# Loop Engineering

An emerging agentic engineering practice for designing recurring workflows that guide AI agents through multi-step tasks with limited human intervention.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses

DevFeed: [Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses](<https://devfeed.tech/articles/agentic-harness-engineering-beta-requirement-centered-evolution-of-agent-harnesses-142220.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24924>)

Author: Jiahang Lin, Jiahao Chen, Yiding Wang, Shichun Liu, Chengjun Pan, Shihan Dou, Honglin Guo, Yuyang Hu, Changhao Jiang, Zhenhua Han, Hang Yan, Qi Zhang, Tao Gui, Xuanjing Huang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [base](<https://devfeed.tech/tags/base.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [beta](<https://devfeed.tech/tags/beta.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [change](<https://devfeed.tech/tags/change.md>), [changes](<https://devfeed.tech/tags/changes.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [harness](<https://devfeed.tech/tags/harness.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>)

### AI overview

AHE-Beta evolves agent harnesses around verified user requirements: simulated users raise issues over multiple turns, a team implements generalizable changes, and changes are merged only after resolving a verified requirement and passing review. On held-out tasks, it raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and the abstract reports higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, users preferred it in 31 of 48 valid pairs and rated it higher on all five dimensions. Without further evolution, reported pass@1 gains over Base Harness transferred to GLM-5.3 (15.8%) and DeepSeek-V4.1-Flash (5.3%).

### Source excerpt

arXiv:2611.24924v1 Announce Type: new Abstract: Real-world harness engineering is driven by explicit and implicit user requirements, which guide development and validation. However, existing harness evolution methods often overlook implicit requirements and interaction needs, while using a single evolution agent to modify the harness and benchmark scores to select changes. This process often produces narrow patches and leads to benchmark-specific local optima. We introduce Agentic Harness Engineering Beta (AHE-Beta), a requirement-centered loop that brings real-world engineering practices into harness evolution. The loop consists of three steps: (1) User-driven evaluation lets simulated users raise their requirements as issues while they work with the harness over multiple turns. (2) Team-based modification implements those requirements as generalizable changes rather than task-specific patches. (3) Requirement-driven selection merges a change only when it resolves a verified requirement and passes review. Empirically, on held-out tasks, AHE-Beta raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and achieves higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, real users prefer AHE-Beta in 31 of 48 valid pairs and rate it higher on all five dimensions, matching the directional preference of the user simulator. The human A/B results show that AHE-Beta achieves its goal of aligning harness evolution with real-world user requirements. Without further evolution, the gains transfer to GLM-5.3 and DeepSeek-V4.1-Flash with pass@1 improvements of 15.8% and 5.3% over Base Harness. Together, these results show that requirement-centered harness evolution is a more general method for improving agent capabilities.

## GitLab 19.6 released

DevFeed: [GitLab 19.6 released](<https://devfeed.tech/articles/gitlab-19-6-released-144780.md>)

Original publisher: [Read original article](<https://docs.gitlab.com/releases/19/gitlab-19-6-released/>)

Author: GitLab

Published: 2026-11-19T00:00:00Z

Content type: release

Language: en

Sources: [GitLab](<https://devfeed.tech/sources/gitlab.md>)

Topics: [GitLab](<https://devfeed.tech/topics/gitlab.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Secret Scanning](<https://devfeed.tech/topics/secret-scanning.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [administrator](<https://devfeed.tech/tags/administrator.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [availability](<https://devfeed.tech/tags/availability.md>), [duo](<https://devfeed.tech/tags/duo.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [slack](<https://devfeed.tech/tags/slack.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

GitLab 19.6 adds governance, agent workflows, faster merge request reviews, and security controls. MCP server tool calls now create audit events, while group Owners can deny tools, require approval, or allow them (the control is in beta). Duo in Slack is in limited availability on GitLab.com; `/goal` starts long-running Developer Flow sessions that can commit, push, and create merge requests without per-action approval, and scheduled automations are in beta. Rapid Diffs is generally available, streaming server-rendered diffs; the first file is reported to appear in about 1.5 seconds versus 4.5 seconds previously. Security updates include Rust scanning in Advanced SAST (added in 19.5 and still beta), malware rules for merge request approvals requiring SBOM-based dependency scanning, and configurable pipeline-variable limits. Web search in Agentic Chat is off by default and requires group or instance enablement; searches create audit events. The notes also flag upgrade guidance, including potential custom NGINX configuration breaks after the bundled version update.

### Source excerpt

GitLab 19.6 released with GitLab Duo in Slack in limited availability on GitLab.com

## Keep recurring work moving with scheduled automations

DevFeed: [Keep recurring work moving with scheduled automations](<https://devfeed.tech/articles/keep-recurring-work-moving-with-scheduled-automations-144777.md>)

Original publisher: [Read original article](<https://about.gitlab.com/blog/gitlab-scheduled-automations/>)

Author: Brittany Lutz

Published: 2026-11-19T00:00:00Z

Content type: article

Language: en

Sources: [GitLab](<https://devfeed.tech/sources/gitlab.md>)

Topics: [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automation](<https://devfeed.tech/tags/automation.md>), [backlog](<https://devfeed.tech/tags/backlog.md>), [beta](<https://devfeed.tech/tags/beta.md>), [cadence](<https://devfeed.tech/tags/cadence.md>), [ci](<https://devfeed.tech/tags/ci.md>), [comment](<https://devfeed.tech/tags/comment.md>), [controls](<https://devfeed.tech/tags/controls.md>), [daily](<https://devfeed.tech/tags/daily.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [duo](<https://devfeed.tech/tags/duo.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [event](<https://devfeed.tech/tags/event.md>), [factory](<https://devfeed.tech/tags/factory.md>), [scheduled](<https://devfeed.tech/tags/scheduled.md>)

### AI overview

GitLab Duo Agent Platform scheduled automations run flows on recurring schedules without waiting for a person or event trigger. Teams describe a task in plain language and choose a cadence from every 15 minutes to monthly, including a time and timezone. Examples include daily issue triage and hourly CI incident checks. Each automation runs at project level under a dedicated service account with scoped permissions; audit events record automation changes, and the Automations page shows run counts, success rates, session details, and failure reasons. Event-based automations remain available for triggers such as merge requests or comment mentions. Scheduled automations are in beta in GitLab 19.6 and use GitLab Credits; trying them requires enabling experimental and beta features.

### Source excerpt

Every engineering team has work that needs regular attention, like triaging new issues or investigating incidents. Among DevSecOps professionals using AI tools, 43% say automating repetitive tasks has created the most efficiency, according to GitLab's Global DevSecOps report. But agents still rely on a human to kick off the workflow or an event trigger to fire, and without a record of what ran and why, no one can trace how the work got done. With scheduled automations, in beta in GitLab 19.6, flows in GitLab Duo Agent Platform handle routine tasks on a schedule your team sets and keep a history of what ran. Scheduled automations are a building block of the governed software factory, where agents and flows work autonomously within controls set by your team. Put routine work on a schedule Relying on a person or an event to start automated work limits efficiency gains and makes timing unpredictable. When the person responsible is out, the work waits, and when there's no event, it never starts. Scheduled automations give routine work a dependable rhythm. You can already run event-based automations in GitLab Duo Agent Platform, triggered by activities like a merge request or a mention in a comment. Scheduled automations start the work on a recurring schedule, with no event needed. Describe the task in plain language, set the cadence once, and the automation runs on its own at the times you choose, with run counts and success rates your team can review. Triage new issues daily to keep your backlog organized, or schedule a flow to check CI health incidents every hour and comment with the likely root cause, so the investigation is underway before anyone opens the issue. You can set a schedule from every 15 minutes to every month, at the time of day and in the timezone that meets the needs of your group. Because automations in GitLab drive the work your whole team depends on, each one runs at the project level. See how to schedule an automation, from describing the task to r

## Agentic Flow Types: Choosing how you work with AI

DevFeed: [Agentic Flow Types: Choosing how you work with AI](<https://devfeed.tech/articles/agentic-flow-types-choosing-how-you-work-with-ai-141886.md>)

