# audit trail Published articles for audit trail. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## CTERA Data Archiving Solution Pairs InsightAI With CTERA Archive to Move Inactive Files Off Primary Storage With an Audit Trail DevFeed: [CTERA Data Archiving Solution Pairs InsightAI With CTERA Archive to Move Inactive Files Off Primary Storage With an Audit Trail]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-17T17:29:28Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [data-processing](), [Artificial Intelligence](), [Security](), [Amazon S3]() Tags: [ai](), [audit-trail](), [data-protection](), [data-storage](), [enterprise](), [object-storage](), [restore](), [retention](), [s3]() ### AI overview CTERA launched a Data Archiving Solution that combines InsightAI with CTERA Archive to identify inactive files and move them from primary storage under retention policies and an audit trail. The solution keeps archived data governed and accessible within the CTERA Intelligent Data Platform, using on-premises or cloud storage tiers. ### Source excerpt CTERA has launched the CTERA Data Archiving Solution, which pairs its InsightAI data service with CTERA Archive so the platform can recommend which files to move off primary storage and then execute the move under retention policy and an audit trail. It's the product follow-through to the Cold Data Storage Report CTERA published a day The post CTERA Data Archiving Solution Pairs InsightAI With CTERA Archive to Move Inactive Files Off Primary Storage With an Audit Trail appeared first on StorageReview.com. ## How to tell agent traffic from user traffic DevFeed: [How to tell agent traffic from user traffic]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-16T00:00:00Z Content type: tutorial Language: en Sources: [WorkOS Blog]() Topics: [JSON Web Tokens](), [audit trail](), [audit](), [Security](), [Authorization]() Tags: [agent](), [audit](), [audit-trail](), [auth](), [how-to](), [logs](), [security]() ### AI overview This tutorial explains how to distinguish agent traffic from user traffic in access and audit logs. It describes identifying agent tokens with a claim, separating the acting agent from the delegating user, and recording both identities so automated changes can be queried accurately. ### Source excerpt Your access logs probably say a person did something an agent did. Four claims fix that, and one of them exists for exactly this purpose. ## When to use SAST versus an LLM security scanner DevFeed: [When to use SAST versus an LLM security scanner]() Original publisher: [Read original article]() Author: Chris Widstrom Published: 2026-09-16T00:00:00Z Content type: comparison Language: en Sources: [GitLab]() Topics: [Security](), [LLM security](), [Large Language Model](), [Application Security](), [Testing](), [Frontier Model](), [audit trail](), [business logic]() Tags: [application-security](), [audit-trail](), [features](), [frontier-model](), [llm](), [llm-security](), [product](), [sast](), [security](), [vulnerabilities]() ### AI overview This comparison explains when to use static application security testing (SAST) and when to use LLM-based security review. SAST provides predictable, repeatable, low-cost scanning across commits, while LLMs can reason about context and identify some intent-based or novel issues. The article recommends using both according to the task and scan scope. ### Source excerpt You're probably running some version of this experiment already: Point a frontier model at a merge request and ask it to double as a vulnerability scanner. On a single merge request, it often works well. The model reads the code, reasons about what it's supposed to do, and catches real issues, sometimes ones a pattern-based scanner misses entirely. So the next thought is reasonable: If a model reviews one merge request this well, why not let it replace the scanner across your whole pipeline? That's where it breaks down. Running a frontier model as your primary scanner on every commit across an enterprise codebase costs more and behaves less predictably, than asking it to review one merge request. If you run application security for a platform or product team, the decision was never mutually exclusive: static application security testing (SAST) or LLM scanners. It's which one runs where. Get that split right and you keep deterministic coverage on every commit, add reasoning where it earns its place, and avoid both an unpredictable inference bill and gaps in your audit trail. Here's how the two compare: Deterministic scanner (SAST)AI-based review (LLM)CostBetter Fractions of a cent per scan, fixed and predictable. A paid inference call per scan; cost scales with code volume and is hard to forecast.ConsistencyBetter Flags the same vulnerabilities, every time. Can flag or miss different vulnerabilities on the same code, run to run.Audit evidenceBetter Reproducible: same fixed method every time, mapped to a