# slack Published articles for slack. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Switching to Slack DevFeed: [Switching to Slack]() Original publisher: [Read original article]() Author: Khan Academy Published: 2015-11-09T23:00:00Z Content type: article Language: en Sources: [Khan Academy]() Topics: [Slack](), [migration](), [notifications](), [systems](), [Documentation]() Tags: [administration](), [chat](), [connectivity](), [delivery](), [documentation](), [engineering](), [infrastructure](), [integration](), [migrate](), [news](), [notifications](), [organization](), [remote](), [slack](), [switching](), [team]() ### AI overview Khan Academy describes its decision to migrate team chat from HipChat to Slack after connectivity, message delivery, and notification problems affected reliability, especially for remote workers. The article outlines cultural, administrative, organizational, and integration-related costs that make chat-platform migration difficult. ### Source excerpt By Benjamin Pollack Khan Academy recently made the decision to migrate our team chat from HipChat to Slack. ... Read more ## From alert to resolution: Manage incidents with Bits Chat in Slack DevFeed: [From alert to resolution: Manage incidents with Bits Chat in Slack]() Original publisher: [Read original article]() Author: Nancy Zhu; Evan Marcantonio; Nicole Parisi; Chris Miller Published: 2026-09-16T00:00:00Z Content type: tutorial Language: en Sources: [Datadog | The Monitor blog]() Topics: [incident](), [Slack](), [Artificial Intelligence](), [telemetry](), [Code](), [Pull Request]() Tags: [ai](), [also](), [bits-ai](), [code](), [collaboration](), [ecommerce](), [incident](), [monitor](), [root-cause-analysis](), [slack](), [telemetry]() ### AI overview This tutorial explains how Bits Chat in Slack can support incident response by investigating alerts, analyzing telemetry, coordinating responders, generating a pull request for a fix, and tracking follow-up work within the incident channel. ### Source excerpt Use Bits Chat in Slack to investigate incidents, collaborate with responders, make code fixes, and capture follow-up work where your team communicates. ## From Atlas experiment to Airlock: extracting agent governance into a product DevFeed: [From Atlas experiment to Airlock: extracting agent governance into a product]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-15T15:35:36Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Authorization](), [Security](), [Artificial Intelligence](), [App](), [Linear](), [Slack]() Tags: [agent](), [ai](), [ai-agents](), [authorization](), [email](), [integrations](), [linear](), [permission](), [policy](), [product](), [security](), [slack]() ### AI overview The article explains how WorkOS's Airlock grew from the Atlas experiment into a standalone authorization product for governing AI-agent actions in company tools. A demonstration shows policies blocking emails containing financial information and requiring approval for unfamiliar distribution lists. ### Source excerpt Airlock grew out of Atlas to give IT and security teams a shared way to govern agent actions. Aaron Tainter's Agent Night demo shows how it works. ## How to Build a Fraud Signal-Sharing Strategy Across Teams and Vendors DevFeed: [How to Build a Fraud Signal-Sharing Strategy Across Teams and Vendors]() Original publisher: [Read original article]() Author: Jacob Sanchez Published: 2026-09-04T16:37:55Z Content type: tutorial Language: en Sources: [Sift Science]() Topics: [data](), [Security](), [dashboards](), [Slack]() Tags: [cross-team-fraud-collaboration](), [dashboards](), [data](), [fraud](), [fraud-kpis](), [fraud-prevention-strategy](), [fraud-signal-sharing](), [signal](), [signal-sharing-strategy](), [slack](), [strategy](), [teams](), [trust-and-safety](), [vendor-data-sharing]() ### AI overview This how-to article discusses building fraud signal-sharing programs across internal teams and vendors. It explains how shared signals such as PII, IP addresses, device data, and activity patterns can support fraud prevention, security, legal, compliance, growth, marketing, and customer support. It also compares informal sharing through Slack and email with shared dashboards and reports. ### Source excerpt I recently joined Jerry Hoff, CEO of AppSec Training, for a Blueprint Series session on fraud signal sharing, and it's a topic I keep coming back to. Fraud, trust and safety, and security teams often work from separate systems with no shared view of the same bad actor. That gap