Original publisher: [Read original article](<https://www.port.io/blog/agentic-flow-types>)

Author: Jenna Danoy

Published: 2026-11-18T06:40:09Z

Content type: article

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-assistance](<https://devfeed.tech/tags/ai-assistance.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [aspm](<https://devfeed.tech/tags/aspm.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [business](<https://devfeed.tech/tags/business.md>), [business-logic](<https://devfeed.tech/tags/business-logic.md>), [flow](<https://devfeed.tech/tags/flow.md>), [types](<https://devfeed.tech/tags/types.md>)

### AI overview

The article presents five ways engineering teams can work with AI, from manual development and AI assistance through human-approved AI output, human-assisted AI-led work, and fully agentic engineering. It treats these as options that can coexist, with teams choosing workflows suited to the task rather than moving through a required maturity sequence. Examples range from AI-generated code and tests to agents that propose fixes or manage feature work, with human review or approval varying by workflow. It says adoption depends on strong engineering context, durable pipelines and workflows, and safe infrastructure; it recommends unifying platform domains and organizing software context as early steps. Fully agentic engineering is described as uncommon in production, and the article expects humans to retain oversight of risk and decisions.

### Source excerpt

Each Agentic Flow Type can deliver different results -- learn how to leverage each type in this article.

## PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows

DevFeed: [PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows](<https://devfeed.tech/articles/pvtsizing-2-0-a-fast-and-reliable-analog-circuit-sizing-operator-for-agentic-eda-workflows-141766.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22328>)

Author: Zichen Kong, Minghuan Song, Xiyuan Tang, Ziming Wei, Yi Zhong, Yuan Wang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Chip design](<https://devfeed.tech/topics/chip-design.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [analog](<https://devfeed.tech/tags/analog.md>), [circuit](<https://devfeed.tech/tags/circuit.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design-automation](<https://devfeed.tech/tags/design-automation.md>), [eda](<https://devfeed.tech/tags/eda.md>), [eda-workflows](<https://devfeed.tech/tags/eda-workflows.md>), [fast](<https://devfeed.tech/tags/fast.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [operator](<https://devfeed.tech/tags/operator.md>), [pvt](<https://devfeed.tech/tags/pvt.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [search](<https://devfeed.tech/tags/search.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [specifications](<https://devfeed.tech/tags/specifications.md>), [study](<https://devfeed.tech/tags/study.md>), [tool](<https://devfeed.tech/tags/tool.md>), [workflow](<https://devfeed.tech/tags/workflow.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

PVTSizing 2.0 combines an independently usable numerical optimizer with an agent workflow for analog circuit sizing across process, voltage, and temperature corners. Loss-guided updates reduce unnecessary training, while critic-guided local refinement searches additional candidates amid cross-corner conflicts. An optional LLM adviser provides parameter relationships; the optimizer chooses adjustment sizes and checks effects through simulation. Across four benchmarks, the standalone optimizer completed all 40 runs and achieved 7.3x lower overall mean runtime than the original PVTSizing, with a comparable mean sample count. In a separate study, the best tested knowledge-injection setup reduced mean runtime by 39.9% and simulation samples by 35.4% versus the standalone optimizer.

### Source excerpt

arXiv:2611.22328v1 Announce Type: cross Abstract: Analog circuit design automation requires both coordinated tool execution and efficient numerical search. Large language models (LLMs) offer new ways to organize tool execution, but finding one sizing that satisfies specifications across process, voltage, and temperature (PVT) corners remains costly. PVTSizing 2.0 addresses these needs through a human-agent workflow built around an independently usable numerical optimizer. An agent carries the designer's approved task through execution and result review. The optimizer reduces unnecessary training through loss-guided updates and uses critic-guided local refinement to explore additional candidates while accounting for cross-corner conflicts. An optional LLM adviser supplies parameter relationships to focus numerical search on circuit-informed directions, while the optimizer selects adjustment amplitudes and verifies their effects through simulation. Across four circuit benchmarks, the standalone optimizer completes all 40 runs and achieves a 7.3x speedup in overall mean runtime over the original PVTSizing, with a comparable mean sample count. In a separate study, the best tested knowledge-injection configuration further reduces mean runtime by 39.9% and simulation samples by 35.4% relative to the standalone optimizer.

## Agentic engineering with GitLab and your local agent: A walkthrough

DevFeed: [Agentic engineering with GitLab and your local agent: A walkthrough](<https://devfeed.tech/articles/agentic-engineering-with-gitlab-and-your-local-agent-a-walkthrough-144773.md>)

Original publisher: [Read original article](<https://about.gitlab.com/blog/agentic-engineering-walkthrough/>)

Author: Fatima Sarah Khalid

Published: 2026-11-18T00:00:00Z

Content type: tutorial

Language: en

Sources: [GitLab](<https://devfeed.tech/sources/gitlab.md>)

Topics: [GitLab](<https://devfeed.tech/topics/gitlab.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [gitlab-ci](<https://devfeed.tech/topics/gitlab-ci.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [codex](<https://devfeed.tech/topics/codex.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code](<https://devfeed.tech/tags/code.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [connect](<https://devfeed.tech/tags/connect.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer](<https://devfeed.tech/tags/developer.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [duo](<https://devfeed.tech/tags/duo.md>), [environment](<https://devfeed.tech/tags/environment.md>), [failed](<https://devfeed.tech/tags/failed.md>), [flow](<https://devfeed.tech/tags/flow.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [harness](<https://devfeed.tech/tags/harness.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [install](<https://devfeed.tech/tags/install.md>), [issue](<https://devfeed.tech/tags/issue.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>)

### AI overview

The GitLab Duo setup skill connects a local coding harness to GitLab Duo Agent Platform, where repository-aware work runs as GitLab flows and merge requests remain subject to existing review, pipeline, security, and approval policies. After reviewing one setup plan, an Owner can enable group workflows, automatic code review, failed-pipeline automation, and the GitLab MCP connection; a project Maintainer can configure only that project. The walkthrough covers handing assigned issues to Developer, reviewing MRs and resolving feedback or conflicts, fixing failed pipelines, and--on Ultimate--triaging security findings. Pipeline fixes appear as inline suggestions when they fit the MR diff, as a new MR when they require other files or no MR is open, or as guidance when a reliable fix cannot be determined or the failure is security-sensitive. Prerequisites include a GitLab.com group with GitLab Credits, a project with pipelines and work items, and Claude Code plus git and glab; group-wide setup requires the Owner role. The pipeline flow reads only the last 150 KiB of a job log. Security automation offers standard and conservative presets with different thresholds and open-MR limits.

### Source excerpt

You can build an agentic engineering environment to drive greater automation throughout your workflow. How? Start in the harness you already use and connect to GitLab Duo Agent Platform once with a skill. Longer, repository-aware workflows run on GitLab, and every merge request still hits the same reviews, pipelines, scans, and approval policies. In this article, we will show you how to quickly get started, from setup to tackling four key use cases. We focus on Claude Code as the local harness because that's what we see most of our customers using but this same flow can apply to the local harness of your choosing, including Duo CLI. How to configure your agentic engineering environment If you already do most of your coding in a local harness, keep working there and wire it to GitLab Duo Agent Platform. From the terminal, you can direct lifecycle work to agentic workflows that run inside GitLab: Picking up an issue and opening a merge request Reviewing every MR as it lands Resolving merge conflicts Repairing a pipeline that just failed With GitLab Ultimate, triaging and fixing security findings once code lands Claude Code, Codex, Cursor, OpenCode, and others become the place from where you direct that work. Part 1 is the setup Install the GitLab Duo setup skill, ask Claude Code to run it, and it sets up your whole top-level group with the necessary settings, the flows, an automation in every project, and the MCP connection. Part 2 walks through four workflows You can try them as soon as the setup is done, each driven from Claude Code: Find an issue assigned to you and hand it to the Developer flow. Get automated code reviews on your merge requests, act on the findings without leaving your harness, and resolve any conflicts that pop up. Use an automation to fix a failed pipeline. On Ultimate, triage and fix security findings with the security flows. When you want an even tighter loop The MR followup skill guides your local harness through the steps above even faster.

