terminal
howtonotcode.com
Google logo

Google

Company

Google is a multinational technology company specializing in Internet-related services and products. It is primarily known for its search engine, but also offers a wide range of services including advertising, cloud computing, software, and hardware. Key use cases include web search, online advertising, and cloud services for businesses and individuals.

article 44 storys calendar_today First seen: 2025-12-30 update Last seen: 2026-03-03 open_in_new Website menu_book Wikipedia

Resources

Links to check for updates: homepage, feed, or git repo.

home Homepage

code Git repo

Stories

Showing 1-20 of 44

Agentic development lands in Xcode, GitHub Actions, and Google APIs

Agentic development is moving from proofs to practice across core tooling, with Xcode 26.3 adding in-IDE agents and MCP, GitHub piloting agentic workflows in Actions with guardrails, and Google introducing APIs that make assistants stateful and documentation-accurate. Apple’s latest Xcode adds deeper agent capabilities and first-class MCP integration, enabling Claude/Codex-style agents to plan, run builds/tests, and verify via Previews within the IDE [InfoQ](https://www.infoq.com/news/2026/02/xcode-26-3-agentic-coding/)[^1]. GitHub Next’s experimental Agentic Workflows bring locked-down, event-driven agents to CI using a CLI that compiles natural language into read-only, sandboxed Actions [Amplifi Labs](https://www.amplifilabs.com/post/css-scope-hits-baseline-github-agentic-workflows-oss-trust-tools)[^2]; meanwhile, Google’s Developer Knowledge API with an MCP server and the new Interactions API push assistants toward on-demand, canonical retrieval and managed, stateful steps for deep research [DevOps.com](https://devops.com/google-launches-developer-knowledge-api-to-give-ai-tools-access-to-official-documentation/)[^3] [Towards Data Science](https://towardsdatascience.com/the-death-of-the-everything-prompt-googles-move-toward-structured-ai/)[^4]. [^1]: Adds: release details on agent behaviors, MCP via mcpbridge, and verification in Xcode 26.3. [^2]: Adds: overview of GitHub Agentic Workflows model, guardrails, and repo automation scenarios. [^3]: Adds: specifics on the Developer Knowledge API, freshness guarantees, and MCP server integration. [^4]: Adds: explanation of Google’s Interactions API for stateful, tool-orchestrated agent flows.

calendar_today 2026-02-09
xcode anthropic claude-agent claude-code openai

Early tests hint Gemini 3.0 Pro GA gains for coding workloads

An early test video claims Google's Gemini 3.0 Pro GA shows strong gains on coding and reasoning, warranting evaluation against current LLMs for backend and data tasks. One early-test breakdown reports top-line improvements with benchmark snippets and demos in this video [Early Test: Gemini 3.0 Pro GA](https://www.youtube.com/watch?v=tPTMHT4O4HQ&pp=ygUXbmV3IEFJIG1vZGVsIGZvciBjb2Rpbmc%3D)[^1]. [^1]: Early, third-party video with anecdotal benchmarks and demos; unofficial and subject to change.

calendar_today 2026-02-09
google gemini-30-pro gemini llm code-generation

Cisco open-sources CodeGuard as research flags predictable LLM code flaws

Cisco donated its CodeGuard security framework to OASIS’s Coalition for Secure AI as new research shows LLM code assistants repeat predictable vulnerabilities, raising the bar for secure-by-default AI coding workflows. Details of the open donation and integration targets (Cursor, Copilot, Windsurf, Claude Code) are in OASIS Open’s announcement [Cisco Donates Project CodeGuard to Coalition for Secure AI](https://www.oasis-open.org/2026/02/09/cisco-donates-project-codeguard-to-coalition-for-secure-ai/)[^1]. Complementary research findings show vulnerability persistence and a black-box FSTab method with up to 94% attack success on LLM-generated apps [AI Code Generation Tools Repeat Security Flaws, Creating Predictable Software Weaknesses](https://quantumzeitgeist.com/ai-security-code-generation-tools-repeat-flaws/)[^2], with broader context on latent backdoors in “clean” AI code [Backdoors With Manners](https://hackernoon.com/backdoors-with-manners-when-ai-writes-clean-code-that-turns-malicious-later?source=rss)[^3] and sector-specific safety layers emerging in healthcare [Inside Guardrails AI](https://www.webpronews.com/inside-guardrails-ai-how-a-seattle-startup-is-deploying-clinical-expertise-to-neutralize-the-most-dangerous-failures-in-artificial-intelligence/)[^4]. [^1]: Adds: Official details on CodeGuard scope, integrations, and governance via CoSAI. [^2]: Adds: Research summary explaining FSTab, vulnerability recurrence metrics, and attack success rates. [^3]: Adds: Perspective on behavioral trojans and delayed-malicious code patterns. [^4]: Adds: Example of domain-specific safety guardrails in production contexts.