slows response time and lets [...] The post How to Build a Fraud Signal-Sharing Strategy Across Teams and Vendors appeared first on Sift. ## Manage end-user OAuth consent for AI agents with Amazon Bedrock AgentCore DevFeed: [Manage end-user OAuth consent for AI agents with Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: Swara Gandhi Published: 2026-09-14T20:35:45Z Content type: tutorial Language: en Sources: [Artificial Intelligence]() Topics: [Amazon Bedrock AgentCore](), [OAuth](), [Amazon Web Services](), [AWS CloudTrail](), [GitHub](), [Slack](), [Model Context Protocol](), [ide]() Tags: [amazon-bedrock](), [amazon-bedrock-agentcore](), [announcements](), [aws](), [aws-cloudtrail](), [claude-code](), [cursor](), [github](), [intermediate-200](), [kiro](), [model-context-protocol](), [oauth](), [slack](), [visual-studio-code]() ### AI overview This tutorial explains how Amazon Bedrock AgentCore Identity's Consent portal manages end-user OAuth consent and session binding for AI agents. It covers configuring GitHub and Slack targets through an AgentCore Gateway, storing user tokens, supporting IDE and MCP clients, and reviewing activity in AWS CloudTrail. ### Source excerpt Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and session binding endpoint for AgentCore Gateway. This post walks through provisioning a portal, configuring GitHub and Slack 3LO targets, and the end-user consent flow, and shows how to review activity in AWS CloudTrail. ## Perplexity Portable Computer Is Now Available on Windows, Powered by NVIDIA RTX DevFeed: [Perplexity Portable Computer Is Now Available on Windows, Powered by NVIDIA RTX]() Original publisher: [Read original article]() Author: Gerardo Delgado Published: 2026-09-14T15:00:52Z Content type: news Language: en Sources: [NVIDIA Blog]() Topics: [Local AI](), [Artificial Intelligence](), [NVIDIA RTX](), [Windows](), [GeForce](), [qwen](), [NVIDIA DGX](), [Cloud](), [GitHub](), [Slack](), [Google](), [Microsoft]() Tags: [agentic-ai](), [ai](), [ai-agents](), [cloud](), [dgx-spark](), [drive](), [geforce](), [github](), [google](), [local-ai](), [microsoft](), [nvidia-dgx](), [nvidia-rtx](), [open-source](), [qwen](), [rtx-pro](), [rtx-spark](), [slack](), [windows]() ### AI overview Perplexity is adding Portable Computer to its Windows app for compatible NVIDIA GeForce RTX PCs and NVIDIA RTX PRO Workstations. The local agent uses NVIDIA-accelerated models to plan multistep tasks, analyze files, and keep sensitive information on the device, while users can authorize cloud support for more advanced research and reasoning. ### Source excerpt As local models become more capable, AI agents can handle more work directly on a PC while keeping sensitive information on the device. Portable Computer is a local version of the agent Perplexity Computer that plans and carries out multistep tasks. Accelerated by NVIDIA GPUs, it uses local models to analyze data, bring together information [...] ## A working incident response model for GPU clouds DevFeed: [A working incident response model for GPU clouds]() Original publisher: [Read original article]() Author: Sridhar Rajarao Published: 2026-09-12T00:00:00Z Content type: article Language: en Sources: [Sridhar Rajarao]() Topics: [incident](), [Incident response](), [GPU](), [Monitoring](), [Tooling]() Tags: [communication](), [debugging](), [gpu](), [gpu-cloud](), [grafana](), [incident](), [incident-management](), [incident-response](), [jira](), [management](), [on-call](), [operations](), [ownership](), [pagerduty](), [review](), [slack](), [sre]() ### AI overview This article presents an incident response model for GPU clouds and other customer-facing infrastructure businesses. It emphasizes preparation, named ownership, meaningful alert paths, incident command, separation of technical work from customer communication, and post-incident learning. It argues that tools such as PagerDuty, Jira, Grafana, and Slack are useful only within a clear operating model. ### Source excerpt The tools matter, but they only work when they sit inside a clear operating model: ownership, signal, command, communication, and learning. ## The hard part of an MCP gateway is auth DevFeed: [The hard part of an MCP gateway is auth]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-11T15:22:28Z Content type: opinion Language: en Sources: [WorkOS Blog]() Topics: [MCP Server](), [Authorization](), [Model Context Protocol](), [Artificial Intelligence]() Tags: [audit](), [auth](), [github](), [integration](), [mcp](), [mcp-gateway](), [mcp-server](), [salesforce](), [scopes](), [slack](), [warehouse]() ### AI overview The article examines Sierra's internal MCP gateway and argues that its most difficult challenges are authentication, identity, per-tool scopes, consent, and audit rather than MCP protocol design. It also discusses integration work and the lack of standardized gateway behavior. ### Source excerpt Sierra's MCP gateway iceberg is a field report on agent auth: identity, per-tool scopes, consent, and audit are the submerged mass, and they ship off the shelf. ## Build custom workflows with Cypress Cloud Webhooks DevFeed: [Build custom workflows with Cypress Cloud Webhooks]() Original publisher: [Read original article]() Published: 2026-09-08T17:17:31Z Content type: tutorial Language: en Sources: [Cypress Blog]() Topics: [Cypress](), [Cloud](), [Automation](), [Messaging](), [GitHub](), [Google Chat](), [Slack]() Tags: [automation](), [cypress](), [github](), [how-to](), [integration](), [integrations](), [mcp](), [slack]() ### AI overview This tutorial introduces Cypress Cloud webhooks for building custom automation workflows. It explains how webhooks can deliver run results and metadata to external systems, trigger actions based on test outcomes, customize notifications, and reduce routine CLI or MCP requests when analyzing runs with AI tools. ### Source excerpt Webhooks are a new addition to Cypress Cloud, supporting more flexible automation workflows beyond what is built into the platform itself. Learn why we've added them and how to get started using them in your project. Integration support in Cypress Cloud Cypress Cloud supports a wide range of integrations out of the box. If you need a GitHub status check for every group of tests in your test run, we've got you covered. Slack and Teams messages when a run fails? That's there, along with deskto ## Mintlify introduces fixed, outcome-based pricing for AI actions DevFeed: [Mintlify introduces fixed, outcome-based pricing for AI actions]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-09-08T00:00:00Z Content type: release Language: en Sources: [Mintlify Blog]() Topics: [Artificial Intelligence](), [Automation](), [Documentation](), [Slack]() Tags: [agent](), [ai](), [announcements](), [automation](), [pricing](), [slack](), [updates]() ### AI overview Mintlify announces fixed credit prices for AI actions, charging for assistant answers and automation updates while making unsuccessful answers and automations with nothing to update free. The company says plan allowances and per-credit prices remain unchanged, and reports that most teams will use the same or fewer credits. ### Source excerpt Every AI action in Mintlify now has a fixed credit price, and you only pay when we deliver a result. Assistant answers and automation updates cost credits. Everything else is free. ## 🎙 How I AI: GPT-6 Astra is a banger + Stripe's AI playbook + Grok Bot vs. OpenClaw: why I replaced my entire agent stack DevFeed: [🎙 How I AI: GPT-6 Astra is a banger + Stripe's AI playbook + Grok Bot vs. OpenClaw: why I replaced my entire agent stack]() Original publisher: [Read original article]() Author: Claire Vo Published: 2026-09-07T15:02:41Z Content type: opinion Language: en Sources: [Lenny's Newsletter]() Topics: [Bot](), [OpenClaw](), [Artificial Intelligence](), [Linear](), [Slack](), [soc 2]() Tags: [agent](), [ai](), [linear](), [openclaw](), [slack](), [soc-2]() ### AI overview A podcast episode compares Grok Bot with OpenClaw through Claire's migration of her agent setup. It discusses using specialized bots for inboxes, family coordination, pull-request review, compliance monitoring, customer support, subscription audits, and shopping, along with permissions, multi-account access, and maintaining agent context and routines. ### Source excerpt Your weekly listens from How I AI, part of the Lenny's Podcast Network ## Catching Salesforce Custom Field Drift With the Postman AI Engineer DevFeed: [Catching Salesforce Custom Field Drift With the Postman AI Engineer]() Original publisher: [Read original article]() Author: Talia Kohan Published: 2026-09-03T16:00:00Z Content type: article Language: en Sources: [Postman Blog]() Topics: [Postman](), [Claude](), [Automation](), [API](), [Front end](), [OpenAPI Specification](), [GitHub](), [Back end](), [Pull Request](), [payload](), [Slack]() Tags: [ai](), [ai-automation](), [api](), [api-drift](), [backend](), [code](), [frontend](), [general](), [github](), [payload](), [postman-agent-mode](), [pull-request](), [salesforce](), [slack]() ### AI