## Detectify launches Agentic Tooling to verify vulnerabilities in live applications

DevFeed: [Detectify launches Agentic Tooling to verify vulnerabilities in live applications](<https://devfeed.tech/articles/detectify-launches-agentic-tooling-to-verify-vulnerabilities-in-live-applications-137776.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/17/detectify-agentic-tooling/>)

Author: Industry News

Published: 2026-11-17T14:13:55Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-tooling](<https://devfeed.tech/tags/agentic-tooling.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [applications](<https://devfeed.tech/tags/applications.md>), [code](<https://devfeed.tech/tags/code.md>), [detectify](<https://devfeed.tech/tags/detectify.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [environments](<https://devfeed.tech/tags/environments.md>), [exploited](<https://devfeed.tech/tags/exploited.md>), [industry-news](<https://devfeed.tech/tags/industry-news.md>), [launches](<https://devfeed.tech/tags/launches.md>), [ledger](<https://devfeed.tech/tags/ledger.md>), [live](<https://devfeed.tech/tags/live.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [verify](<https://devfeed.tech/tags/verify.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

Detectify's Agentic Tooling lets organizations' own AI agents investigate suspected vulnerabilities and test exploitability in live applications using Detectify testing engines. It runs in customers' environments through MCP and a CLI, with their own agents and models, on data they provide. In automated workflows, agents can take findings from code scans, bug bounties, red teams or attack-surface data, test them externally and produce evidence. The append-only Security Ledger records requests, payloads and results, links them to the original ticket, and helps teams distinguish tested findings from unsupported agent claims. Detectify says the approach addresses noisy AI-driven SAST output and aims to keep verification pace with rapid software delivery; the article notes the tooling builds on its MCP Server and that future integrations may trigger investigations from new platform data.

### Source excerpt

Detectify has launched Agentic Tooling. It lets organizations' own AI agents, running in their own environments, proactively investigate suspected vulnerabilities and test whether they can be exploited in running applications. A new Security Ledger lets security teams verify agents' findings against objective evidence, ensuring informed decisions rather than relying solely on probabilistic conclusions. The tools address a growing gap in DevSecOps. Engineering teams have built software factories that move code from commit to production in ... More -> The post Detectify launches Agentic Tooling to verify vulnerabilities in live applications appeared first on Help Net Security.

## Build Durable, Secure Long-Running Agents

DevFeed: [Build Durable, Secure Long-Running Agents](<https://devfeed.tech/articles/build-durable-secure-long-running-agents-139474.md>)

Original publisher: [Read original article](<https://www.decodingai.com/p/build-durable-secure-long-running-agents>)

Author: Paul Iusztin

Published: 2026-11-17T07:02:53Z

Content type: tutorial

Language: en

Sources: [Decoding ML](<https://devfeed.tech/sources/decoding-ml.md>)

Topics: [long-running](<https://devfeed.tech/topics/long-running.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [22](<https://devfeed.tech/tags/22.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [added](<https://devfeed.tech/tags/added.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-builder](<https://devfeed.tech/tags/agent-builder.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-graphrag](<https://devfeed.tech/tags/agentic-graphrag.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [build](<https://devfeed.tech/tags/build.md>), [code](<https://devfeed.tech/tags/code.md>), [crashes](<https://devfeed.tech/tags/crashes.md>), [long-running](<https://devfeed.tech/tags/long-running.md>), [long-running-agents](<https://devfeed.tech/tags/long-running-agents.md>), [run](<https://devfeed.tech/tags/run.md>), [running](<https://devfeed.tech/tags/running.md>)

### AI overview

The article describes CodeClimb, an overnight coding-agent workflow that improves code against dataset-based metrics while isolating coding from evaluation. A TypeScript orchestrator enforces metric, round, time, and spend limits; a metering proxy holds provider credentials, meters calls, and blocks models outside an allowlist. Inngest checkpoints experiment and evaluation steps so runs can resume after tested worker or network interruptions, while explicit cleanup is needed to stop active agents and sandboxes. Human events can pause runs without occupying workers, and per-experiment Git commits preserve the best result and provide a basis for continuation. In the GraphRAG example, the workflow approached its node extraction target but missed edge extraction; test retrieval and graph-merge metrics exceeded 0.9. The author reports about $75 for the winning night, notes dataset quality as a major bottleneck, and says the resulting code was not suitable for production scaling. Cloud deployment with Inngest Sandboxes is described, with a one-hour active runtime limit.

### Source excerpt

From crashes, throwaway code and surprise bills to a $74.63 run you are proud of

## Build Your Own Software Factory in 5 Steps

DevFeed: [Build Your Own Software Factory in 5 Steps](<https://devfeed.tech/articles/build-your-own-software-factory-in-5-steps-138259.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/build-your-own-software-factory-in>)

Author: Daniel Moka

Published: 2026-11-17T06:01:53Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [issue tracking](<https://devfeed.tech/topics/issue-tracking.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [autopilot](<https://devfeed.tech/tags/autopilot.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud-agent](<https://devfeed.tech/tags/cloud-agent.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [control](<https://devfeed.tech/tags/control.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>)

### AI overview

The guide describes a five-step GitHub workflow that turns reports into reviewed pull requests while leaving merge approval to a person. Jev routes support emails and issues; a question about instructions outside the reported problem adds `needs-human` to keep suspicious issues away from coding agents. CodeRabbit Plan posts implementation plans, and a coding agent claims `planned` issues and opens pull requests. CodeRabbit reviews each push; the agent responds to findings, while configured checks can flag weakened tests and run security scanners. A script signals readiness only after CI is green and review is complete. CodeRabbit Triage ranks queued pull requests, and Explain groups changes by purpose. For repository security, Secure offers required pre-merge review checks, scheduled or on-demand deep scans, an attack surface map, and AI-drafted fixes. The author reports one scan finding an authorization bypass and a fix that added role checks and regression tests. The workflow automates triage through review, but a person still reads and merges the pull request.

### Source excerpt

The 5-step guide to implementing an end-to-end software factory on your repositories.

## Agentic AI-Empowered Dynamic Survey Framework

DevFeed: [Agentic AI-Empowered Dynamic Survey Framework](<https://devfeed.tech/articles/agentic-ai-empowered-dynamic-survey-framework-138740.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.04071>)

Author: Furkan Mumcu, Lokman Bekit, Michael J. Jones, Anoop Cherian, Yasin Yilmaz

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [coherence](<https://devfeed.tech/tags/coherence.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [framework](<https://devfeed.tech/tags/framework.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [structure](<https://devfeed.tech/tags/structure.md>), [survey](<https://devfeed.tech/tags/survey.md>), [surveys](<https://devfeed.tech/tags/surveys.md>)

### AI overview

The framework treats survey papers as living documents that need ongoing maintenance as new research appears. It incrementally integrates emerging work into existing surveys while aiming to preserve their structure and minimize disruption. In retrospective experiments, it reportedly identified and incorporated new research while maintaining coherence and structure across extended update sequences.

### Source excerpt

arXiv:2602.04071v2 Announce Type: replace Abstract: Survey papers play a central role in synthesizing and organizing scientific knowledge, yet they are increasingly strained by the rapid growth of research output. As new work continues to appear after publication, surveys quickly become outdated, contributing to redundancy and fragmentation in the literature. We reframe survey writing as a long-horizon maintenance problem rather than a one-time generation task, treating surveys as living documents that evolve alongside the research they describe. We propose an agentic Dynamic Survey Framework that supports the continuous updating of existing survey papers by incrementally integrating new work while preserving survey structure and minimizing unnecessary disruption. Using a retrospective experimental setup, we demonstrate that the proposed framework effectively identifies and incorporates emerging research while preserving the coherence and structure of existing surveys, even over extended sequences of updates.

