AIAIAI.FYI LIVE

Engineers & builders · The Build

Every AI tool, API and release, the minute it ships.

40%+of pull requests on GitHub in September 2026 started with an AI agent's first draft, up from 17% in MarchGitHub Octoverse 2026 (Oct. 28, 2026)
66%of Stack Overflow's 2026 respondents named coding assistants and agents as an AI use case, the most common oneStack Overflow Developer Survey 2026, AI
48%of developers say they trust AI output when they can easily validate the answersStack Overflow Developer Survey 2026, AI
12h vs 1.5hlength of software tasks (in skilled-human time) the best public agents finished 50% vs 80% of the time, early 2026METR, Frontier Risk Report (May 19, 2026)
61%of GitHub Copilot users who pick their own model used more than one model in September 2026, up from 50% four months earlierGitHub Octoverse 2026 (Oct. 28, 2026)
90%of agent-started pull requests were merged within two weeks in September 2026, vs about 86% for PRs with no detected agentGitHub Octoverse 2026 (Oct. 28, 2026)

Release radar

From official changelogs, GitHub releases and lab announcements.

Tool stack map

Coding agents & AI IDEs

Agents that read your repo, edit files, run tests and open pull requests. Claude Code (66%) and GitHub Copilot (59%) were the most used coding agents in the 2026 Stack Overflow survey. Most teams run more than one. Commit an AGENTS.md or CLAUDE.md with build commands and conventions; GitHub found new repos with an agent configuration file logged 8x as many commits.

Claude CodeGitHub CopilotOpenAI CodexCursorGemini CLIZedAiderCline

Stack Overflow Developer Survey 2026, AI

Model APIs

First-party APIs get new models and features first. Cloud marketplaces (Bedrock, Vertex AI, Foundry) trade a short lag for your existing billing, IAM and data-residency setup. Pin model IDs, read the deprecations page monthly, and keep a second provider wired up for failover.

Claude API (Anthropic)OpenAI APIGemini API (Google AI Studio)Amazon BedrockGoogle Cloud Vertex AIMicrosoft FoundryMistral AIOpenRouter
Agent frameworks

Libraries for the loop of plan, call a tool, observe, repeat. LangChain (30%) and the OpenAI Agents SDK (24%) led the 2026 Stack Overflow survey. Start with your provider's SDK and a plain loop; adopt a framework when you need durable state, multi-agent handoffs or tracing you'd otherwise build yourself. Note that OpenAI's Agent Builder shuts down on 2026-11-30.

LangChain / LangGraphOpenAI Agents SDKClaude Agent SDKGoogle Agent Development Kit (ADK)Pydantic AIVercel AI SDKCrewAIMastra

Stack Overflow Developer Survey 2026, AI

MCP & tool protocols

The Model Context Protocol (MCP) is the common way to expose tools and data to AI clients: write a server once and Claude, ChatGPT, IDE agents and others can call it. A2A covers agent-to-agent messaging. Treat every tool result as untrusted input: prompt injection through tool output is the main security risk.

Model Context ProtocolMCP reference serversAgent2Agent (A2A)AGENTS.mdOpenAPI
Local & open-weight runtimes

Run open-weight models on a laptop or your own servers for privacy, offline use or predictable cost. Quantized models trade some quality for memory. Check the license before shipping: open weights often come with use restrictions.

Ollamallama.cppLM StudioMLXJanHugging Face Hub
Evals & observability

If you can't measure it, every model upgrade is a gamble. Build a task-specific eval set from real traffic, grade it automatically, and trace production calls. OpenAI's Evals dashboard and API go read-only on 2026-11-30, and OpenAI's docs point users to Promptfoo.

PromptfooInspectLangfuseArize PhoenixLangSmithBraintrustOpenTelemetry GenAI conventions
Vector & retrieval

Retrieval quality decides RAG quality. Hybrid search (keywords plus embeddings) with a reranker beats either alone on most business documents. If you already run Postgres, start with pgvector and move only when you measure a reason to.

pgvectorQdrantWeaviateMilvusChromaPineconeturbopufferCohere
Fine-tuning & training

Fine-tune for format, tone and narrow tasks after prompting and retrieval stop improving your evals. Most teams fine-tune open-weight models with LoRA. Plan around OpenAI's timeline: new organizations lost self-serve fine-tuning on 2026-05-07, and existing customers can no longer create new jobs from 2027-01-06.

Hugging Face TRLUnslothAxolotlPyTorchTogether AI
Inference serving

For self-hosting at scale, the open-source servers handle batching, KV-cache management and speculative decoding for you. Managed inference providers serve open-weight models per token. Compare on your own prompts: throughput and latency numbers vary a lot with input length.

vLLMSGLangNVIDIA TensorRT-LLMFireworks AIGroqBasetenModal
Automation & no-code

For workflows that glue SaaS apps together with an AI step in the middle. Make (39%) and n8n (33%) led automation tools in the 2026 Stack Overflow survey. Put a human approval step before anything that emails customers or moves money.

Maken8nZapierMicrosoft Power Automate

Stack Overflow Developer Survey 2026, AI

Open source