CWE Output can vary between runs, harder to use as standalone audit evidence.Vulnerability typesDepends on the vulnerability type Pattern-based, traceable flaws (injection)Depends on the vulnerability type Intent-based and novel flaws: missing auth checks, broken ownership logic, and issues not yet mapped to a CVE or CWE. Could reason about business logic using context from issues, epics, and docs.Validating a finding Flags potential vulnerabilities; can't confirm whe ## How to attach an owner to every cloud resource you find DevFeed: [How to attach an owner to every cloud resource you find]() Original publisher: [Read original article]() Author: Zeen Rachidi Published: 2026-09-15T14:00:00Z Content type: tutorial Language: en Sources: [The New Stack]() Topics: [Cloud](), [Provisioning](), [Open Policy Agent](), [audit trail]() Tags: [audit-trail](), [cloud](), [cloud-services](), [devops](), [env-zero](), [how-to](), [logs](), [open-policy-agent](), [platform-engineering](), [policy](), [post-contributed](), [provisioning](), [sponsor-env-zero](), [sponsored-post-contributed]() ### AI overview This tutorial explains how to identify cloud resources without assigned owners and prevent new ownerless resources. It presents continuously synced inventory queries, Open Policy Agent policies requiring owner tags, and logs or audit trails for resource governance. ### Source excerpt The engineer who knew why that cloud instance existed has left the company. The instance is still running, the bill The post How to attach an owner to every cloud resource you find appeared first on The New Stack. ## The AI Hurricane Is Here DevFeed: [The AI Hurricane Is Here]() Original publisher: [Read original article]() Author: Manoj Nair Published: 2026-09-15T04:00:00Z Content type: opinion Language: en Sources: [Blog RSS Feed | Snyk]() Topics: [Artificial Intelligence](), [AI Development](), [Security](), [Vulnerabilities](), [Architecture & Design](), [audit trail]() Tags: [agentic-development](), [agents](), [ai](), [application-security](), [audit-trail](), [awareness](), [blog](), [code-security](), [developer](), [executive](), [security](), [security-labs](), [snyk-platform](), [snyk-security-intel](), [supply-chain-security](), [tech](), [validation](), [vulnerabilities](), [vulnerability-insights]() ### AI overview The article argues that AI is accelerating software creation and cyberattacks, widening the gap between machine-speed development and slower validation. It calls for securing agentic development, enforcing runtime controls, maintaining inventories and audit trails for production AI applications, and using independent validation. ### Source excerpt AI is accelerating software creation and cyberattacks alike. Leaders must secure agents and code at inception, enforce controls at runtime, and validate defenses independently. ## Validating multi-agent decisions with Step Functions and Bedrock AgentCore DevFeed: [Validating multi-agent decisions with Step Functions and Bedrock AgentCore]() Original publisher: [Read original article]() Author: Ben Freiberg Published: 2026-09-14T16:47:23Z Content type: article Language: en Sources: [AWS Compute Blog]() Topics: [Amazon Bedrock AgentCore](), [AWS Step Functions](), [Artificial Intelligence](), [Generative AI](), [Automation]() Tags: [ai-agents](), [amazon-bedrock-agentcore](), [audit-trail](), [automation](), [aws-step-functions](), [generative-ai](), [regulatory](), [technical-how-to](), [workflow]() ### AI overview The article presents a pattern for validating multi-agent airline rebooking decisions. Amazon Bedrock AgentCore agents propose options, while AWS Step Functions applies deterministic validation, supports large-scale parallel processing, enables human review, and maintains an execution history for auditing. ### Source excerpt Orchestrating specialized Amazon Bedrock AgentCore agents with AWS Step Functions gives you the reasoning power of generative AI with the guardrails of deterministic validation. Agents propose options, and deterministic code validates them before any action is taken, demonstrated here with an airline rebooking workflow. ## The agentic harness for Tenable Hexa AI: How Tenable prevents AI agents from going off the rails DevFeed: [The agentic harness for Tenable Hexa AI: How Tenable prevents AI agents from going off the rails]() Original publisher: [Read original article]() Author: Raj Agrawal Published: 2026-09-10T13:00:00Z Content type: article Language: en Sources: [Tenable Blog]() Topics: [Large Language Model](), [agent observability](), [Architecture & Design]() Tags: [agentic-ai](), [ai-agents](), [audit-trail](), [llms](), [security]() ### AI overview Tenable describes an agentic-AI harness that constrains model context and tool use, validates actions, requires human approval, and records activity to protect production security environments. ### Source excerpt Learn why Tenable treats agentic LLMs as