- Published: May 8, 2025
- Type: Problem & solution

Risk Operations teams investigating Account Takeover (ATO) cases must gather data across systems, run SQL queries, and make decisions under pressure, creating delays and error risk. The SOP-driven LLM agent framework represents the workflow as a natural-language, indentation-based tree whose steps specify queries, external functions, and decision criteria. During execution, the SOP planner navigates the tree and produces JSON-formatted instructions, while a Worker Agent invokes APIs or SQL queries and stores results in a feedback loop. The process ends by synthesising investigation data into a report and final decision. In reported results, handling time fell from 22 to 3 minutes per ticket, 87% of ATO cases were automated since launch, and the error rate was zero.


### [Evolution of Product Classification at Shopify: From Categories to Comprehensive Product Understanding](https://yomu.fyi/post/evolution-of-product-classification-at-shopify-from-categories-to-comp.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: May 8, 2025
- Type: Explainer

Shopify’s product classification system evolved from a 2018 logistic-regression model using TF-IDF into a product-understanding platform designed to capture categories, attributes, characteristics, metadata, and content-safety signals. A 2020 multimodal image-and-text approach improved classification, but growing product complexity led Shopify to combine Vision Language Models with its Standard Product Taxonomy, spanning more than 10,000 categories and over 1,000 attributes across more than 26 business verticals. The production pipeline uses two-stage category and attribute prediction, with category context shaping the second call, and runs on Kubernetes with NVIDIA GPUs; FP8 quantization, Nvidia Dynamo in-flight batching, and KV caching improve inference efficiency. A multi-LLM annotation system independently evaluates products and uses arbitration when models disagree, helping build training data for consistent predictions. The resulting system processes over 30 million predictions daily, delivers an 85% predicted-category acceptance rate, and doubles hierarchical precision and recall versus the earlier neural network approach.


### [Sessions 2025 Developer Track resources](https://yomu.fyi/post/sessions-2025-developer-track-resources.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Ashley Ansari
- Published: May 7, 2025
- Type: Announcement

Stripe’s Sessions 2025 developer track recap presents new products, APIs, and enhancements for building and managing financial infrastructure. Stripe’s Workflows provides visual automation for real-time events, with more than 600 triggers, branching logic, dynamic fields, and built-in error handling, while the MCP server and agent toolkit connect AI tools and agents to Stripe documentation, account data, APIs, and financial capabilities. Accounts v2 unifies connected-account management, and fully localized Connect Mobile Embedded Components bring onboarding to iOS and Android; the Payment Element also gains support for the Checkout Sessions API. New Stripe Apps UI components, generally available Sandboxes, Organization-wide sharing of customers and payment methods, and conversational documentation extend customization, testing, and collaboration.


### [Introducing the SOP-driven LLM agent frameworks](https://yomu.fyi/post/introducing-the-sop-driven-llm-agent-frameworks.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Fujiao Liu
- Published: Apr 25, 2025
- Type: Announcement

Grab introduces an LLM agent framework that uses Standard Operating Procedures (SOPs) to guide enterprise automation and improve consistency in complex processes. It represents SOPs as trees of action and decision nodes, while a planner uses Depth-First Search, prompt generation, and backtracking to direct an LLM-powered worker agent; context compression and limited APIs are used to address hallucination and efficiency concerns. An SOP editor, plugins for APIs, Python, and SQL, workflows, a GRAG pipeline, playground, multilingual user agent, and state stack extend the framework’s capabilities. Reported evaluations include over 99.8% accuracy, an Account Takeover Investigations bot automating 87% of cases and reducing investigation time from 23 minutes to three, and fraud investigations cutting AHT by 45% and saving over 300 man-hours monthly.


### [A Fall Internship at Ramp: Improving Reimbursements](https://yomu.fyi/post/a-fall-internship-at-ramp-improving-reimbursements.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Sat Arora
- Published: Apr 3, 2025
- Type: Explainer

During a fall internship at Ramp, a backend software engineering intern worked on the reimbursements team and describes projects that improved reimbursement flows while providing full-stack experience. One early change clarified multi-currency mileage reimbursements by showing both the expense currency and the payout currency, while later work overhauled mileage support with live navigation storage, frequent-trip recommendations, commute deductions, and automatic e-receipts. The post also discusses using LLMs to predict merchant categories from receipt text, enhancing merchant matching, and adding monitoring and alerts for OCR categorization errors. The reflection emphasizes measuring feature usage and outcomes, writing and revising specifications before implementation, leaving reusable code, and using Ramp’s transparent documentation and collaborative support. The internship concluded with a return to the University of Waterloo planned for 2025.