calendar_today 2026-02-09
cisco oasis-open coalition-for-secure-ai-cosai project-codeguard cursor

Agentic coding enters IDEs, CI, and docs with MCP and stronger guardrails

Agentic coding is moving into mainstream tooling as Xcode 26.3, GitHub Actions pilots, and new Google offerings converge on guarded, MCP-compatible agents across IDEs, CI, and authoritative docs. Xcode 26.3 expands integrated agentic coding for Claude and Codex, adds Model Context Protocol support, and lets agents verify UI via Previews for iterative fixes and planning.[^1] GitHub Next is piloting Agentic Workflows for Actions with strict defaults, while Google advances an agent‑first stack via Antigravity and a Developer Knowledge API plus MCP server that enables assistants to retrieve official docs at runtime.[^2][^3][^4] [^1]: https://www.infoq.com/news/2026/02/xcode-26-3-agentic-coding/ — Details on Xcode 26.3 agent capabilities, MCP support, and verification via Previews. [^2]: https://www.amplifilabs.com/post/css-scope-hits-baseline-github-agentic-workflows-oss-trust-tools — Newsletter coverage of GitHub Agentic Workflows and safety guardrails. [^3]: https://antigravity.im/ — Independent guide outlining Google Antigravity’s agent‑first IDE and multi‑agent orchestration. [^4]: https://devops.com/google-launches-developer-knowledge-api-to-give-ai-tools-access-to-official-documentation/ — Overview of Google’s Developer Knowledge API and MCP server for authoritative documentation retrieval.

calendar_today 2026-02-09
xcode anthropic claude-agent claude-code openai

AI dev tools adoption: 6 pitfalls and a team playbook

A practical playbook details six common pitfalls teams face when adopting AI coding tools and how to roll them out safely and effectively. It covers skill gaps, top‑down tool choice, blind trust and review load, context starvation, and people concerns, with concrete rollout steps for teams ([CodeRabbit adoption guide](https://www.coderabbit.ai/blog/ai-coding-tools-adoption-for-teams-guide))[^1]. [^1]: Adds: Summarizes 6 pitfalls and provides actionable team rollout guidance based on real-world adoptions.

calendar_today 2026-02-07
coderabbit google claude github gitlab

Plan for multi-model agents and resilience in 2026

AI agents are set to pressure reliability, with more outages expected and a push toward chaos engineering and multi-cloud failover, per [TechRadar’s 2026 outlook](https://www.techradar.com/pro/the-year-of-the-ai-agents-more-outages-heres-what-lies-ahead-for-it-teams-in-2026)[^1]. In parallel, a [community thread on using Google Gemini with the OpenAI Agents SDK](https://community.openai.com/t/using-gemini-with-openai-agents-sdk/1307262#post_8)[^2] highlights growing demand for multi-model agent stacks—so design provider abstractions, circuit breakers, and fallback paths now.

calendar_today 2026-02-03
gemini openai-agents-sdk openai google techradar

CORE: Persistent memory and actions for coding agents via MCP

CORE is an open-source, self-hostable memory agent that gives coding assistants persistent, contextual recall of preferences, decisions, directives, and goals, and can trigger actions across your stack via MCP and app integrations like Linear, GitHub, Slack, Gmail, and Google Sheets; see [CORE on GitHub](https://github.com/RedPlanetHQ/core)[^1]. For backend/data teams, this replaces brittle context-dumps with time- and intent-aware retrieval across Claude Code and Cursor, enabling consistent code reviews and automated updates tied to prior decisions. [^1]: Adds: repo, docs, and integration details (MCP, supported apps, memory model, self-hosting).

calendar_today 2026-02-03
core redplanethq claude-code cursor mcp

Shift from brittle automations to agentic workflows (Google Antigravity cue)

A recent video argues for designing agentic workflows—multi-step, tool-using, stateful flows—instead of one-off AI automations. "Google Antigravity" is referenced as an example of this direction, though details are limited; the practical takeaway is to treat agents like orchestrated workflows with planning, tool calls, memory, and robust controls.

calendar_today 2026-01-06
google-antigravity agentic-workflows tool-use observability evaluation

Early agent benchmarks: Claude leads tool-calling, Gemini 3 Flash rebounds, GPT Mini/Nano lag