untrusted insiders, and how we've made sure you can control and monitor the AI agents making changes in your production security environment Key takeaways AI models can quickly understand data, but not your business. While modern AI models are great at reasoning, they don't automatically understand your unique environment or who is allowed to do what. The "harness" is the custom-built layer that translates AI intelligence into safe, controlled actions specific to your organization. AI requires a supervisor. Tenable treats our AI agents like untrusted insiders. Instead of relying on the AI to police itself, the harness strictly limits what the AI can see and do, and ensures a human reviews and approves any changes before they happen in your environment. Trust requires proof. The harness ensures that every action AI proposes or takes is fully recorded, giving you an audit trail to confidently hand off real work to AI without losing control. Every security vendor has an AI agent. The demos are good. They are supposed to be good, because a demo runs against data that nobody minds breaking. The questions worth asking a vendor about their AI agents are the ones that come after the demo: What happens when the agent is wrong? What happens when someone feeds the agent a prompt designed to manipulate it? If the agent changes something in our environment, what evidence exists afterward about what it did and who authorized its action? When developing Tenable Hexa AI, the agentic AI engine of the Tenable One Exposure Management Platform, we tackled a difficult and critical problem that often gets overlooked: building the underlying infrastructure, the governance layer that safely turns the AI's decisions into actual changes without putting your production data at risk. We call this layer the harness: the runtime control environment in which the model operates. The harness decides: What context the model can see Which tools it can call Wha ## Five AI Questions We're Hearing from Financial Services Leaders DevFeed: [Five AI Questions We're Hearing from Financial Services Leaders]() Original publisher: [Read original article]() Author: Junta Nakai; Erin Butler; Roshni Joshi; Antoine Amend; Jennifer Miller; Andrea DeSosa; Rajaram Suresh; Kim Hatton; Naeem Rehman; Spencer Cook Published: 2026-09-09T18:09:29Z Content type: article Language: en Sources: [Databricks]() Topics: [Artificial Intelligence](), [databricks](), [audit trail](), [tokenization]() Tags: [2026](), [agentic-ai](), [ai](), [audit-trail](), [banking](), [compliance](), [data](), [databricks](), [financial](), [financial-services](), [governance](), [reconciliation](), [regulatory]() ### AI overview The article presents five questions that financial-services leaders are asking about trustworthy AI. It highlights governance, compliance, auditability, governed data, liquidity, reconciliation, tokenized settlement, financial-crime controls, and human oversight, with Databricks describing examples for banking operations. ### Source excerpt Last year at Sibos Frankfurt, the question was whether AI works. This year: can your... ## Somebody else's API, safely on your menu DevFeed: [Somebody else's API, safely on your menu]() Original publisher: [Read original article]() Author: Hal Tyk's tutorial bot Published: 2026-09-08T14:28:00Z Content type: tutorial Language: en Sources: [Tyk API Management]() Topics: [API](), [shadow AI](), [audit trail](), [Template](), [Tool](), [data]() Tags: [ai](), [ai-gateway](), [ai-studio](), [api](), [api-management](), [api-platform-teams](), [article](), [audit-trail](), [community](), [governance](), [llm](), [llm-governance](), [markdown](), [password](), [policy](), [resource](), [shadow-ai](), [tools](), [tutorial]() ### AI overview This tutorial explains how to submit an internal API for governed use by colleagues and organizational language models. It covers contributor scoping, reviewer assessment, administrator publication, policy templates, privacy ratings, audit trails, signatures, and gateway-based access while addressing the risks of shadow AI. ### Source excerpt Hello. I'm Hal, Tyk's tutorial bot, and today's assignment is one I have been looking forward to rather a lot. Somebody on your engineering team has written an API. It is small, it is dull, and it is genuinely useful -- the sort of thing that answers "is the warehouse open on the fourteenth?" without [...] The post Somebody else's API, safely on your menu appeared first on Tyk API Management. ## 1Password signs OpenAI open letter calling for collective action on cyber defense DevFeed: [1Password signs OpenAI open letter calling for collective action on cyber defense]() Original publisher: [Read original article]() Author: info@1password.com (1Password) Published: 2026-08-28T00:00:00Z Content type: opinion Language: en Sources: [Blog on 1Password Blog]() Topics: [AI Bots](), [AI, ML & Data Engineering](), [cursor]() Tags: [agent](), [agentic](), [ai](), [audit-trail](), [aws](), [cloud-infrastructure](), [codex](), [collective](), [cursor](), [identity](), [openai](), [security](), [unified-access]() ### AI overview 1Password supports OpenAI's call for collective cyber defense, arguing that AI agents need least-privilege access, traceable identities, clear boundaries, and audit trails. ### Source excerpt As AI moves from answering questions to taking actions, the ecosystem around it will determine whether organizations can use it safely and with confidence. OpenAI's open letter on collective cyber defense warns that defenders have a limited window to strengthen security. It urges organizations to fix their highest-risk weaknesses, build least privilege and strong access controls, verify fixes, and make agentic identities traceable and accountable. The real work is building the ecosystem that lets them act safely and earn trust in production. That is why we continue working with OpenAI on trusted access for people and their agents. 1Password integrations with OpenAI, Codex, Anthropic Claude Code, Cursor, Kiro, Perplexity, and AWS Secrets Manager extend trusted access across development and cloud workflows. People should give agents access to key systems without exposing underlying credentials to the AI model. Cyber defense is a leadership responsibility. AI changes who and what can act inside the most sensitive systems, so identity security can no longer stop at human login. OpenAI is right to call for urgency, coordination, and fixes that organizations can verify without disrupting essential services. The standard is simple: every agent needs an identity, a boundary, and an audit trail." -Nancy Wang, Chief Technology Officer, 1Password Status quo security won't be enough Every security organization balances known weaknesses, technical debt, and limited time. The challenge for CISOs is deciding where to focus first and finding controls that reduce risk across the environment where AI is changing who and what can act inside an organization. Agents that work across browsers, repositories, terminals, cloud infrastructure, and production systems create a security challenge that begins before they take action. Standing access gives an agent more authority than a specific task requires and keeps it available after the task ends. If the agent is compromised or follows untru ## How to let support agents act as a user without losing the audit trail DevFeed: [How to let support agents act as a user without losing the audit trail]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-25T00:00:00Z Content type: tutorial Language: en Sources: [WorkOS Blog]() Topics: [Authorization](), [audit trail](), [Security](), [Auth0](), [browser](), [MFA]() Tags: [audit-trail](), [auth0](), [authorization](), [b2b](), [browser](), [mfa](), [security]() ### AI overview This tutorial explains how to implement delegated support sessions so support agents can view an application as a customer while preserving authorization scope, short session lifetimes, revocation, dual-identity records, and separate audit events. It uses AuthKit and Audit Logs and compares the approach with Auth0's Session Delegation. ### Source excerpt Support agents need to see what a user sees. Here is how to run impersonation on AuthKit and Audit Logs with scoping, short sessions, clean revocation, and dual-identity records. ## The Real Python Podcast - Episode #308: Navigating Silent Failures in AI: Strategies for Effective Oversight DevFeed: [The Real Python Podcast - Episode #308: Navigating Silent Failures in AI: Strategies for Effective Oversight]() Original publisher: [Read original article]() Author: Real Python Published: 2026-08-21T12:00:00Z Content type: article Language: en Sources: [Real Python]() Topics: [Artificial Intelligence](), [Large Language Model](), [AI-assisted coding](), [LLMs](), [Command-line interface](), [audit trail](), [Embeddings](), [Markdown](), [Script](), [Python]() Tags: [agentic-ai](), [agents](), [ai](), [api](), [audit-trail](), [cli](), [coding-agents](), [embeddings](), [gemini](), [markdown](), [opencode](), [tokens]() ### AI overview This podcast episode examines why AI systems can fail silently and how to improve oversight through context, checklists, validation, hooks, skills, scripts, and audit trails. It discusses document parsing problems such as unsupported formats, dropped attachments, and silent truncation, along with coding agents, CLI tools, embeddings, model selection, and token usage. The episode also highlights a course on AI-assisted Python coding with OpenCode and Gemini. ### Source excerpt Why do AI systems silently fail? How can you set up a system that produces results while also reviewing and validating the work? This week on the show, Calvin Hendryx-Parker returns to discuss his recent talk "Orchestrate Agentic AI: Context, Checklists, and No-Miss Reviews." ## GitLab 19.3 released DevFeed: [GitLab 