AI-Assisted Spec-Driven Development

7/31/2026

Introduces the general availability of agent and model evaluations within the Gemini Enterprise Agent Platform. This feature provides a unified engine for measuring and comparing agents and models using consistent metrics across development and production. Key components include over 20 pre-built metrics (quality, safety, grounding, tool use, reference-based scoring), adaptive rubrics that tailor judging criteria, and the ability to define custom code-based or LLM-as-a-judge metrics. Experiment management allows for local or server-side runs with auditable and reproducible artifacts stored in Cloud Storage. Online monitors integrate with existing telemetry to grade live production traffic, producing score-over-time charts and drift alerts. Case generation and simulation tools (user simulator, environment simulator) are provided to bootstrap evaluation datasets and test agent behavior under various conditions, including simulated backend failures.

7/31/2026

Introduced Agent Skills for Genkit, a mechanism for packaging specialized expertise into discoverable capabilities that agents load only when needed. This leverages a progressive disclosure model where only skill metadata is initially exposed to the agent's system prompt, with the full skill body and bundled resources (scripts, references) loaded dynamically when required. This improves token efficiency, simplifies implementation, and allows for resource bundling. Demonstrated integration with Genkit Go via middleware hooks, including discovery, activation, and execution stages, with code examples for a recipe generation tool and a multi-modal art restoration application.

7/16/2026

This post introduces a production prompt transpiler that treats AI agent prompts as build artifacts rather than static text. It advocates for modular skill files, dependency management, build-time validation (e.g., for missing imports, undefined variables, circular dependencies), and drift checking through CI pipelines. The system supports dynamic skills and agent-authored updates, where agents can propose changes to their instruction layers via pull requests, which are then subjected to validation and review. This approach aims to improve prompt maintainability, reduce blast radius, prevent copy-paste drift, and defer runtime errors, ultimately enhancing agent reliability.

7/16/2026

This post announces the evolution of Conductor from a Gemini CLI extension to a portable plugin. This change allows for a more conversational interaction model where AI dynamically generates context, specs, and plans, moving away from strict command sequences. The plugin architecture ensures compatibility with multiple tools like Antigravity CLI and Claude, maintaining project context and artifacts (spec.md, plan.md) across different environments. It also highlights improved task completion rates on complex benchmarks compared to non-SDD workflows.

7/8/2026

This post details the development of an AI Race Coach using Antigravity and Gemini, showcasing real-time telemetry ingestion, edge reasoning with Gemma 4, and cloud reasoning with Gemini API. It highlights the use of Antigravity for domain bridging, Python for data parsing, Jetpack Compose for the UI, and custom hardware for direct vehicle telemetry capture. A key technical achievement was the activation of the Pixel 10 TPU, enabling 40 tokens per second processing for real-time coaching alerts.

7/1/2026

Introduces Genkit, an open-source framework for building full-stack, AI-powered and agentic applications. Highlights the Agents API for defining and driving agents with a unified interface, supporting TypeScript, Go, Dart, and Python. Details server-managed and client-managed state persistence, HTTP serving capabilities, and a rich client for full-stack integration. Explains human approval workflows, long-running tasks via detached turns, and agent delegation for coordinating specialized agents.

7/1/2026

Introduces the Google Cloud Workbench Notebooks extension for VS Code, enabling users to connect their local IDE to managed cloud environments for ML development. This extension streamlines the ML lifecycle by eliminating context switching and allowing users to run notebooks directly on Workbench instances. It also highlights the open-sourced nature of the extension and provides steps for installation and connection.

7/1/2026

This post introduces ADK 2.0, which enhances AI agent development by providing a structured workflow runtime and task-collaboration model. It allows for the seamless blending of deterministic execution logic with LLM-based agents, addressing issues like context bloat, execution derailment, and prompt injection. The post details the benefits of this approach through a customer refund processing example, highlighting efficiency gains in token usage and latency, and introduces dynamic workflows for complex business logic and structured multi-agent collaboration.

6/30/2026

ADK for Go 2.0 introduces a graph-based workflow engine for composing multi-agent applications, built-in human-in-the-loop (HITL) as a primitive, dynamic orchestration in Go, LLM agent modes, and a unified node runtime. It enhances resilience with built-in retry policies, timeouts, and concurrency controls. The update also unifies agent and workflow execution models and introduces a single `agent.Context` for tools, callbacks, and workflow nodes.