A practitioner benchmarked LLMs on real operational tasks (data enrichment, calendar scheduling, CRM clean-up) with minimal prompting and explicit tool specs. Claude was most reliable at tool-calling but can hit context limits on long tasks; Gemini 3 Flash notably improved and outperformed 3 Pro; GPT Mini/Nano struggled with constraint adherence when reasoning was off. These are early, single-source results but map closely to common backend/data-engineering agent patterns.

calendar_today 2026-01-06
claude gemini-3-flash openai tool-calling agent-benchmarks

GitHub Copilot: GPT-5.1 Codex preview, Spaces sharing, and model retirements

GitHub Copilot added a public preview of GPT-5.1-Codex-Max across web, IDE, mobile, and CLI (Enterprise/Business must enable it), made Spaces shareable publicly or per-user with a code-viewer add-to-Space flow, and refined the VS model picker. Older OpenAI/Anthropic/Google models were retired with suggested replacements, agents gained mission control and skills with broader IDE coverage, and knowledge bases fully sunset in favor of Spaces.

calendar_today 2026-01-06
github-copilot agentic-ai context-grounding model-lifecycle jetbrains

AI IDE forks exposed by OpenVSX namespace hijack in built-in extension recommendations

Koi found that popular AI IDEs forked from VS Code (Cursor, Windsurf, Google Antigravity, Trae) inherit hardcoded extension recommendations that point to Microsoft’s marketplace, but those extensions don’t always exist on OpenVSX (the registry these IDEs actually use). Unclaimed namespaces on OpenVSX could be registered by attackers to ship malicious lookalike extensions that the IDE proactively recommends based on files or installed software. Koi preemptively claimed several risky namespaces (e.g., PostgreSQL, Azure Pipelines, ARM tools) with placeholder packages to reduce immediate risk.

calendar_today 2026-01-06
cursor windsurf openvsx vscode supply-chain-security

Gemini 3 Flash vs Pro: cost/speed trade‑offs and when to use each

Chatly compares Google’s Gemini 3 Flash and Pro, saying Flash is cheaper and faster with better token efficiency, while Pro leads on complex reasoning, long‑context, and specialized multimodal tasks. They cite benchmark coverage (SWE‑bench Verified, MMMU‑Pro, AIME 2025, GPQA Diamond, MRCR v2) and recommend Flash for most applications, reserving Pro for niche, high‑difficulty workloads. Concrete scores aren’t provided, so teams should validate on their own tasks.

calendar_today 2026-01-06
gemini-3-flash gemini-3-pro code-generation model-evaluation cost-optimization

Agentic coding assistants: separate Google’s official stack from unverified plugin claims

Several videos tout new '1‑click' Google AI agents and a free Chinese coding agent, but most details are unverified. What is concrete today: Google’s Gemini API, AI Studio, Vertex AI Agent Builder, and Project IDX already support building and evaluating agentic workflows for coding and automation. Treat influencer 'leaks' as speculation and run controlled trials on official, supported tools.

calendar_today 2026-01-02
google-gemini vertex-ai project-idx agentic-workflows ci-cd

Baytech review: Google Antigravity agentic IDE—greenfield boost, Microsoft friction

Baytech Consulting reports that Google released an AI-native IDE, Antigravity, in late 2025 that uses the Gemini 3 model to orchestrate agentic, multi-file development (a "mission controller" vs autocomplete). Their analysis says it accelerates prototyping and greenfield work but introduces a walled-garden feel and integration friction for teams anchored in VS Code and Azure DevOps. This is a single consultancy review; official details from Google are limited.

calendar_today 2026-01-02
google-antigravity gemini-3 agentic-development azure-devops visual-studio-code

Agentic IDEs: Google Antigravity vs Cursor for backend teams

Agentic IDEs can plan, execute, and verify changes across files, terminals, and browsers with minimal human orchestration. Google’s Antigravity lets you manage multiple parallel agents via a manager view with artifacts for traceability and supports Gemini 3 Pro, Claude Sonnet 4.5, and OpenAI models; it’s free in public preview. Cursor blends fast inline autocomplete with an Agent mode for multi-file changes, using deep code context and real-time diff review.

calendar_today 2025-12-31
antigravity cursor agentic-ide code-generation sdlc

Update: Google DeepMind AGI roadmap and agentic systems

In a new video, Demis Hassabis lays out the clearest public roadmap to AGI yet, explicitly centering on agentic systems that plan, use tools, and work across modalities. New vs prior: he more clearly sequences milestones (improving tool-use reliability and long‑horizon planning before higher autonomy) and positions Gemini and Project Astra as stepping stones rather than endpoints.

calendar_today 2025-12-30
agi agents multimodal google deepmind
Next