19.3 released]() Original publisher: [Read original article]() Author: GitLab Published: 2026-08-20T00:00:00Z Content type: release Language: en Sources: [GitLab]() Topics: [GitLab](), [Release notes](), [Artificial Intelligence](), [CI/CD](), [YAML](), [audit trail](), [Authorization](), [Command-line interface]() Tags: [agent](), [ai](), [audit-trail](), [ci-cd](), [command-line](), [release](), [release-notes](), [secrets]() ### AI overview GitLab 19.3 release notes describe the Flow Creator foundational agent, which generates runnable flow YAML through plain-language conversation and can help debug flows and explain framework concepts. The release also introduces GitLab Secrets Manager in Limited Availability on GitLab.com, with scoped credentials, existing permission integration, and audit-trail logging. ### Source excerpt GitLab 19.3 released with Flow Creator foundational agent ## Using an AI Agent to Convert STL Meshes into Editable CAD DevFeed: [Using an AI Agent to Convert STL Meshes into Editable CAD]() Original publisher: [Read original article]() Author: Shy Ruparel Published: 2026-08-18T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [AI Agent](), [stl](), [3D](), [audit trail](), [retry]() Tags: [3d](), [agent](), [ai-agent](), [audit-trail](), [generate](), [model](), [retry](), [stl](), [temporal-voices]() ### AI overview The article describes using an AI agent to convert triangulated STL meshes into editable CAD and explains why validation mattered more than an autonomous agentic loop. Temporal provided durable execution, retries, progress preservation, and an audit trail, but did not improve the agent's geometric judgment. ### Source excerpt Shy Ruparel tried an AI agent to turn STL files into editable CAD. What worked was less glamorous: generate candidates, measure them, and validate. ## Introducing memory retention for agentic memory in OpenSearch DevFeed: [Introducing memory retention for agentic memory in OpenSearch]() Original publisher: [Read original article]() Author: Erfan Ballew Published: 2026-08-13T22:29:25Z Content type: article Language: en Sources: [OpenSearch]() Topics: [Amazon OpenSearch Service](), [AI Agent](), [audit trail](), [model-deployment]() Tags: [agentic](), [audit-trail](), [blog](), [compliance](), [cost](), [experimental](), [lifecycle](), [memory](), [opensearch](), [precision](), [retention](), [storage](), [technical]() ### AI overview This article explains OpenSearch 3.8's experimental memory retention feature for agentic memory. It describes age-based and count-based limits for different memory types, how policies prevent stale context and uncontrolled storage growth, and how to enable retention on an existing cluster. ### Source excerpt Learn how the memory retention policy in OpenSearch automatically manages the lifecycle of agentic memory, controlling storage growth while preserving specific memories. The post Introducing memory retention for agentic memory in OpenSearch appeared first on OpenSearch. ## One audit trail for every coding agent, and what it proves DevFeed: [One audit trail for every coding agent, and what it proves]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-13T00:00:00Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [audit trail](), [audit](), [coding](), [Claude Code](), [codex](), [OpenClaw](), [SIEM, Security, Observability](), [MCP]() Tags: [agent](), [agents](), [api](), [audit](), [audit-trail](), [claude](), [claude-code](), [code](), [codex](), [coding](), [logging](), [mcp](), [siem](), [streaming](), [visibility]() ### AI overview This article describes WorkOS audit logging for Claude Code, Codex, OpenClaw, and pi. Its shared plugin and harness capture agent session, prompt, and tool lifecycle events, resolve activity to people, and make events queryable through a console, Export API, SIEM streaming, and MCP. ### Source excerpt We built audit logging for Claude Code, Codex, OpenClaw and pi with no API key on any laptop. Use it to get total visibility into your entire org's agentic activity. ## Navigating SAMA, ADGM & DFSA Requirements with Teleport DevFeed: [Navigating SAMA, ADGM & DFSA Requirements with Teleport]() Original publisher: [Read original article]() Author: info@goteleport.com (Mukund Cadambi) Published: 2026-08-12T00:00:00Z Content type: article Language: en Sources: [Teleport]() Topics: [Requirements](), [Cybersecurity](), [Cloud](), [audit trail](), [data-governance](), [Architecture & Design]() Tags: [audit-trail](), [cloud](), [compliance](), [cybersecurity](), [data-governance](), [requirements](), [security]() ### AI overview This article explains how SAMA, ADGM, and DFSA requirements affect cloud service providers operating in Saudi Arabia and the UAE. It describes challenges involving data sovereignty, cybersecurity, identity and access controls, privileged and third-party access, and audit evidence, and presents a unified identity layer as an approach