### [Stripe’s new AI Assistant in VS Code](https://yomu.fyi/post/stripe-s-new-ai-assistant-in-vs-code.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Mathew Varughese
- Published: Mar 18, 2025
- Type: Announcement

Stripe has introduced an AI Assistant in its VS Code extension to answer developer questions using current Stripe knowledge rather than relying on LLM pre-training. The extension retrieves API reference entries, integration guides, code examples, and curated summaries of developer Discord threads, while inserting the user’s API key into generated snippets and supporting either GitHub Copilot’s @stripe agent or its own chat interface. Its retrieval pipeline classifies queries, combines BM25 keyword and k-nearest-neighbor embedding search, reranks results, and sends selected sources, code, user code, and the question to Claude Sonnet through a RAG prompt. A nightly Temporal workflow refreshes indexed content, while evaluation uses golden and synthetic datasets, Mean Reciprocal Rank, and human and automated review. On its synthetic test dataset, the system includes the best source about 91.11% of the time and reports an MRR of about 78%.


### [Importing sales data from Stripe into AWS](https://yomu.fyi/post/importing-sales-data-from-stripe-into-aws.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Hidetaka Okamoto
- Published: Mar 4, 2025
- Type: Tutorial

The article presents a low-code method for analyzing Stripe business and customer data and moving scheduled report results into AWS. Stripe Sigma lets users query payment, subscription, and plan-related data with SQL, while Sigma Assistant can generate and execute queries from natural-language prompts such as cancellation analysis. For delivery, the article uses the sigma.scheduled\_query\_run.created event and Stripe's Event Destination to Amazon EventBridge, where a partner event bus and event rule trigger AWS services without a separate public webhook API. Its Lambda example downloads the report CSV with the Stripe API key, parses it into JavaScript objects, and publishes the result through Amazon SNS; the same event-driven pattern can support Lambda, Step Functions, or Glue workflows.


### [Behind the scenes of Canva's DesignDNA campaign](https://yomu.fyi/post/behind-the-scenes-of-canva-s-designdna-campaign.md)
- Company: [Canva](https://yomu.fyi/company/canva.md)
- Author: Divya Patel
- Published: Feb 24, 2025
- Type: Problem & solution

Canva launched DesignDNA in December 2024 as a personalized year-in-review campaign to highlight user achievements and showcase generative AI capabilities. Because internal privacy rules strictly prohibited inspecting personal designs, the engineering and creative teams inferred user preferences from the style and theme metadata tags on public templates. An initial keyword-matching algorithm paired 95% of users with one of seven emerging design trends, while generative AI keyword expansion increased coverage to 99%. The team also synthesized over one million localized poems and distinct design personalities using tools like Magic Write and Dream Lab. Finally, dynamic Canva template elements populated through URL parameters assembled 95 million distinct multi-page stories across nine locales.


### [Did Semgrep Just Get A Lot More Interesting?](https://yomu.fyi/post/did-semgrep-just-get-a-lot-more-interesting.md)
- Company: [Fly.io](https://yomu.fyi/company/fly-io.md)
- Published: Feb 10, 2025
- Type: Explainer

Thomas Ptacek considers whether LLM-driven coding agents could make Semgrep more useful by closing the loop between code generation, execution, and automated repair. He describes Semgrep as a semantics-aware code-search tool whose symbolic variable placeholders and ordinary code can express vulnerability patterns, while noting that teams rarely have time to build extensive rule libraries. Drawing on Cursor’s rules feature, including rules that help organize or generate other rules, he proposes having an agent observe runtime errors, generalize fixes into unit tests, and generate Semgrep rules for the underlying bug. The proposed workflow would test each rule with positive and negative controls, save it, scan the codebase, and fix newly found instances. The post concludes that this adaptive process may be more compelling than predicting every failure in advance.


### [AI Core Team Lead Mike Schuster on How to Get the Most From LLMs](https://yomu.fyi/post/ai-core-team-lead-mike-schuster-on-how-to-get-the-most-from-llms.md)
- Company: [Two Sigma](https://yomu.fyi/company/two-sigma.md)
- Author: Joy Looney
- Published: Feb 4, 2025
- Type: Explainer

Mike Schuster, Head of the AI Core Team at Two Sigma, advocates for grounding large language model adoption in practical tasks rather than speculative industry hype. Realistic enterprise applications focus on accelerating data processing, running faster experiments, and extracting domain-specific features from transcripts such as earnings calls and Federal Reserve speeches via prompt engineering. Because financial data faces inherent volume limits across trading days, successful deployments require multidisciplinary human teams to balance rapid technical experimentation with rigorous domain expertise and analytical reasoning. Schuster also dismisses predictions that programming will become obsolete, comparing coding to learning a musical instrument that cultivates structured thinking, problem decomposition, and scientific common sense essential for building complex predictive models.


[Newer posts](https://yomu.fyi/topic/llm/page/30.md) · [Older posts](https://yomu.fyi/topic/llm/page/32.md)