## Does a completed simulation run mean a usable urban wind result for AI agents?

DevFeed: [Does a completed simulation run mean a usable urban wind result for AI agents?](<https://devfeed.tech/articles/does-a-completed-simulation-run-mean-a-usable-urban-wind-result-for-ai-agents-137441.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19385>)

Author: Zhongke Qu, Yunwei Zhang, Junwei Su, Yabin Zhang, Chengwei Li, Qingxiang Shui, Hailong Qu, Zhaolin Gu

Published: 2026-11-17T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Simulation](<https://devfeed.tech/topics/simulation.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cfd](<https://devfeed.tech/tags/cfd.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [execution](<https://devfeed.tech/tags/execution.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [parsing](<https://devfeed.tech/tags/parsing.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [raw](<https://devfeed.tech/tags/raw.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [token-consumption](<https://devfeed.tech/tags/token-consumption.md>), [usability](<https://devfeed.tech/tags/usability.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

A completed CFD run did not guarantee usable urban-wind metrics: on 30 OpenFOAM tasks, a base agent reached the structural-score maximum on 28 but earned numerical credit on only 6. UrbanWind-AgentBench defines contracts for variable and fixed conditions, thresholds and deliverables, and separates structural checks--including provenance and raw evidence--from numerical scores independently recomputed against references. WindPilot adds contract parsing, execution provenance, deterministic verification and bounded acceptance review to the execution loop. With the same model name and budget, it earned numerical credit on 17 tasks, achieved full scores on 3, and raised the mean score from 62.5 to 72.5; it also reduced mean action steps from 130.4 to 104.9 and token use by 12.9%. The reported mean gain was 18.5 points for atmospheric boundary layer tasks. Results are limited to the stated 30-task evaluation.

### Source excerpt

arXiv:2611.19385v1 Announce Type: new Abstract: AI agents based on large language models (LLMs) can now configure and run computational fluid dynamics (CFD) solvers, but a completed run does not ensure that delivered metrics can be recomputed from raw outputs. This gap was examined for urban wind simulation, where multi-case comparisons must hold non-target conditions fixed and reported values must be traceable to raw samples. UrbanWind-AgentBench, comprising 200 tasks and 367 cases in 10 engineering task families, was constructed. Public task contracts specify variable factors, fixed conditions, numerical thresholds and deliverable requirements, and two-layer scoring separates a structural score for deliverables, run provenance and raw evidence from a numerical score obtained by independent recomputation against references. WindPilot was then proposed as an execution framework that incorporates contract parsing, execution provenance, deterministic verification and bounded acceptance review into the LLM execution loop. On 30 OpenFOAM tasks with independent references, at least the structural maximum of 60 points was reached by a base agent on 28 tasks, but numerical credit was obtained on only 6. With the same model name and budget, WindPilot increased the number of tasks with numerical credit to 17, full-score tasks from 0 to 3 and the mean task score from 62.5 to 72.5. Mean action steps fell from 130.4 to 104.9, and mean token consumption decreased by 12.9%. The mean gain for atmospheric boundary layer (ABL) tasks was 18.5 points. A completed simulation run is therefore not sufficient for a usable urban wind result; usability depends on checks that tie reported metrics to raw evidence during execution.

## Loop Engineering: Version-Bound, Evidence-Gated Coordination for Production Coding Agents

DevFeed: [Loop Engineering: Version-Bound, Evidence-Gated Coordination for Production Coding Agents](<https://devfeed.tech/articles/loop-engineering-version-bound-evidence-gated-coordination-for-production-coding-agents-137957.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18571>)

Author: Yupeng Pang, Meiling Chen, Yang Yang, Wei Fu

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [release engineering](<https://devfeed.tech/topics/release-engineering.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [version-control](<https://devfeed.tech/topics/version-control.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-loops](<https://devfeed.tech/tags/agent-loops.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-design](<https://devfeed.tech/tags/ai-design.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [audit](<https://devfeed.tech/tags/audit.md>), [automated](<https://devfeed.tech/tags/automated.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [commit](<https://devfeed.tech/tags/commit.md>), [context](<https://devfeed.tech/tags/context.md>), [continuous-integration](<https://devfeed.tech/tags/continuous-integration.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [loop-engineering](<https://devfeed.tech/tags/loop-engineering.md>), [production](<https://devfeed.tech/tags/production.md>), [version](<https://devfeed.tech/tags/version.md>)

### AI overview

Loop Engineering coordinates asynchronous coding-agent work through shared auditable repository state. Each loop defines a trigger, context projection, authority boundary, verifier, stop condition, and write-back rule; versioned Skills encode policy, a Harness limits actions and collects evidence, and human gates approve consequential transitions against exact artifact versions. In a production study at MewDesign, five specialized loops handled planning, implementation, review, test release, and reconciliation. Of five pull requests reaching a version-bound test lock, three advanced to test releases with runtime evidence from sources separate from deployment requests, while two stopped before merge. In one drift episode, a new commit invalidated prior approval and evidence, so stale continuous-integration results were not reused. This design-and-experience study is not a controlled benchmark and does not establish causal productivity or general safety; it offers early evidence of feasibility and traceability in one production setting.

### Source excerpt

arXiv:2611.18571v1 Announce Type: new Abstract: Coding agents can edit repositories and execute tests, yet production software work extends far beyond code generation. It requires durable task context, scoped authority, version-aware approval, source-independent verification, interruption recovery, and accountable handoffs between humans and automated workers. We present Loop Engineering, a method for operating multiple asynchronous agent loops over shared, auditable repository state without relying on private conversational handoffs. Each loop is specified by six elements: a trigger, a context projection, an authority boundary, a verifier, a stop condition, and a write-back rule. Versioned procedural contracts, called Skills, encode reusable operating policy; a Harness bounds the available action surface and collects evidence; human gates authorize high-consequence transitions against exact artifact versions. We report a design-and-experience study from MewDesign, a revenue-generating commercial AI design product. Five specialized loops cover planning, scoped implementation, review, test release, and reconciliation. A cross-sectional audit contains 50 durable marker records across 26 GitHub work items. Five pull requests reached a version-bound test lock: three proceeded to test releases with runtime evidence from sources distinct from the deployment request, and two stopped before merge. A detailed drift episode shows one observed fail-closed path: a new commit invalidated prior approval and evidence, and the workflow refused to reuse stale continuous-integration results. The study is not a controlled benchmark and does not establish causal productivity or general safety. It provides early evidence of feasibility, traceability, and bounded progression in one production setting.

## From tasks to goals

DevFeed: [From tasks to goals](<https://devfeed.tech/articles/from-tasks-to-goals-137784.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/from-tasks-to-goals>)

Author: LangChain Accounts

Published: 2026-11-16T23:53:29Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [To-Do](<https://devfeed.tech/topics/todo.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [act](<https://devfeed.tech/tags/act.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [background](<https://devfeed.tech/tags/background.md>), [based](<https://devfeed.tech/tags/based.md>), [best](<https://devfeed.tech/tags/best.md>), [better](<https://devfeed.tech/tags/better.md>), [blog](<https://devfeed.tech/tags/blog.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [browser](<https://devfeed.tech/tags/browser.md>), [bug](<https://devfeed.tech/tags/bug.md>), [but](<https://devfeed.tech/tags/but.md>), [goals](<https://devfeed.tech/tags/goals.md>), [more](<https://devfeed.tech/tags/more.md>), [moving](<https://devfeed.tech/tags/moving.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Goal-focused agents take on ongoing responsibility: they break a user's desired outcome into tasks, choose when to act, and update their plan. This shifts the user's role from specifying each action to setting direction, boundaries, and feedback. The excerpt identifies practical needs: a visible task list and varied task selection; controls over which tools agents can call, since goal-level requests make future tool use less predictable; a way for background agents to ask people for clarification; progress measures paired with human feedback to avoid blindly optimizing metrics; wake-up triggers such as heartbeats, recurring or one-off cron jobs, and event streams, plus ways to pause or stop; and memory that carries decisions and feedback across runs. The article cautions that ongoing responsibility does not mean acting constantly: sometimes doing nothing is appropriate.