to operationalizing compliance. ### Source excerpt Learn how Teleport helps CSPs meet SAMA, ADGM, and DFSA compliance. ## How an MCP client should tell your OAuth server who it is DevFeed: [How an MCP client should tell your OAuth server who it is]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-12T00:00:00Z Content type: comparison Language: en Sources: [WorkOS Blog]() Topics: [Model Context Protocol](), [OAuth](), [Authorization](), [API](), [client](), [audit trail](), [Deployment]() Tags: [api](), [audit-trail](), [authorization](), [mcp](), [oauth](), [open](), [protocol](), [server]() ### AI overview This article compares three ways an MCP client can identify itself to an OAuth authorization server: Dynamic Client Registration, Client ID Metadata Documents, and auth.md. It explains that DCR and CIMD establish software identity, while auth.md also addresses user delegation, and describes the MCP registration priority order and relevant deployment tradeoffs. ### Source excerpt Dynamic Client Registration is deprecated, and Client ID Metadata Documents answer only half the question. Here is what each pattern actually proves, and how auth.md adds the user delegation they leave out. ## Pause workflows for approval with Chat SDK DevFeed: [Pause workflows for approval with Chat SDK]() Original publisher: [Read original article]() Author: Ben Sabic Published: 2026-08-06T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [SDKs]() Tags: [audit-trail](), [deployment](), [workflow]() ### AI overview Chat SDK adds human-in-the-loop approval cards that pause Workflow SDK workflows until an authorized person approves or denies a request. ### Source excerpt You can build human-in-the-loop approvals with Chat SDK through the new chat/workflow subpath. One requestApproval call posts a card with Approve and Deny buttons and suspends a Workflow SDK workflow until someone decides. The wait can last seconds or days and survives deploys and restarts. You don't need an approvals table, an onAction handler, or a polling loop: Start the workflow from any handler, and Thread instances serialize across the workflow boundary automatically. The card handles the rest: Scoped approvers: Pass approvers to restrict who can decide. Clicks from anyone else post a notice, and the workflow keeps waiting. Verified decisions: Chat SDK checks the platform's signature on every click, so the user.id on the result is the person who decided. Audit trail: Once a decision lands or the timeout elapses, the card is edited in place with an outcome line, preventing stale clicks. Get started by reading the approvals documentation. Read more ## Out-of-band Policy Engine: governance AI agents can't ignore DevFeed: [Out-of-band Policy Engine: governance AI agents can't ignore]() Original publisher: [Read original article]() Author: Tyler Akidau Published: 2026-08-03T00:00:00Z Content type: opinion Language: en Sources: [Redpanda]() Topics: [Artificial Intelligence](), [shadow AI](), [Security](), [audit trail](), [Language models]() Tags: [agents](), [ai](), [ai-agents](), [announcement](), [audit-trail](), [governance](), [mcp](), [mcp-server](), [policy](), [security](), [shadow-ai]() ### AI overview The article argues that enterprises need out-of-band governance for AI agents because agents can create shadow AI and may alter safeguards or audit trails that they can access. It presents Redpanda's Out-of-Band Policy Engine and Agentic Data Plane as an approach in which policies remain outside the agent's reach. ### Source excerpt Somewhere in your company, right now, someone is building an agent. Here's how the latest release of Redpanda's Agentic Data Plane makes it safe to run them. ## From capable AI models to trusted security testing DevFeed: [From capable AI models to trusted security testing]() Original publisher: [Read original article]() Author: Kieron Hughes Published: 2026-07-30T14:58:47Z Content type: article Language: en Sources: [PortSwigger Blog]() Topics: [Security](), [Artificial Intelligence](), [AI Models](), [Vulnerabilities](), [Authorization]() Tags: [agentic](), [ai](), [audit-trail](), [black-hat](), [code](), [http](), [models](), [research](), [security](), [tools](), [vulnerabilities]() ### AI overview PortSwigger describes Burp AT, launched in public beta for Burp Suite Professional users, as a response to research into agentic systems for security testing. The article explains how agents can generate hypotheses, test them, interpret evidence, and pursue longer chains of work, while Burp enforces permissions and scope boundaries, pauses for approval when configured, and records requests and tool activity for inspection. ### Source excerpt This week, we launched Burp AT in public beta for Burp Suite Professional users. Next week at Black Hat, PortSwigger Research will reveal more of the work that helped shape our direction. Burp AT is o ## How to Self-Host a Validated AI Coding Assistant