All Content

- Why SDKs are now central to API quality: most developers use APIs through SDKs rather than raw HTTP, so type safety, ergonomics, and documentation increasingly define the overall developer experience - Stainless’s core idea: using OpenAPI plus lightweight configuration to generate high-quality SDKs, docs, CLIs, and MCP servers, helping teams deliver a more polished, scalable, and Stripe-level API experience - What they demoed + discussed: generating multi-language SDKs from a single spec, layering custom functionality on top of generated clients, and how modern API tooling is evolving to better support AI agents, developer workflows, and long-term maintainability

- Why multimodal is a shift: video, images, and audio are becoming first-class AI data, but most stacks still treat them as opaque files, leading to brittle pipelines and high maintenance overhead - Pixeltable’s core idea: a more “database-like,” declarative table/view model with native media types, built-in transforms + model inference, and strong lineage/observability - What we demoed + discussed: ingesting video by URL, extracting/transcribing/chunking, building embeddings for semantic search, and an auto-crop example, plus Q&A on flexibility (UDFs/models), private deployment, and scaling direction

In this session, we explored why agentic AI can be risky: models can sound confident while hallucinating, skipping required steps, or overstepping their authority. We covered semantic authorization, granting permissions based on meaning, context, and output quality, and demoed a control-plane pattern that enforces pre-checks, calibrates thresholds against known-good responses, and records a full audit trail tied to a human owner for real workflows.

During the discussion with Span, we talked about a challenge many eng leaders are navigating: AI is increasing coding throughput, but overall delivery impact can feel flat as code review, rework, and quality bottlenecks emerge. We also discussed what it would take to measure AI impact day-to-day: going beyond vanity metrics and surveys to instrument the full SDLC, surface actionable insights, and tie adoption to quality and cost.

In this demo, we explore how Superlink is addressing the challenges language models face when processing structured data. By creating custom vector embedding models, they improve the efficiency of encoding and retrieving information from complex data sets. Their approach simplifies the process with a pipeline for data ingestion, embedding, and query matching, making it easier to extract valuable insights from varied data types. Superlink’s platform provides flexible deployment options, including personalized recommendations based on user behavior, and is built to integrate seamlessly with major cloud providers. Their vendor lock-in strategy focuses on compute rather than storage, offering a powerful solution for AI engineers working with large datasets. This demo gives us a closer look at Superlink’s innovations and how they could shape future advancements in machine learning and data management.

In this demo, we explore Augment Code’s innovative use of AI to enhance the development process within popular IDEs like VS Code and JetBrains. By enabling seamless pair programming, Augment AI provides developers with a deeper understanding of their codebase, highlighting details and snippets that other AI tools often miss. Its ability to leverage contextual documentation and historical changes gives developers a significant edge in navigating and optimizing their code. Augment’s advanced code completion capabilities offer a smarter, more intuitive coding experience by predicting and suggesting relevant code based on the entire project context. This session demonstrates how Augment is pushing the boundaries of AI-assisted development, making it easier for developers to write cleaner, more efficient code.

Throughout this discussion, we explored various aspects of DevTools, from emerging trends like AI-powered tools such as GitHub Co-pilot, JetBrains AI Assistant, Augment and Slack bot to favorite tools like Backstage, FireHydrant, Blameless and Rootly. Besides, our conversation also delved into topics like onboarding automation, DORA metrics, and the build vs. buy decision.