overview This Postman Blog article explains how a Salesforce custom field caused drift between an API collection, frontend code, and an OpenAPI specification. It describes using the Postman AI Engineer to diagnose the failing request and Postman AI Automation to update the affected artifacts and add tests through a GitHub pull request. ### Source excerpt A Salesforce custom field broke my app. See how Postman Agent Mode found the drift and how a Skill kept it from happening again. The post Catching Salesforce Custom Field Drift With the Postman AI Engineer appeared first on Postman Blog. ## How River takes security work from a fix to merge DevFeed: [How River takes security work from a fix to merge]() Original publisher: [Read original article]() Author: Erin Son Published: 2026-09-02T16:30:45Z Content type: article Language: en Sources: [Shopify Engineering](), [Shopify Engineering - Shopify Engineering]() Topics: [Vulnerabilities](), [AI Bots]() Tags: [agentic](), [ai-agent](), [autonomous](), [ci](), [security](), [shopify](), [slack](), [vulnerability](), [workflow]() ### AI overview Shopify describes River, an AI agent that manages vulnerability remediation from patch review through merge and verification against the repository head and dependency graph. The article reports a 70% reduction in open dependency issues during the workflow's first 11 days. ### Source excerpt River, Shopify's AI agent in Slack, enables autonomous vulnerability remediation, not just detection. ## Grok Bot vs. OpenClaw: How I replaced my entire agent stack DevFeed: [Grok Bot vs. OpenClaw: How I replaced my entire agent stack]() Original publisher: [Read original article]() Author: Claire Vo Published: 2026-09-02T12:03:39Z Content type: comparison Language: en Sources: [Lenny's Newsletter]() Topics: [OpenClaw](), [multi-agent](), [Bot](), [Pull Request](), [soc 2 compliance](), [Monitoring](), [Support](), [Slack]() Tags: [agents](), [bots](), [helpdesk](), [monitoring](), [multi-agent](), [openclaw](), [rbac](), [slack](), [soc-2-compliance]() ### AI overview A podcast episode compares Grok Bot with OpenClaw and explains why the host migrated a multi-agent setup to Grok Bot. It covers bots for inboxes, Slack, PR management, SOC 2 monitoring, customer support, family tasks, and personal activities, along with the migration process. ### Source excerpt Watch now | 🎙 I've been running Grok Bot for several weeks, and I've killed every OpenClaw I had. Here are the nine bots doing real work across my inbox, my kids' school pickups, my PR queue, and my wardrobe ## 🎙 How I AI: How this PM uses Claude to handle 70% to 80% of his workday DevFeed: [🎙 How I AI: How this PM uses Claude to handle 70% to 80% of his workday]() Original publisher: [Read original article]() Author: Lenny Rachitsky Published: 2026-08-31T15:01:58Z Content type: article Language: en Sources: [Lenny's Newsletter]() Topics: [Claude](), [Artificial Intelligence](), [Notion](), [Slack](), [email]() Tags: [ai](), [claude](), [email](), [notion](), [podcast](), [slack]() ### AI overview A podcast episode explains how Melio product manager Daniel Blum built a self-improving AI system around Claude and Cowork. The system manages parts of his Notion workflow, prepares weekly and daily briefs, scans Slack and email for relevant context, asks questions about missing knowledge, and learns from his edits. Blum says it eventually handles 70% to 80% of his workday, while emphasizing that system architecture and continuously maintained context matter more than choosing a particular AI platform. ### Source excerpt Your weekly listens from How I AI, part of the Lenny's Podcast Network ## Build Your Own AI-Powered Slack Bot with the Laravel AI SDK DevFeed: [Build Your Own AI-Powered Slack Bot with the Laravel AI SDK]() Original publisher: [Read original article]() Author: Freek Van der Herten (freek@spatie.be) Published: 2026-08-31T12:59:25Z Content type: tutorial Language: en Sources: [freek.dev - all blogposts]() Topics: [Laravel](), [Artificial Intelligence](), [SDK](), [Slack]() Tags: [ai](), [build](), [knowledge-base](), [laravel](), [php](), [providers](), [sdk](), [slack](), [spatie](), [tasks](), [tools]() ### AI overview A tutorial on building an AI-powered Slack bot with the Laravel AI SDK. The bot can switch AI providers, answer questions, execute tasks, and retrieve information from a controlled knowledge base. ### Source excerpt In this article, we'll build an AI-powered Slack bot with the Laravel AI SDK. Unlike tools