### Source excerpt

LangChain CEO and Co-founder Harrison Chase shares how we're moving from task-specific agents to goal-focused agents. Learn more.

## Detectify's Agentic Tooling lets AI agents test suspected flaws in running applications

DevFeed: [Detectify's Agentic Tooling lets AI agents test suspected flaws in running applications](<https://devfeed.tech/articles/detectify-s-agentic-tooling-lets-ai-agents-test-suspected-flaws-in-running-applications-135281.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/16/detectifys-agentic-tooling-lets-ai-agents-test-suspected-flaws-in-running-applications/>)

Author: Duncan Riley

Published: 2026-11-16T08:00:53Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Security research](<https://devfeed.tech/topics/security-research.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-tooling](<https://devfeed.tech/tags/agentic-tooling.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [alfred](<https://devfeed.tech/tags/alfred.md>), [application](<https://devfeed.tech/tags/application.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-agents](<https://devfeed.tech/tags/artificial-intelligence-agents.md>), [balderton-capital](<https://devfeed.tech/tags/balderton-capital.md>), [cyber-hygiene-index](<https://devfeed.tech/tags/cyber-hygiene-index.md>), [detectify](<https://devfeed.tech/tags/detectify.md>), [detectify-ab](<https://devfeed.tech/tags/detectify-ab.md>), [detectify-mcp-server](<https://devfeed.tech/tags/detectify-mcp-server.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [exploited](<https://devfeed.tech/tags/exploited.md>), [false-positives](<https://devfeed.tech/tags/false-positives.md>), [first-fellow-partners](<https://devfeed.tech/tags/first-fellow-partners.md>), [fudan-university](<https://devfeed.tech/tags/fudan-university.md>), [insight-partners](<https://devfeed.tech/tags/insight-partners.md>), [inventure](<https://devfeed.tech/tags/inventure.md>), [launch](<https://devfeed.tech/tags/launch.md>), [ledger](<https://devfeed.tech/tags/ledger.md>), [loop-engineering](<https://devfeed.tech/tags/loop-engineering.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [news](<https://devfeed.tech/tags/news.md>), [rickard-carlsson](<https://devfeed.tech/tags/rickard-carlsson.md>), [security](<https://devfeed.tech/tags/security.md>), [security-ledger](<https://devfeed.tech/tags/security-ledger.md>), [squareone-app](<https://devfeed.tech/tags/squareone-app.md>), [static-application-security-testing](<https://devfeed.tech/tags/static-application-security-testing.md>), [surface-monitoring](<https://devfeed.tech/tags/surface-monitoring.md>), [tencent](<https://devfeed.tech/tags/tencent.md>), [tencent-holdings](<https://devfeed.tech/tags/tencent-holdings.md>), [test](<https://devfeed.tech/tags/test.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [tools](<https://devfeed.tech/tags/tools.md>), [verification-factory](<https://devfeed.tech/tags/verification-factory.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

Detectify's Agentic Tooling lets customer AI agents verify suspected vulnerabilities against running applications using Detectify's testing engines. A CI run or other finding source creates a ticket; the agent reads relevant code, then tests the live application externally. Tools run in the customer's environment, connect through MCP or a command-line interface, and use only customer-provided data. Detectify's append-only Security Ledger records requests, payloads, and results, providing evidence written by Detectify to distinguish tests actually run from unsupported agent conclusions. Potentially harmful tests, such as denial-of-service tests, are flagged for human decision. The excerpt says the offering is available on request and works with the customer's existing agent.

### Source excerpt

Swedish application security company Detectify AB today launched Agentic Tooling, a set of tools aimed at letting an organization's own artificial intelligence agents test whether suspected vulnerabilities can be exploited in running applications. A new Security Ledger, also part of the launch, is designed to record the evidence behind each test. Detectify is pitching the release [...] The post Detectify's Agentic Tooling lets AI agents test suspected flaws in running applications appeared first on SiliconANGLE.

## Software engineering when code is cheap

DevFeed: [Software engineering when code is cheap](<https://devfeed.tech/articles/software-engineering-when-code-is-cheap-134477.md>)

Original publisher: [Read original article](<https://read.theaimerge.com/p/software-engineering-when-code-is-cheap>)

Author: Alex Razvant

Published: 2026-11-15T11:31:10Z

Content type: opinion

Language: en

Sources: [Neural Bits](<https://devfeed.tech/sources/neural-bits.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [reliable codebases](<https://devfeed.tech/topics/reliable-codebases.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [agentic-software-factory](<https://devfeed.tech/tags/agentic-software-factory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [clicks](<https://devfeed.tech/tags/clicks.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The author's central finding is that AI makes it easy to start more code changes than engineers can understand, review, and safely ship. They recommend using agents first to gather project context, investigate the actual problem, and challenge a proposed plan; then choose a justified change, define checks that measure the requirement, and plan a rollback. Code generation is cheap, but review, integration, migration, and production responsibility still take human time. Automated reviews can help with low and medium impact work, while someone who knows a production service should judge readiness. The author also urges teams to protect senior reviewers' capacity and give junior engineers real problems, mentorship, and time to learn. They value simple task definitions and relevant context over elaborate agent setups, and note that long agent sessions can lose important details as context changes or gets summarized.

### Source excerpt

I can start more changes with AI than I can understand. Here's how I deal with that, and why it's a team problem too.

## Advancing science & engineering with Antigravity's /teamwork

DevFeed: [Advancing science & engineering with Antigravity's /teamwork](<https://devfeed.tech/articles/advancing-science-engineering-with-antigravity-s-teamwork-134088.md>)

Original publisher: [Read original article](<https://research.google/blog/advancing-science-engineering-with-antigravitys-teamwork-feature/>)

Published: 2026-11-13T20:47:18Z

Content type: news

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [antigravity](<https://devfeed.tech/tags/antigravity.md>), [education-innovation](<https://devfeed.tech/tags/education-innovation.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [general-science](<https://devfeed.tech/tags/general-science.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [science](<https://devfeed.tech/tags/science.md>), [teamwork](<https://devfeed.tech/tags/teamwork.md>)

### AI overview

Antigravity's /teamwork pairs specialized agents with independent checks to tackle research and engineering tasks over long horizons. Researchers set the questions and constraints; agents explore candidates, while tools such as Lean 4, test suites, simulators, and hardware counters verify results. The system limits context loss by giving agents task-specific files and tools and handing work to fresh agents for review. Reported applications include machine-checked proofs, molecular structure identification, kernel optimization, and large code rewrites. For example, a 30-agent chemistry workflow reached 95% top-1 accuracy on benchmark molecules; a Rust rewrite of libgav1 achieved bit-exact parity and, after profiling-led optimization, ran 20-30% faster than the original on x86_64 and ARM. Gemini 4 with /teamwork and /boost is available in Antigravity, Deep Review is also offered there, and the article says additional formal-proof workflows are forthcoming.

### Source excerpt

Education Innovation

## EasyFoam: Skill-Oriented OpenFOAM Agents with Evidence-Driven Evolution

DevFeed: [EasyFoam: Skill-Oriented OpenFOAM Agents with Evidence-Driven Evolution](<https://devfeed.tech/articles/easyfoam-skill-oriented-openfoam-agents-with-evidence-driven-evolution-132016.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14525>)

Author: Peng Yin, Zhiwei Chen, Tianyi Liu, Chen Li, Kai Li, Jian Cheng

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computational Fluid Dynamics (CFD)](<https://devfeed.tech/topics/cfd.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cfd](<https://devfeed.tech/tags/cfd.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [execution](<https://devfeed.tech/tags/execution.md>), [framework](<https://devfeed.tech/tags/framework.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [skill](<https://devfeed.tech/tags/skill.md>), [workflow](<https://devfeed.tech/tags/workflow.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The abstract identifies a gap in OpenFOAM agent evaluation: simulations may run successfully yet fail numerical or quantity-of-interest criteria. It introduces ExtFoamBench, which varies workflows across five axes and assesses execution completion, numerical soundness, and QoI satisfaction separately. EasyFoam externalizes CFD expertise into reusable skills. Its execution loop builds workflows from task requirements and uses structured simulation evidence to diagnose failures and guide repairs; its evolution loop turns task experience into skill updates chosen through paired evaluation. The abstract reports substantially higher task acceptance rates than baseline agents, without giving figures or further evaluation details.