6/30/2026

This post introduces a "quality flywheel" for engineering AI agents, driven by a coding agent that automates the evaluation and refinement cycle. It details a five-stage process: Prepare Data, Run Inference, Grade, Analyze Failures, and Optimize & Iterate. Key components include adaptive AutoRaters for grading, Automatic Loss Analysis for clustering failures, and a decoupled optimizer/evaluator architecture. The post also highlights the development of custom metrics to isolate specific failure modes, such as mid-conversation changes in agent behavior, and provides concrete examples of how the system operates using the `_travel-concierge_` agent.

6/22/2026

This post introduces the practical application of the Agent Development Kit (ADK) and the Agent-to-Agent (A2A) protocol for building cross-language multi-agent systems. It details how to create a contract compliance pipeline with a Python agent (using Gemini for extraction) and a Go agent (for deterministic validation), connected via A2A. Key contributions include demonstrating the A2A protocol's discovery (Agent Cards) and communication (JSON-RPC 2.0 with Message Parts) mechanisms, the use of ADK's RemoteA2aAgent for abstracting remote A2A services, and the concept of shared state (ToolContext.state) for inter-agent communication. It also highlights production-ready patterns like state management for fault tolerance (MANUAL_REVIEW) and the decomposition of monolithic agents into specialized microservices.

6/22/2026

This post introduces a new methodology for evaluating proactive AI coding agents by developing benchmarks that grade their 'insight policy.' It details a process of clustering real bug-fixing history to identify higher-level 'aspirational goals' and using these as ground truth targets for agent evaluation. The post also presents preliminary results from testing this methodology on internal Google codebases, demonstrating the effectiveness of the core diagnostic logic and the importance of exploration budgets for complex problems. It outlines plans to expand this evaluation to public GitHub data and ingest richer context streams.

6/18/2026

This post introduces the Agent-to-Agent (A2A) protocol, a new communication standard designed for collaborative AI agents. It details the architectural advantages of A2A, including secure boundaries for sensitive data, zero context pollution by offloading dependencies to peer agents, dynamic autonomy enabling agents to refine plans and ask clarifying questions, and workload distribution for modular development. The post highlights the FoldRun agent as a practical application in life sciences for protein structure prediction, demonstrating how A2A simplifies complex workflows. It also outlines potential applications in agentic commerce, enterprise data streaming, cross-platform IT/DevOps, and secure telecommunications. The post also announces the availability of A2A SDKs in Python and Go (GA), Java (Beta), .NET (Preview), and JavaScript/TypeScript.

5/21/2026

Announces ADK for Kotlin 0.1.0 and ADK for Android 0.1.0. ADK for Kotlin enables agentic workflows on backend projects, supporting hybrid orchestration (cloud orchestrator with on-device sub-agents), on-device sequential agents, local retrieval, and flexible tooling. ADK for Android provides specialized on-device optimizations for AI agents within Android apps, leveraging local LLMs (like Gemini Nano) for enhanced privacy and the ability to bridge with cloud models. The post provides code examples for building agents in Kotlin and integrating ADK into Android projects, highlighting features like model swapping, session state sharing, and tool integration using annotations.

5/12/2026

This post introduces the concept of building long-running AI agents using the Agent Development Kit (ADK) that can pause, resume, and maintain context. It details three key architectural shifts: durable memory schemas, event-driven dormancy gates, and multi-agent delegation. The post demonstrates how to implement these concepts using a state machine for tracking onboarding progress, wiring the state into the agent's system instruction, using tools to advance the state machine, implementing checkpoint-and-resume with persistent sessions (SQLite/Cloud SQL), and handling idle time with event-driven resumption via webhook endpoints. It also highlights the use of a coding agent and Agents CLI for scaffolding and iterative development.

4/14/2026

This post details 5 key developer tips for building production-grade AI agents, derived from the Google Cloud AI Agent Bake-Off. It emphasizes moving beyond simple prompt engineering to rigorous 'agentic engineering'. Key takeaways include: 1. Architecting for multi-agent workflows by decomposing problems into specialized sub-agents managed by a supervisor agent, similar to microservices. 2. Building agent harnesses with a mindset of impermanence, expecting them to be replaced by advancements in state-of-the-art models. 3. Treating multimodality as a core requirement, not an add-on, by natively integrating multimodal models for richer context ingestion and generation. 4. Leveraging open source protocols like MCP, A2A, UCP, AP2, A2UI, and AG-UI for dynamic resource discovery and communication, reducing the need for custom integration code. 5. Using deterministic code (e.g., Python functions, SQL queries) for execution after LLMs perform reasoning and intent extraction, with strict JSON validation schemas to capture and validate model outputs.