such as Claude Tag, it can switch AI providers, answer questions, execute tasks, and retrieve information from a knowledge base you control. Read more ## How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio) DevFeed: [How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)]() Original publisher: [Read original article]() Author: Claire Vo Published: 2026-08-31T12:04:18Z Content type: article Language: en Sources: [Lenny's Newsletter]() Topics: [Claude](), [Notion](), [Slack](), [email](), [Artificial Intelligence](), [Automation](), [AI Infrastructure](), [User experience (UX)]() Tags: [agent-orchestration](), [automation](), [claude](), [email](), [notion](), [slack](), [ux]() ### AI overview A podcast episode in which Daniel Blum explains how he uses Claude and Cowork to manage Notion, Slack, and email workflows, automate weekly preparation, learn internal terminology, and identify improvements to his system. He also discusses scaling the setup to Melio's PM team and the remaining limitations. ### Source excerpt Listen now | 🎙 PM Daniel Blum walks through the exact Cowork and Claude setup that manages his Notion, tracks his tasks across Slack and email, and self-improves every week without him lifting a finger ## Community updates: taking time off, AI club, and next events 💬 DevFeed: [Community updates: taking time off, AI club, and next events 💬]() Original publisher: [Read original article]() Author: Luca Rossi Published: 2026-08-28T07:01:45Z Content type: article Language: en Sources: [Refactoring]() Topics: [sessions](), [Artificial Intelligence](), [Processes](), [legacy]() Tags: [ai](), [community](), [events](), [ownership](), [processes](), [projects](), [sessions](), [slack]() ### AI overview A community update recaps discussions from the August Mastermind and AI Club, including planning time off without disrupting team ownership, AI learning and legacy migrations, and upcoming events. ### Source excerpt A special edition focused on our community activities! ## Build and deploy eve agents from the Vercel dashboard DevFeed: [Build and deploy eve agents from the Vercel dashboard]() Original publisher: [Read original article]() Author: Shar Dara Published: 2026-08-28T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Bots](), [AI Chat](), [MSP MCP]() Tags: [agents](), [ai](), [ai-gateway](), [code](), [data](), [git](), [identity](), [mcp](), [mcp-server](), [model](), [next-js](), [slack](), [tools](), [vercel](), [web]() ### AI overview Vercel's dashboard can now scaffold, repository-back, and deploy eve agents, with model selection, chat channels, and service integrations. ### Source excerpt You can now create eve agents directly from the Vercel dashboard, giving you a deployed agent that you can chat with right away. The builder scaffolds the agent, creates a private Git repository with its files, and deploys it as a new Vercel project on your team. In a few clicks, you get a working agent, backed by a repo with code you can use to customize it. From the builder you can: Write the instructions that define the agent's identity Pick any model available through AI Gateway Add a Next.js web chat or Slack channel where people can talk to the agent Give the agent tools and data from other services through built-in connections like Linear and Notion, or a custom MCP server Select Add New -> Agent in your dashboard to create your first agent. Read more ## Run Claude Managed Agents with Chat SDK DevFeed: [Run Claude Managed Agents with Chat SDK]() Original publisher: [Read original article]() Author: Ben Sabic Published: 2026-08-28T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Chat](), [AI Bots](), [SDKs]() Tags: [agents](), [claude](), [database](), [slack](), [streaming](), [vercel]() ### AI overview Vercel announces support for running Claude Managed Agents with Chat SDK. The managed service runs the agent loop, model, tools, session state, and sandboxed web research server-side, with streaming replies and activity feeds for chat integrations. ### Source excerpt You can now run Claude Managed Agents with Chat SDK. Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research. That means you can ship a Slack research bot built on Claude Managed Agents and Chat SDK, with one persistent session per thread and streamed briefs with sources. What you get Token-by-token streaming: Replies render as the model writes them, over a single streamed response. Live activity feed: Tool calls and model requests are available during the turn, so you can surface a trace in the chat. No database to run: The Managed Agents session stores the conversation, so the sidebar, transcript, and replay read from it, no server-side state of your own. Portability by design: Swapping a few lines in the handler moves your agent to Teams, Google Chat, Discord, WhatsApp, and 30+ other platforms. Get started To try Claude Managed Agents with Chat SDK: Deploy a Slack research agent on Vercel in one click Follow the step-by-step guide or view the template source Read more ## Putting an agent in a shared thread makes it a colleague DevFeed: [Putting an agent in a shared thread makes it a colleague]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-27T15:16:58Z Content type: opinion Language: en Sources: [WorkOS Blog]() Topics: [Artificial Intelligence](), [Slack]() Tags: [agent](), [agents](), [ai](), [context](), [slack](), [threads]() ### AI overview The article argues that placing AI agents in shared Slack threads makes them function like colleagues, creating social and operational questions around addressing, assignment, permissions, presence, and audience. Drawing on the experience of running more than 80 team agents, it presents mention-only responses and a distinction between room membership and assignment as practical rules. ### Source excerpt Internal AI moved from dashboards into Slack threads. That changes addressing, mandate, presence, and audience -- questions that used to apply only to people. ## How we shipped a production API out of one Slack thread DevFeed: [How we shipped a production API out of one Slack thread]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-27T14:09:14Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [API](), [Slack](), [CRUD]() Tags: [agents](), [api](), [merge](), [production](), [pull-requests](), [rest](), [security](), [slack]() ### AI overview WorkOS describes how its IT Contact API was shipped from a single Slack thread. Humans made product and design decisions and gated the merge, while agents handled tickets, pull requests, review responses, and merges. The discussion shaped the API from an initial RPC proposal toward REST and resolved security, deletion, and duplicate-creation questions. ### Source excerpt The WorkOS IT Contact API went live on August 18 out of a single Slack thread. Humans made the decisions and gated the merge; agents did everything else. ## Tailscale PAM beta: Manage connectivity and privileged access in one place DevFeed: [Tailscale PAM beta: Manage connectivity and privileged access in one place]() Original publisher: [Read original article]() Author: Smriti Sharma Published: 2026-08-27T14:00:00Z Content type: release Language: en Sources: [Blog on Tailscale]() Topics: [Authorization](), [Security](), [Kubernetes](), [OpenSSH](), [API](), [Databases](), [web applications](), [incident]() Tags: [api](), [compliance](), [databases](), [external](), [identity](), [incident](), [infrastructure](), [kubernetes](), [logs](), [production](), [security](), [servers](), [slack](), [ssh](), [web-applications]() ### AI overview Tailscale PAM beta brings privileged access management into the Tailscale admin console. It provides resource-specific access policies, just-in-time approvals through Slack, and session logs and recordings for audits and investigations across databases, servers, Kubernetes clusters, and web applications. ### Source excerpt Just-in-time access, resource policies, and session auditing, right where you need them. ## Three ways to let an AI agent call third-party APIs on behalf of a user DevFeed: [Three ways to let an AI agent call third-party APIs on behalf of a user]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-27T00:00:00Z Content type: tutorial Language: en Sources: [WorkOS Blog]() Topics: [AI Agent](), [OAuth](), [Security]() Tags: [agent](), [ai-agent](), [apis](), [hubspot](), [linear](), [oauth](), [patterns](), [proxy](), [security](), [slack](), [third-party](), [tokens]() ### AI overview This article explains three patterns for letting an AI agent access third-party APIs on a user's behalf: storing OAuth credentials yourself, fetching tokens at runtime, or using a proxy that keeps tokens out of the agent-controlled runtime. It compares their operational and security implications and recommends choosing based on where the code runs and the system's requirements. ### Source excerpt Store the token yourself, fetch it at runtime, or never hold it at all. Where the credential ends up in each pattern, what each one costs, and how to pick without guessing. [Next page]()