### Source excerpt

arXiv:2611.14525v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly capable of automating end-to-end OpenFOAM workflows for computational fluid dynamics (CFD). However, current progress is bottlenecked by two critical limitations. First, existing evaluations are dominated by tutorial-level cases and execution-oriented metrics, masking a substantial executability--acceptability gap: successfully executed simulations often fail to satisfy prescribed numerical or quantity-of-interest (QoI) criteria. Second, domain expertise in existing systems is tightly coupled with bespoke agent architectures, limiting its reuse and continual refinement across agent implementations. To address these challenges, we introduce ExtFoamBench, a challenging benchmark for OpenFOAM agents that spans five axes of workflow variation, and separately assesses execution completion, numerical soundness, and QoI satisfaction. Complementing this, we propose EasyFoam, an agent framework that decouples CFD expertise into modular, externalized skills driven by a dual-loop mechanism. An execution loop constructs workflows from explicit task requirements and uses structured simulation evidence to diagnose failures and guide targeted repairs. Meanwhile, an evolution loop distills task experience into reusable skill updates selected through paired evaluation. Empirical evaluations demonstrate that EasyFoam achieves substantially higher task acceptance rates than baseline agents, establishing this work as a starting point for future research toward self-improving CFD agents.

## MechFoundry: An agentic loop that poses and performs engineering analyses and optimization of real-world objects

DevFeed: [MechFoundry: An agentic loop that poses and performs engineering analyses and optimization of real-world objects](<https://devfeed.tech/articles/mechfoundry-an-agentic-loop-that-poses-and-performs-engineering-analyses-and-optimization-of-real-world-objects-132023.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14571>)

Author: Xue-Ling Luo, Marco Conte, Peter Yichen Chen, Nikolaos Bouklas

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Finite Element Method (FEM)](<https://devfeed.tech/topics/finite-element-method.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-loop](<https://devfeed.tech/tags/agentic-loop.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [automate](<https://devfeed.tech/tags/automate.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [loading](<https://devfeed.tech/tags/loading.md>), [material](<https://devfeed.tech/tags/material.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [object](<https://devfeed.tech/tags/object.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [shape](<https://devfeed.tech/tags/shape.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

MechFoundry automates structural analysis and design improvement from an object's text description: it generates a shape, infers a use-related loading case, assigns materials to parts, solves nonlinear structural response, and optimizes the design for those loads. A differentiable GPU solver using an adaptive octree supports the transition from shape generation to simulation and optimization. Across 50 everyday and engineering objects, the system posed and solved a loading case in an average of 6.5 minutes and US$1.3 per object. Because there is no test suite to verify the engineering decisions, language-model reviewers graded sessions as an initial assessment of where the agent's judgment succeeds or fails.

### Source excerpt

arXiv:2611.14571v1 Announce Type: cross Abstract: AI agents can automate software engineering because a compiler or a test suite checks that the code does what the user or the agent intended. In engineering analysis, however, the steps that precede the computation have few easily verifiable checks: modeling a design or an object, deciding how it is used, where supports and loads are applied, and what material each part is made of. A human expert therefore makes these decisions, carries out the steps, and judges the result, one object at a time. We present MechFoundry, an agentic loop coupled with bespoke software that automates structural analyses of real-world objects without a human in the loop. From an object's lexical description, it generates a shape, poses a loading case relevant to how the object is used, assigns a material to each part, solves the nonlinear structural response, and improves the design against the loads it carries. A differentiable GPU solver built on an adaptive octree that need not conform to the surface enables the transition from shape generation to simulation and optimization. Across 50 everyday and engineering objects, the agent posed and solved a loading case in 6.5 minutes and for US$1.3 per object on average. Without a test suite to check against, we had language-model reviewers grade each session, as a first indication of where the agent's engineering judgment holds and where it fails.

## AVA: Agentic Variant Adjudication for Automated, Auditable Read-Level Review in Cancer Diagnostic Sequencing

DevFeed: [AVA: Agentic Variant Adjudication for Automated, Auditable Read-Level Review in Cancer Diagnostic Sequencing](<https://devfeed.tech/articles/ava-agentic-variant-adjudication-for-automated-auditable-read-level-review-in-cancer-diagnostic-sequencing-132021.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14560>)

Author: Caleb Chin, Sidharth Gupta, Arun K Anguraj Vadivel, Robert Siddaway, Siddharth Arya, Arianna He, Peter Zhukovsky, Cynthia Hawkins

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [To-Do](<https://devfeed.tech/topics/todo.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [automated](<https://devfeed.tech/tags/automated.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cancer](<https://devfeed.tech/tags/cancer.md>), [claude-sonnet-5](<https://devfeed.tech/tags/claude-sonnet-5.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [dna](<https://devfeed.tech/tags/dna.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gemma-4-31b](<https://devfeed.tech/tags/gemma-4-31b.md>), [generate](<https://devfeed.tech/tags/generate.md>), [glm-5-3-flash](<https://devfeed.tech/tags/glm-5-3-flash.md>), [in-the-loop](<https://devfeed.tech/tags/in-the-loop.md>), [inspection](<https://devfeed.tech/tags/inspection.md>), [q-bio-gn](<https://devfeed.tech/tags/q-bio-gn.md>), [review](<https://devfeed.tech/tags/review.md>), [rna](<https://devfeed.tech/tags/rna.md>), [variant](<https://devfeed.tech/tags/variant.md>)

### AI overview

AVA automates read-level review of borderline cancer-sequencing variants, where fixed VAF and depth thresholds cannot reliably distinguish mutations from artifacts. Its subagents examine evidence, generate investigative code, and produce real-or-artifact adjudications with auditable reasoning, without training on existing data. In a subsample of borderline cases from the SEQC2 DNA-seq benchmark and patient RNA-seq data, Claude Sonnet 5, GLM 5.3 Flash, and Gemma 4 31b reportedly outperformed the best achievable VAF/depth thresholds. The framework can run locally with open-weight models for privacy-constrained settings and provides traces intended to keep specialists involved. The supplied text does not give performance metrics or describe results beyond those evaluation settings.

### Source excerpt

arXiv:2611.14560v1 Announce Type: cross Abstract: Identifying a tumor's DNA mutations is central to cancer diagnosis and treatment, but distinguishing genuine mutations from sequencing artifacts is error-prone. In practice, genuine mutations are identified using fixed variant-allele-frequency (VAF) and depth thresholds which cannot separate artifacts from genuine mutations in the borderline low-VAF zone where they overlap. A laboratory specialist must manually inspect the read-level sequencing data, a slow step that has high inter-rater variability and causes diagnosis delays. We present AVA: Agentic Variant Adjudication; an agentic framework that automates this read-level inspection with subagents that reason over evidence, generate investigative code, and return a real-or-artifact adjudications with an auditable reasoning trace all without training on existing data. On both the SEQC2 DNA-seq benchmark and patient RNA-seq data, restricted to a subsample of borderline variants where thresholds fail, both closed-source (Claude Sonnet 5) and open-weight (GLM 5.3 Flash and Gemma 4 31b) agents outperform the best achievable VAF/depth thresholds. Ultimately, AVA is suited for privacy-constrained clinical deployment, since the framework can run on locally deployed open-weight models with descriptive reasoning traces to keep specialists in the loop.