3/10/2026

Introduced 'Finish Changes' and 'Outlines' features to Gemini Code Assist extensions for IntelliJ and VS Code. 'Finish Changes' allows AI to complete code based on in-progress modifications, pseudocode, comments, and demonstrated patterns, reducing the need for explicit prompts. 'Outlines' generates inline code summaries for improved comprehension and navigation within the IDE. Both features are powered by Gemini 3.0 and aim to streamline developer workflows and reduce ramp-up time.

3/10/2026

Introduced Agent Mode with Auto Approve for automated multi-file code changes, Inline Diff Views for direct editing of AI-generated code, Revert to Checkpoint for rolling back changes, Multi-part Chat Code Suggestions for granular acceptance of AI code, Chat Code Suggestion Previews for scannable code blocks, and improved code completion speed. Enhanced user control with Context Drawer for managing conversational context, Custom Commands for workflow automation, adding code snippets and terminal output to chat context, configurable codebase awareness via AI exclusion files, and a stop button for in-progress chat responses. Added 'thinking tokens' and release channel name in chat banner for transparency.

8/12/2025

Introduces a "critic" functionality integrated into the AI coding agent (Jules) to review and critique generated code before it is presented to the user. This critic-augmented generation process involves an adversarial review of proposed code changes, flagging issues like subtle logic errors, missed edge cases, and inefficient algorithms. The critic operates in a one-shot pass for the initial version, with future plans for multi-step agent capabilities. The goal is to improve code quality, test coverage, and security by moving the review process earlier in the development cycle.

7/24/2025

Introduces Opal, an experimental tool for building and sharing AI mini-apps. Opal allows users to create workflows by chaining prompts, AI model calls, and tools using natural language and a visual editor, without requiring code. It supports sharing these apps for immediate use by others.

6/24/2025

This post announces the general availability of the AI-first Google Colab experience, which integrates agentic capabilities for accelerating machine learning projects, debugging, and data visualization. It highlights features like iterative querying, a Next-Generation Data Science Agent for autonomous workflows, and effortless code transformation through natural language. The post details how users are leveraging these features for end-to-end ML lifecycle acceleration, smarter debugging with AI pair programming and diff-based fixes, and hassle-free data visualization generation.

5/20/2025

Introduces Stitch, a new experiment from Google Labs that leverages Gemini 2.5 Pro to generate UI designs and frontend code from natural language prompts or image inputs. Stitch offers features for rapid iteration and design exploration, and provides 'Paste to Figma' functionality and front-end code export for seamless transition to development workflows.

5/20/2025

This post announces a reimagined, AI-first Google Colab powered by Gemini 2.5 Flash. It introduces an agentic collaborator that understands code, actions, intentions, and goals across the entire notebook. Key features include iterative querying for code generation, transformation, and intelligent error fixing; an upgraded Data Science Agent (DSA) for autonomous analytical workflows and interactive feedback; and effortless code transformation based on natural language descriptions. The new Colab offers flexible interaction methods via a center stage box and a side panel.

5/14/2024

Introduces 'Checks', Google's AI-powered compliance platform, now generally available for Android and iOS developers. It provides automated privacy compliance reports by analyzing app behavior, data collection, and sharing practices against stated policies. It offers actionable insights, integrates with CI/CD, and provides dashboards. A new feature, 'Checks Code Compliance' (private preview), uses Gemini models to analyze source code in real-time for compliance issues. 'Checks AI Safety' (private preview) offers automated adversarial testing for generative AI content.

2/15/2024

Project IDX now integrates Gemini models to provide AI features that speed up and refine the end-to-end developer workflow. This includes inline AI assistance for real-time error correction, code suggestions, and auto-completion within any file by pressing Cmd/Ctrl + I. It also introduces a Gemini API template for embedding AI-powered features into applications using the Gemini Pro model, supporting multimodal inputs like images, text, and code, and can be used with the LangChain framework.