LangChain launched Engine, an agent that autonomously investigates traces and drafts PRs to improve other agents.
“We're working towards a future where agents improve themselves.”
OpenAI DevDay
- Dates
- 2026-04-10
- Location
- San Francisco, CA
- Ecosystem
- frontier lab
- Importance
- 9/10
Related coverage & signals
OpenAI's computer use agents are now '180 degrees different,' approaching superhuman software operation speed
“180 degrees different”
Agent infrastructure is now commoditized by cloud platforms, making context the new competitive frontier
“They're all taxes one has to pay in order to get an agent out there to play the game.”
Google expands Gemini API Managed Agents with Gemini 3.6 Flash, hooks, and production-ready features.
Google's Interactions API reaches GA, unifying all Gemini models under one stateful interface
“It is an agent-first ecosystem.”
Paper uses HTML/CSS as rendering engine to make design tools natively agent-compatible
“design is this great differentiator. And if you look at every great company of the last 10 20 years, basically all of them have exceptional design.”
Hugging Face showcases CUGA, a lightweight harness with two dozen working examples for building real agentic apps.
Microsoft launches Work IQ Developer Tools as a guided Copilot plugin development lifecycle wrapper
Microsoft Build 2026 debuts agent-friendly terminal, WSL containers, and 75+ Unix utilities for Windows developers
“intelligent terminal, which is an experimental terminal experience that we're providing that makes it more seamless to work with agents while working with a terminal prompt”
Warp's Ben Holmes shows how LLMs can transform scattered notes into navigable, interconnected knowledge bases.
“It's very easy to do these days now that agents can access your machine and use HTML.”
.NET Aspire is being extended to simplify building and deploying agent-based distributed apps.
“The latest way we've been talking about Aspire is that any modern distributed app you could pick anything out of any of these boxes.”
datasette-agent adds inline agent chat accessible via keyboard shortcut in Datasette UI
GitHub's agent capabilities remain underutilized among developers unfamiliar with platform depth.
OpenAI DevDay 2026 launched Dots always-on agents, GPT-6.1 Sol, and major platform APIs
OpenAI DevDay 2026 unveiled GPT-6 Astra alongside 20+ developer announcements
SpaceXAI launches Grok 4.6, a 1.5T model targeting knowledge work agents
“builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work”
Greg Brockman confirms ChatGPT Chat and Work modes will merge by end of 2026
Google I/O 2026 repositioned Gemini as consumer AI surface and developer agent platform with three major launches
“Google used I/O to reposition Gemini as both a consumer AI surface and a developer/agent platform, with three core technical announcements: Gemini 3.5 Flash for fast agentic/coding workloads, Gemini Omni for multimodal generation/editing starting with video, and a broader Antigravity agent stack spanning desktop/CLI”
Meta's Muse is the first consumer-accessible agentic AI with persistent Linux VMs per user
“It's the first consumer-accessible agentic AI system, and Meta has truly done an amazing job with that. But it's a genuinely open question whether consumers have any understanding what this means.”
Open-source coding agent OpenCode hit 13M monthly active users with 20x growth in 2026
“We also recently started processing around 7 trillion tokens per day. Uh for context, uh Open Router does a total of around 6 trillion.”
YC's Garry Tan claims 400x personal coding productivity gain with AI agents.
“One person does what used to take a thousand people. And I don't mean that as a metaphor. I mean that mechanically this year, the people in this room will do this.”
Databricks launched Omnigent, an open-source 'meta-harness' layer on top of the agentic stack to make agents effective at scale.
“we call it a meta harness of harnesses, if you know what an agent harness is.”
Databricks open-sources Omnigent, a meta-harness to combine, control, and share agents across Claude Code, Codex, Cursor, and more.
“CDC is brittle enough to joke that it means “continuous data corruption,””
Google DeepMind adds computer use capabilities to its Gemini 3.5 Flash model.
Clay runs over 350 million go-to-market AI agents monthly, processing trillions of tokens per week.
“We run this over 350 million times a month. It processes trillions of tokens every week.”
Z.ai's open-weight GLM-5.2 marks a step-change for open agentic models, rivaling top labs.
“minor version numbers can have AI models crossing meaningful user experience thresholds”
Microsoft Foundry assembles agents, tuning, evals, and OpenEnv into an owned reinforcement-learning loop that improves over time.
“the durable asset is not the model you rent, it is the learning loop you own”
Apple opens Core AI, its on-device inference framework powering Apple Intelligence, to all developers.
“Core AI is the inference framework powering on-device Apple Intelligence. And now, it's available for you to use, bringing that same power to your app's own intelligence.”
Apple opens its Private Cloud Compute server LLM to third-party developers via the Foundation Models framework at WWDC26.
“And now, by changing just one line of code, you can switch to the new server model on PCC.”
AI lets enterprises finally capture human capital and tacit knowledge, but humans stay valuable by finding gaps.
“Every company is going to have the human capital that is still going to be super valuable because humans and their ability to find the gaps that exist at all times is going to be the way we all will create value”
Microsoft unveiled a new GitHub Copilot desktop app that runs parallel agentic coding sessions and auto-merges PRs.
“When I enable agent merge, Copilot will continuously babysit this PR through CI checks, code review, and merge conflicts.”
Google launches Anti-gravity agentic platform and Gemma 4 hits 100M downloads in first month
“It's our smartest open model yet. It's purposebuilt for advanced reasoning, agentic workflows, and the response has been incredible. 100 million downloads in the first month and it's pushing Gemma downloads past half a billion.”
All major AI model labs are now also building agents as their core product
LangChain achieved 64% cost reduction in their coding agent via model routing with no quality loss
“we were able to see a 64% reduction in median cost per thread with no measurable change in quality”
Claude Cowork moves model inference and VM execution to the cloud for mobile and battery improvements
“The "new" version of Cowork runs model inference and the VM in the cloud. Each session gets its own sandbox, not sharing state with other sessions.”
Pi 1.0 and Pi Durable launch durable, crash-resistant AI agent runtime in TypeScript
“Every step is recorded as a checkpointed task. If a process fails or restarts, agents and subagents automatically resume from their last exact state.”
xAI's Grok 4.7 lands on Amazon Bedrock with 500K context and self-verification for agents
“A model that checks its own output before continuing tends to fail less catastrophically on long trajectories, where an early mistake otherwise compounds through every later step.”
DHH declared hand-writing source code economically unviable, endorsing AI-generated code at Rails World 2026
“It is your obligation to deliver those CLIs by next Friday. So I can use your application without actually ever having to touch it.”
Software engineering will become factory engineering as AI agents automate the full SDLC
“the discipline of software engineering will become something more like factory engineering”
GEPA proposes reflective optimization in text space to overcome RL's sample inefficiency
“instead of using only a zero or one reward signal, we can make a language model or agent analyze the entire execution process to understand what worked and what didn't”