## Build once, run on any agent: A practical guide to agent skills

DevFeed: [Build once, run on any agent: A practical guide to agent skills](<https://devfeed.tech/articles/build-once-run-on-any-agent-a-practical-guide-to-agent-skills-132660.md>)

Original publisher: [Read original article](<https://github.blog/ai-and-ml/github-copilot/build-once-run-on-any-agent-a-practical-guide-to-agent-skills/>)

Author: Andrea Griffiths

Published: 2026-11-12T22:54:52Z

Content type: tutorial

Language: en

Sources: [GitHub Blog](<https://devfeed.tech/sources/github-engineering.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [build](<https://devfeed.tech/tags/build.md>), [can](<https://devfeed.tech/tags/can.md>), [capture](<https://devfeed.tech/tags/capture.md>), [context](<https://devfeed.tech/tags/context.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [files](<https://devfeed.tech/tags/files.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-universe](<https://devfeed.tech/tags/github-universe.md>), [guide](<https://devfeed.tech/tags/guide.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [practical](<https://devfeed.tech/tags/practical.md>), [project](<https://devfeed.tech/tags/project.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [review](<https://devfeed.tech/tags/review.md>), [run](<https://devfeed.tech/tags/run.md>), [skills](<https://devfeed.tech/tags/skills.md>), [tools](<https://devfeed.tech/tags/tools.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Agent skills are versioned directories centered on `SKILL.md` files that capture bounded, repeatable work, while the host still supplies tools, credentials, and permissions. The Data Forge example coordinates skills through a shared project manifest and a common data-platform access path; people review decisions at workflow checkpoints. Proof Agent uses a separate verifier to assess AI-generated changes and cite evidence. Its GitHub Action statically reviews diffs without executing code or running tests; a failing result blocks a merge only when configured as a required check. The article recommends keeping project details in reviewable manifests, packaging shared skill sources for each client, and verifying that each client loads the instructions and has the needed setup. For workflows needing stable interfaces, shared state, audit trails, long-running control, or permissions enforced outside the model, it says an application is a better fit.

### Source excerpt

Agent skills capture repeatable engineering work in files teams can review and reuse, while tools, project context, and permissions remain specific to the host that runs them. The post Build once, run on any agent: A practical guide to agent skills appeared first on The GitHub Blog.

## Kimi K3.1 Pro is now available in Token Pass

DevFeed: [Kimi K3.1 Pro is now available in Token Pass](<https://devfeed.tech/articles/kimi-k3-1-pro-is-now-available-in-token-pass-133480.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/kimi-k3-1-pro-is-now-available-in-token-pass>)

Author: Roman Olynyk

Published: 2026-11-12T20:56:38Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [long-context](<https://devfeed.tech/topics/long-context.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [cline](<https://devfeed.tech/tags/cline.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [deepseek-v4-1-flash](<https://devfeed.tech/tags/deepseek-v4-1-flash.md>), [glm-5-3-flash](<https://devfeed.tech/tags/glm-5-3-flash.md>), [k3](<https://devfeed.tech/tags/k3.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [kimi-k3-1-pro](<https://devfeed.tech/tags/kimi-k3-1-pro.md>), [moonshot-ai](<https://devfeed.tech/tags/moonshot-ai.md>), [subscription](<https://devfeed.tech/tags/subscription.md>), [team](<https://devfeed.tech/tags/team.md>), [token](<https://devfeed.tech/tags/token.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>), [vision](<https://devfeed.tech/tags/vision.md>), [zero-data-retention](<https://devfeed.tech/tags/zero-data-retention.md>)

### AI overview

Token Pass now includes Moonshot AI's Kimi K3.1 Pro, described as its most capable model for coding and agentic workflows, with vision, tool use, and a 1M-token context window. The Early Access subscription for Pro teams costs $30 per team monthly and provides $80 in monthly credit. It also includes Kimi K3, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash. Credit can be used with coding agents connected to AI Gateway, including fx, Pi, Cline, and Command Code, or agents built with the AI SDK. Requests served through Token Pass have zero data retention. Subscribe from the Token Pass page in the team's AI Gateway dashboard, then select `moonshotai/kimi-k3.1-pro` in the connected agent's model picker.

### Source excerpt

Token Pass now includes Kimi K3.1 Pro, Moonshot AI's most capable model for coding and agentic workflows, with vision, tool use, and a 1M context window. Token Pass is an Early Access subscription for Pro teams that includes Kimi K3, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash, with more models to come. For $30 per team per month, you get $80 in monthly credit to use in coding agents connected to AI Gateway, including fx, Pi, Cline, and Command Code, as well as agents you build with the AI SDK. Requests served through Token Pass have zero data retention. Subscribe on the Token Pass page in your team's AI Gateway dashboard, then select moonshotai/kimi-k3.1-pro in your connected agent's model picker. Read more

## From AI Tools to AI-Native: How HelloFresh Is Redesigning How Work Gets Done

DevFeed: [From AI Tools to AI-Native: How HelloFresh Is Redesigning How Work Gets Done](<https://devfeed.tech/articles/from-ai-tools-to-ai-native-how-hellofresh-is-redesigning-how-work-gets-done-130971.md>)

Original publisher: [Read original article](<https://engineering.hellofresh.com/from-ai-tools-to-ai-native-how-hellofresh-is-redesigning-how-work-gets-done-c71eb2b601f2?source=rss----ac51da0a699a---4>)

Author: Ingmar Krusch

Published: 2026-11-12T16:36:43Z

Content type: news

Language: en

Sources: [HelloTech](<https://devfeed.tech/sources/hellotech.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [internal developer platform automation](<https://devfeed.tech/topics/internal-developer-platform-automation.md>), [finops](<https://devfeed.tech/topics/finops.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-native-transformation](<https://devfeed.tech/tags/ai-native-transformation.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [applications](<https://devfeed.tech/tags/applications.md>), [automate](<https://devfeed.tech/tags/automate.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-cowork](<https://devfeed.tech/tags/claude-cowork.md>), [empowering-non-tech](<https://devfeed.tech/tags/empowering-non-tech.md>), [hellofresh](<https://devfeed.tech/tags/hellofresh.md>), [model-tiers-and-costs](<https://devfeed.tech/tags/model-tiers-and-costs.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

HelloFresh describes becoming AI-native as redesigning work around smaller teams and agents, rather than merely adding automation. Its shared foundations include a vetted AI Marketplace, a budgeted Model Router, a curated Company Brain, App Kitchen for governed hosting, and a Software Factory direction in which agents handle more delivery work while teams remain accountable. A review agent is live; broader agent identity and access controls are still in progress. Non-engineering staff build workflow tools, with personal sandboxes separated from reviewed, centrally hosted production tools; workflows involving core infrastructure, finance, or regulated customer data require Tech Team review. Routing suitable traffic to open-weight models cut model costs 41% in the first weeks, and an open-weight model matched a frontier review baseline at about 97% lower cost per review. The company tracks team delivery outcomes rather than tokens or lines of code, and says its main adoption opportunity is growing the share of employees building automated workflows. Company-wide AI-native workflows remain an ambition for next year.

### Source excerpt

Ingmar Krusch speaking at the GenAI Demo Session for non-tech HelloFresh employees HelloFresh has long brought a tech-first approach to an industry still catching up. AI extends that advantage, but only if we rethink how we work. Becoming AI-native means more than adopting tools or automating tasks. It means redesigning work across the company: removing obsolete processes, empowering smaller teams to own broader scope, and enabling AI agents to plan, decide, and execute alongside knowledge workers. Automating a flawed process only scales dysfunction. The opportunity is to fundamentally change what a team can accomplish. We are not starting from scratch, there are already many examples for agentic ways of working at HelloFresh: Our Start-Up Squads, cross-functional teams owning end-to-end scope, already build software with an AI agent as standard practice. Marketing uses AI at scale for media generation, AI-moderated focus groups, localization, and analytics. Operations has begun rolling out AI tools to over 1,000 employees. Scaling this company-wide is our core objective. This blog post shares what we've learned on our journey, from the technical foundations to the cultural shift and the lessons along the way. Enable Everyone to Build: Shared Platforms Over Custom Applications HelloFresh committed to becoming AI-native in late 2025, forming our first GenAI enablement team. In 2026, engineering began moving to agentic workflows. By mid-2026, the initiative expanded company-wide, enabling non-technical teams to automate processes and build custom applications. Instead of teams building isolated AI tools, we provide shared foundations anchored on four core pillars: Our AI Marketplace centralizes vetted skills and plugins for internal reuse. It serves Claude Code and Claude Cowork today, with support for OpenCode under way. Engineers and non-technical colleagues alike use it. Our AI Model Router gives every team one endpoint to frontier and open-weight models, with budg