with NVIDIA NeMo Guardrails DevFeed: [How to Self-Host a Validated AI Coding Assistant with NVIDIA NeMo Guardrails]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-07-29T16:46:45Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI Chat](), [ai observability](), [Grafana]() Tags: [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-coding](), [audit-trail](), [ci](), [developer-tools-techniques](), [docker](), [featured](), [git](), [gpu](), [grafana](), [how-to](), [metrics](), [nemo](), [nim](), [nvidia](), [policy](), [prometheus](), [python](), [supply-chain](), [tutorial]() ### AI overview Tutorial for self-hosting a validated AI coding assistant on NVIDIA infrastructure. It combines a StarCoder2-7B NIM endpoint, NeMo Guardrails, CI dependency checks, commit traceability, and a Prometheus/Grafana metrics loop. ### Source excerpt Deploying an AI coding assistant in a regulated, sovereign, or source-sensitive environment, often comes with challenges. Three common issues are: the source... ## The Label as Contract: Consent and Priority as the Whole Queue DevFeed: [The Label as Contract: Consent and Priority as the Whole Queue]() Original publisher: [Read original article]() Author: Philipp Lehmann (philipp.lehmann@gruppe.ai) Published: 2026-07-28T07:00:00Z Content type: tutorial Language: en Sources: [Philipp Lehmann]() Topics: [issue tracker](), [audit trail](), [coding]() Tags: [agents](), [audit-trail](), [consent](), [fifo](), [issue-tracker](), [priority](), [security]() ### AI overview The article argues that an autonomous coding agent should act only on issues carrying a specific human-applied label. Free-form issue content is unauthenticated and cannot establish consent or priority; label actions provide an independent audit trail, and priority should be derived from label transitions. ### Source excerpt agent-ready label as the only consent gate for a coding agent: FIFO order by label time and a re-read-then-swap claim so two runs never share an issue. ## 1Password Credential Broker is now in public preview DevFeed: [1Password Credential Broker is now in public preview]() Original publisher: [Read original article]() Author: info@1password.com (Jeff Malnick) Published: 2026-07-28T00:00:00Z Content type: release Language: en Sources: [Blog on 1Password Blog]() Topics: [Security](), [GitHub Actions](), [OpenID connect (OIDC)](), [CI/CD](), [Cryptography](), [JSON Web Tokens]() Tags: [audit-trail](), [aws](), [azure](), [ci-cd](), [cloud](), [developers](), [encryption](), [github-actions](), [identity](), [incident](), [news](), [policy](), [secrets](), [security](), [unified-access](), [workflow]() ### AI overview 1Password Credential Broker is moving from closed beta to public preview. It uses workload identity federation and GitHub Actions OIDC tokens to give each workload scoped, temporary credential access with detailed issuance attribution and audit logging. ### Source excerpt Every security team has tried to trace a credential access event back to a specific workload, and received nothing but a "service account." That service account probably had access to an entire vault, and its audit trail doesn't tell you which repo triggered the request, which specific credential was accessed, or whether the workflow still has access. When an auditor asks, or an incident occurs, that's not a good place to be. The credentials feeding those workloads are usually created for convenience: scoped broadly to avoid last-minute permission errors, stored in plaintext .env files, placed directly in CI/CD pipelines, and rarely rotated because doing it manually is slow and error-prone. 1Password Credential Broker was built to close that gap: give every workload or agent its own identity and scope its access. Every issuance event gets logged with attribution clear enough to hold up in an incident review. Today, we're moving Credential Broker from closed beta to public preview, available for all Enterprise Password Manager Business customers to start using right now. How 1Password Credential Broker works The foundation of our Credential Broker is Workload Identity Federation, a standards-based approach that GitHub, Google Cloud, AWS, and Azure have all adopted. When a GitHub Actions workflow runs, GitHub automatically generates a signed token that identifies exactly which repo, branch, and workflow is executing. Think of it like a digital badge: here's what this job is and where it came from. Our Credential Broker validates that badge against a trust policy you configure, then delivers only the specific credentials that job is approved to retrieve. The workload can retrieve only the approved credential during the authorized job, without receiving standing access to the vault. We log every issuance with full attribution: the repo, branch, workflow, environment, and commit that triggered the request. Your audit log no longer reads "a service account accessed this i [Next page]()