## How Pinterest Improved Analytics Agent Compliance with Loop Engineering

DevFeed: [How Pinterest Improved Analytics Agent Compliance with Loop Engineering](<https://devfeed.tech/articles/how-pinterest-improved-analytics-agent-compliance-with-loop-engineering-131438.md>)

Original publisher: [Read original article](<https://medium.com/pinterest-engineering/how-pinterest-improved-analytics-agent-compliance-with-loop-engineering-d3c52d0abaa2?source=rss----4c5a5f6279b6---4>)

Author: Pinterest Engineering

Published: 2026-11-12T16:01:06Z

Content type: article

Language: en

Sources: [Pinterest](<https://devfeed.tech/sources/pinterest-engineering-blog-medium.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>)

Tags: [ads](<https://devfeed.tech/tags/ads.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [data-discovery](<https://devfeed.tech/tags/data-discovery.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [latency](<https://devfeed.tech/tags/latency.md>), [loop-engineering](<https://devfeed.tech/tags/loop-engineering.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [pinterest](<https://devfeed.tech/tags/pinterest.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [query](<https://devfeed.tech/tags/query.md>), [question](<https://devfeed.tech/tags/question.md>), [search](<https://devfeed.tech/tags/search.md>), [skill](<https://devfeed.tech/tags/skill.md>)

### AI overview

Pinterest's loop engineering process tunes its Analytics Agent through repeated, measured changes: people define compliance rules and safety boundaries, while the loop proposes and evaluates small edits to prompts, skills, context, or tools. For each rule, paired test suites check both whether the agent follows the rule when needed and skips it when unnecessary; validation, holdout, and broader regression suites help catch overfitting and collateral damage. Each fresh iteration receives a structured handoff of scores, failures, prior changes, and constraints. A change is kept only if it fixes more cases than it breaks, addresses a general pattern, and preserves protected performance. In Pinterest's internal evaluation, the process improved compliance without reducing performance on skip and regression suites; one source-search improvement required a backend change, labeled datasets, 12 loop iterations, and two verification runs. Results are limited: the reported 89.3% pooled pass rate was mostly gained in the first change, and 10.3% of cases changed verdict between runs. The evaluation used one base model and reasoning setting, and answer quality was not directly measured.

### Source excerpt

Skyler Zheng | Software Engineer II; Chris Moradi | Staff Data Scientist; Lu Liu | Staff Software Engineer; Aman Gairola | Manager II; Michael Chau | Manager II The Compliance ProblemCompliance means following the right steps at the right time Pinterest's Analytics Agent helps teams answer questions such as "How did query latency for the ads reporting pipeline change last week?" It searches the company's data ecosystem, analyzes the relevant information, and recommends an answer or course of action. Not every question requires the same steps. We call the agent compliant when it identifies and follows the steps that apply. Improving compliance is intended to make answers more consistent and reduce the risk of incomplete or inaccurate results. Examples include: Read the data-discovery skill when it needs help finding the right tools or sources. Inspect table metadata before writing SQL to learn what the columns mean, which filters are required, and whether the table has important usage notes. Search every relevant source type, including tables, dashboards, and metrics, rather than stopping at the first useful result. These are three examples from a broader set of compliance rules, and whether they apply depends on the question. If a user provides the appropriate table, the agent may not need the data-discovery skill, while an open-ended question may require a broader search. The agent must decide which rules apply and follow them when needed. That flexibility also makes compliance difficult. When the agent skips a required step, it may stop at the first table it finds, miss an important filter in the metadata, or overlook a certified metric with a more authoritative definition. It could then confidently report that "latency is down 4.2%."[1] The answer may sound reasonable while using the wrong definition, pipeline stage, or reporting window. Why manually revising the agent's instructions was not enough Measuring noncompliance showed us where the agent failed, but not

## Lights-out for AI coding agents: Gemini, ADK and a canary that rolls itself back

DevFeed: [Lights-out for AI coding agents: Gemini, ADK and a canary that rolls itself back](<https://devfeed.tech/articles/lights-out-for-ai-coding-agents-gemini-adk-and-a-canary-that-rolls-itself-back-131170.md>)

Original publisher: [Read original article](<https://medium.com/google-developer-experts/lights-out-ai-coding-agents-gemini-adk-canary-rollback-36ac910de522?source=rss----a67bd6fa7d58---4>)

Author: Nicola Guglielmi

Published: 2026-11-12T15:44:05Z

Content type: article

Language: en

Sources: [Google Developer Experts](<https://devfeed.tech/sources/google-developer-experts-medium.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [canary release](<https://devfeed.tech/topics/canary-release.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [adk](<https://devfeed.tech/tags/adk.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [canary](<https://devfeed.tech/tags/canary.md>), [devops](<https://devfeed.tech/tags/devops.md>), [error](<https://devfeed.tech/tags/error.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [google-cloud-platform](<https://devfeed.tech/tags/google-cloud-platform.md>), [mutation](<https://devfeed.tech/tags/mutation.md>), [production](<https://devfeed.tech/tags/production.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [rollback](<https://devfeed.tech/tags/rollback.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

Lights-out moves a ticket from code changes to a staged canary using six agent roles, with scripts--not models--making GO/NO-GO decisions from numeric gates. PR checks include risk, secrets, dependencies, static analysis, tests, and mutation testing; post-merge, a signed image is deployed to 5% then 25% of traffic, with PromQL comparisons triggering automatic rollback. A person must approve promotion beyond 25%. It runs locally with Podman and recorded model responses, or live with a Gemini API key; its gates and deployment path remain active in either mode. Coding roles use Gemini CLI by default, while document roles use ADK with evals; Claude and OpenAI options are described, and a Claude change was blocked by the mutation threshold. The Google Cloud profiles are documented but untested, and the project says its approach is not yet proven on repositories outside its own.

### Source excerpt

What I learned putting six agents behind numeric gates, on a laptop, with no cloud account An agent opens a pull request on a codebase nobody on the team trusts. The tests are green. Now what? Do you merge it? Do you read every line? Do you let it reach production, and if so, who notices when it breaks? A lights-out factory runs in the dark because its safety systems are trusted. I wanted to know what that safety system looks like for AI coding agents that write and ship code, so I built one: lights-out. It takes a ticket all the way to production with six agent roles, and stops it at every point where a number says no. One human decision is left, before 100% of the traffic. Everything else is either a gate or a rollback. Reading every line doesn't scale when an agent can write a thousand of them before lunch. So I stopped trying to check the code and started designing the road it drives on: which files a ticket may touch, which numbers a change has to beat, how much real traffic a canary gets before a person looks at it. The agents pick the route, the guardrails decide where it can end up. My job moved from reviewing lines to choosing thresholds, and writing down where each one comes from. It runs complete on a laptop: no cloud account, no API key, no credit card. That constraint shaped most of the design, so I'll come back to it. The rule that comes first The model never decides whether a change is good. A number does. Every station in the pipeline is a script that prints exactly one line on stdout: GO: <name> or NO-GO: <name> -- <reason>. Tests, dependency advisories, static analysis, mutation score, the canary's error rate against stable. The agents write code, review it, explain a release and triage an alert. They never sit where a threshold sits. Written down it sounds obvious. In practice it's the first thing that erodes, because asking a model "is this canary healthy?" is easier than writing the PromQL query. So it became a rule with a check behind it, and ev

[Next page](<https://devfeed.tech/topics/loop-engineering.md?cursor=WyIyMDI2LTExLTEyVDE1OjQ0OjA1KzAwOjAwIiwgIjA1YWM2YzFlLTc0ZDQtNGZmNC1iZWFkLTAyOTViOTQyNjdlOCJd>)