--- title: "Insulin Blog: AI Agents, Knowledge Bases & Jobs" url: https://www.insulin.dev/blog/ canonical: https://www.insulin.dev/blog/ type: Blog description: "How to build and run AI agents, ground them in your own knowledge bases, and automate work with jobs and custom apps in Insulin, the AI workspace by Suger." --- # Insulin Blog: AI Agents, Knowledge Bases & Jobs > Canonical HTML version: https://www.insulin.dev/blog/ 1. [Home](/) 2. / 3. Blog # Insulin Blog Building agents, grounding them in your own data, and putting the results to work. [ ![How to Build an AI Account-Research Agent](/images/blog/ai-account-research-agent/hero.png) Agents ## How to Build an AI Account-Research Agent Reps spend hours researching an account before a call and still miss the one thing that mattered. How to build an agent that does the research and shows its sources. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva") Aug 21, 2026 Read article ](/blog/ai-account-research-agent/) [ ![AI Agent Audit Logs: What Enterprises Record](/images/blog/ai-agent-audit-logs/hero.png) Security ### AI Agent Audit Logs: What Enterprises Record When an AI agent does something wrong, the first question is 'what exactly happened' — and most teams cannot answer it. What an agent audit log has to capture, and why. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 21, 2026 ](/blog/ai-agent-audit-logs/) [ ![AI Agent Incident Response for Enterprises](/images/blog/ai-agent-incident-response/hero.png) Security ### AI Agent Incident Response for Enterprises An AI agent will eventually take an action it should not have. The teams that handle it well decided how to detect, contain, and recover before it happened — not after. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 21, 2026 ](/blog/ai-agent-incident-response/) [ ![AI Agents for Finance Operations, Explained](/images/blog/ai-agents-for-finance-operations/hero.png) Agents ### AI Agents for Finance Operations, Explained Finance runs on recurring, rule-bound work that is perfect for agents and unforgiving of mistakes. Where AI agents fit the close, reconciliation, and reporting — safely. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 21, 2026 ](/blog/ai-agents-for-finance-operations/) [ ![AI Agents vs Workflows vs Copilots: Which to Use](/images/blog/ai-agents-vs-workflows-vs-copilots/hero.png) Agents ### AI Agents vs Workflows vs Copilots: Which to Use Three words for three different things, used as if they were one. What separates an AI agent from a workflow from a copilot, and how to pick the right one per task. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 21, 2026 ](/blog/ai-agents-vs-workflows-vs-copilots/) [ ![Change Management for Enterprise AI Rollouts](/images/blog/change-management-for-enterprise-ai/hero.png) Workspace ### Change Management for Enterprise AI Rollouts The AI rollout that fails rarely fails on the technology. It fails because people were handed a tool and left to figure out whether it was safe to trust. A rollout plan. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 21, 2026 ](/blog/change-management-for-enterprise-ai/) [ ![Enterprise AI Adoption Metrics That Matter](/images/blog/enterprise-ai-adoption-metrics/hero.png) Workspace ### Enterprise AI Adoption Metrics That Matter Logins prove people opened the tool, not that it changed their work. The adoption metrics that actually predict whether enterprise AI sticks — and how to read them. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 21, 2026 ](/blog/enterprise-ai-adoption-metrics/) [ ![Enterprise AI Spend Governance: A Practical Guide](/images/blog/enterprise-ai-spend-governance/hero.png) Security ### Enterprise AI Spend Governance: A Practical Guide AI spend does not blow up on the model price — it blows up on usage nobody is watching. How to govern AI cost by user, app, and model before the bill teaches you. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 21, 2026 ](/blog/enterprise-ai-spend-governance/) [ ![Permission-Aware Enterprise Search for AI Agents](/images/blog/permission-aware-enterprise-search/hero.png) Knowledge Bases ### Permission-Aware Enterprise Search for AI Agents An AI agent that searches everything will eventually answer from a document the asker was never allowed to see. How permission-aware search stops that at retrieval. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 21, 2026 ](/blog/permission-aware-enterprise-search/) [ ![Shadow AI: How to Find and Govern It at Work](/images/blog/shadow-ai-governance/hero.png) Security ### Shadow AI: How to Find and Govern It at Work Employees are already using AI you did not sanction. Banning it drives it underground; ignoring it leaks data. How to find shadow AI and govern it into the open. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 21, 2026 ](/blog/shadow-ai-governance/) [ ![AI Agent Observability: What Business and IT Teams Should Monitor](/images/blog/ai-agent-observability/hero.png) Automation ### AI Agent Observability: What Business and IT Teams Should Monitor Once an agent runs unattended, you monitor it or you trust it blindly. What business and IT teams should watch — completion, escalation, groundedness, cost, latency, drift — and where each signal lives. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 20, 2026 ](/blog/ai-agent-observability/) [ ![AI Agent Failure Handling: Retries to Rollbacks](/images/blog/ai-agent-failure-handling/hero.png) Jobs ### AI Agent Failure Handling: Retries to Rollbacks An agent that runs unattended will fail sometimes. What matters is what happens next — retry, degrade, hand to a person, or leave nothing behind to undo. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 20, 2026 ](/blog/ai-agent-failure-handling/) [ ![AI Agent Risk Assessment: A Reusable Business Workflow Template](/images/blog/ai-agent-risk-assessment/hero.png) Trust ### AI Agent Risk Assessment: A Reusable Business Workflow Template Before you grant an agent access, score the risk. A reusable template that rates data sensitivity, reversibility, autonomy, blast radius, oversight, and auditability — and decides what to gate. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 20, 2026 ](/blog/ai-agent-risk-assessment/) [ ![AI Agents for IT Help Desks: A Practical Automation Blueprint](/images/blog/ai-agents-for-it-help-desks/hero.png) Agents ### AI Agents for IT Help Desks: A Practical Automation Blueprint A blueprint for automating the IT help desk with AI agents: triage and route tickets, answer from your IT docs with cited sources, and gate every account change on human approval. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 20, 2026 ](/blog/ai-agents-for-it-help-desks/) [ ![AI Agents for Revenue Operations: 10 Workflows Worth Automating](/images/blog/ai-agents-for-revenue-operations/hero.png) Agents ### AI Agents for Revenue Operations: 10 Workflows Worth Automating RevOps runs on recurring, deadline-shaped, and change-triggered work — exactly what an agent handles well. Ten workflows to automate, and where a human still approves. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 20, 2026 ](/blog/ai-agents-for-revenue-operations/) [ ![AI Use-Case Prioritization: How to Choose the First Five Business Workflows](/images/blog/ai-use-case-prioritization/hero.png) Automation ### AI Use-Case Prioritization: How to Choose the First Five Business Workflows Everything looks automatable in a workshop. A scored framework — value, frequency, data, reversibility, a checkable 'done', and integrations — picks the first five that actually pay off. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 20, 2026 ](/blog/ai-use-case-prioritization/) [ ![Build vs Buy Enterprise AI Agents: A Decision Framework](/images/blog/build-vs-buy-enterprise-ai-agents/hero.png) Agents ### Build vs Buy Enterprise AI Agents: A Decision Framework A framework makes the prototype easy. Production ownership — governance, integrations, audit, reliability, security — stays expensive. A decision framework for build vs buy. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 20, 2026 ](/blog/build-vs-buy-enterprise-ai-agents/) [ ![Enterprise AI Agent Memory: What Should Agents Remember—and Forget?](/images/blog/enterprise-ai-agent-memory/hero.png) Agents ### Enterprise AI Agent Memory: What Should Agents Remember—and Forget? "Give the agent memory" is usually four different requests wearing one word. Which kind of memory each business fact belongs in, and what an agent should never keep. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 20, 2026 ](/blog/enterprise-ai-agent-memory/) [ ![The Enterprise AI Maturity Model: From Personal Copilots to Governed Agentic Work](/images/blog/enterprise-ai-maturity-model/hero.png) Workspace ### The Enterprise AI Maturity Model: From Personal Copilots to Governed Agentic Work Enterprise AI adoption is a ladder, not a switch. Five levels — copilots, grounded chat, scoped agents, scheduled jobs, governed operations — each with the capability and the governance it needs. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 20, 2026 ](/blog/enterprise-ai-maturity-model/) [ ![How to Measure AI Answer Quality and Source Coverage](/images/blog/measure-ai-answer-quality/hero.png) Search ### How to Measure AI Answer Quality and Source Coverage Fluency tells you nothing about whether an AI answer is right. The metrics that do — groundedness, source coverage, retrieval recall — and how to compute each one on your own knowledge base. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 20, 2026 ](/blog/measure-ai-answer-quality/) [ ![25 Security Questions to Ask an Enterprise AI Agent Vendor](/images/blog/25-security-questions-to-ask-an-enterprise-ai-agent-vendor/hero.png) Security ### 25 Security Questions to Ask an Enterprise AI Agent Vendor A buyer's checklist for evaluating an enterprise AI agent platform — 25 questions across data, access, scoping, actions, audit, and deletion, with the evidence to demand for each. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 19, 2026 ](/blog/25-security-questions-to-ask-an-enterprise-ai-agent-vendor/) [ ![AI Agents for Customer Support: From Answering Questions to Resolving Cases](/images/blog/ai-agents-for-customer-support-from-answering-questions-to-resolving-cases/hero.png) Agents ### AI Agents for Customer Support: From Answering Questions to Resolving Cases Support AI is moving past deflection. Here is how an agent grounds in your help docs, acts across systems with scoped access and approvals, and escalates when it should. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 19, 2026 ](/blog/ai-agents-for-customer-support-from-answering-questions-to-resolving-cases/) [ ![Enterprise AI Data Privacy: A Practical Guide for Business Teams](/images/blog/enterprise-ai-data-privacy-a-practical-guide-for-business-teams/hero.png) Trust ### Enterprise AI Data Privacy: A Practical Guide for Business Teams What company data can safely enter an AI workflow — and the operating rules for classification, access, retention, residency, and deletion that keep it that way. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 19, 2026 ](/blog/enterprise-ai-data-privacy-a-practical-guide-for-business-teams/) [ ![From AI Pilot to Production: The Enterprise Readiness Checklist](/images/blog/from-ai-pilot-to-production-the-enterprise-readiness-checklist/hero.png) Agents ### From AI Pilot to Production: The Enterprise Readiness Checklist A demo that impresses is not an agent you can trust in production. Here is the cross-functional readiness checklist for taking an AI agent live. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 19, 2026 ](/blog/from-ai-pilot-to-production-the-enterprise-readiness-checklist/) [ ![How to Calculate the ROI of AI Agents for Business Workflows](/images/blog/how-to-calculate-the-roi-of-ai-agents-for-business-workflows/hero.png) Agents ### How to Calculate the ROI of AI Agents for Business Workflows A transparent framework for AI agent ROI: value from time saved, rework avoided, faster cycles, and wider coverage, minus its build and review cost. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 19, 2026 ](/blog/how-to-calculate-the-roi-of-ai-agents-for-business-workflows/) [ ![How to Choose the Right Enterprise AI Agent Platform](/images/blog/how-to-choose-the-right-enterprise-ai-agent-platform/hero.png) Agents ### How to Choose the Right Enterprise AI Agent Platform The demo is easy. The requirements matrix is where platforms separate: knowledge grounding, integrations, governance, observability, and how an agent actually deploys. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 19, 2026 ](/blog/how-to-choose-the-right-enterprise-ai-agent-platform/) [ ![How to Evaluate AI Agents: A Business-Focused Scorecard](/images/blog/how-to-evaluate-ai-agents-a-business-focused-scorecard/hero.png) Trust ### How to Evaluate AI Agents: A Business-Focused Scorecard Response quality is not the same as good work. An AI agent evaluation framework that scores the whole task — completion, correctness, policy, escalation, cost, and latency. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 19, 2026 ](/blog/how-to-evaluate-ai-agents-a-business-focused-scorecard/) [ ![How to Test an AI Agent Before It Touches a Business System](/images/blog/how-to-test-an-ai-agent-before-it-touches-a-business-system/hero.png) Trust ### How to Test an AI Agent Before It Touches a Business System Before you grant an agent write access, put it through a test suite: golden tasks, adversarial cases, scope checks, tool-failure handling, and approvals. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 19, 2026 ](/blog/how-to-test-an-ai-agent-before-it-touches-a-business-system/) [ ![How to Write Reliable Instructions for Enterprise AI Agents](/images/blog/how-to-write-reliable-instructions-for-enterprise-ai-agents/hero.png) Agents ### How to Write Reliable Instructions for Enterprise AI Agents Most agent failures start with vague ownership and undefined exceptions. Reliable AI agent instructions read like an operating contract, not a prompt. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 19, 2026 ](/blog/how-to-write-reliable-instructions-for-enterprise-ai-agents/) [ ![RAG vs Fine-Tuning for Business AI: Which One Do You Need?](/images/blog/rag-vs-fine-tuning-for-business-ai-which-one-do-you-need/hero.png) Knowledge Bases ### RAG vs Fine-Tuning for Business AI: Which One Do You Need? Teams reach for fine-tuning when what they actually need is current company knowledge. Here is what each does, and why retrieval is the default for factual business context. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 19, 2026 ](/blog/rag-vs-fine-tuning-for-business-ai-which-one-do-you-need/) [ ![How to See Past Runs of a Scheduled AI Job](/images/blog/ai-job-run-history-and-runs-table/hero.png) Jobs ### How to See Past Runs of a Scheduled AI Job An unattended agent ran overnight. The runs table on each job's detail page shows every past execution — when it ran, whether it worked, what it did. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 18, 2026 ](/blog/ai-job-run-history-and-runs-table/) [ ![Build an Internal Dashboard With AI, No Code](/images/blog/build-a-custom-app-in-plain-english/hero.png) Custom Apps ### Build an Internal Dashboard With AI, No Code Type a sentence, get a working dashboard. What happens in between — generate, compile, safety-check — is the part that decides whether you can trust it. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 18, 2026 ](/blog/build-a-custom-app-in-plain-english/) [ ![Connect Google Drive to an AI Knowledge Base](/images/blog/connect-external-sources-to-a-knowledge-base/hero.png) Knowledge Bases ### Connect Google Drive to an AI Knowledge Base Beyond uploading files: connect GitHub, Google Drive, or ClickUp to an Insulin AI knowledge base, or crawl a public site, and read sync status per source. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 18, 2026 ](/blog/connect-external-sources-to-a-knowledge-base/) [ ![Auto-Draft a Follow-Up When a Deal Stage Changes](/images/blog/crm-trigger-draft-reply-and-offer/hero.png) Inbox App ### Auto-Draft a Follow-Up When a Deal Stage Changes Wire a Salesforce stage change to a voice-matched follow-up and a staged private offer — with an approval gate so nothing sends until you say so. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 18, 2026 ](/blog/crm-trigger-draft-reply-and-offer/) [ ![How to Schedule a Recurring AI Agent Job](/images/blog/how-to-schedule-a-recurring-ai-job/hero.png) Jobs ### How to Schedule a Recurring AI Agent Job Turn a chat request into an unattended schedule: pick the agent, write the task in plain English, choose the trigger, review the runs. A step-by-step walkthrough. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 18, 2026 ](/blog/how-to-schedule-a-recurring-ai-job/) [ ![How to Build a Grounded AI Agent for Marketplace Ops](/images/blog/how-to-build-a-grounded-agent-marketplace-ops/hero.png) Agents ### How to Build a Grounded AI Agent for Marketplace Ops The six-step build for a document-grounded marketplace ops agent in Insulin: name it, scope it, pick a model, attach knowledge bases, allowlist integrations. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 18, 2026 ](/blog/how-to-build-a-grounded-agent-marketplace-ops/) [ ![How to Share an Internal App with Roles](/images/blog/publish-a-custom-app-with-roles/hero.png) Custom Apps ### How to Share an Internal App with Roles Roll one app out to everyone with a safe default role, then grant a named few more — the Viewer, User, Editor, Admin, Owner ladder, org-wide. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 18, 2026 ](/blog/publish-a-custom-app-with-roles/) [ ![Install an AI Agent for the Whole Organization](/images/blog/roll-out-an-agent-org-wide/hero.png) Agent Marketplace ### Install an AI Agent for the Whole Organization The eval-first way to install an AI agent for the whole organization: try it on your own account first, then roll the same component out org-wide once it earns its place. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 18, 2026 ](/blog/roll-out-an-agent-org-wide/) [ ![Restrict Which Integrations an AI Agent Can Access](/images/blog/scope-an-agent-to-its-integrations/hero.png) Agents ### Restrict Which Integrations an AI Agent Can Access The integration allowlist is the safety boundary for an AI agent. Grant only the connected systems its job needs, and it cannot reach data outside them. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 18, 2026 ](/blog/scope-an-agent-to-its-integrations/) [ ![How to Weight Vector vs Keyword Search](/images/blog/tune-hybrid-search-vector-keyword-weight/hero.png) Search ### How to Weight Vector vs Keyword Search Hybrid search has a dial. How to weight vector vs keyword matching in a knowledge base, when to pick a pure mode, and how to read the relevance score. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 18, 2026 ](/blog/tune-hybrid-search-vector-keyword-weight/) [ ![Agents and Skills: What the Difference Is](/images/blog/agents-and-skills/hero.png) Agents ### Agents and Skills: What the Difference Is An agent is who you talk to. A skill is what it knows how to do. Getting the distinction right decides whether you build one thing or twenty. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 16, 2026 ](/blog/agents-and-skills/) [ ![When to Build a Custom App, Not a Dashboard](/images/blog/custom-app-or-dashboard/hero.png) Custom Apps ### When to Build a Custom App, Not a Dashboard A dashboard shows you a number. An app lets someone do something about it. Choosing wrongly is why so many dashboards get opened once. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 16, 2026 ](/blog/custom-app-or-dashboard/) [ ![Build an Internal Tool Without Writing Code](/images/blog/build-an-internal-tool-without-code/hero.png) Custom Apps ### Build an Internal Tool Without Writing Code The dashboard nobody built is usually the one that needed three fields and a filter. Describing it is now faster than requesting it. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 16, 2026 ](/blog/build-an-internal-tool-without-code/) [ ![Setting Up Email Rules Without Writing Code](/images/blog/email-rules-without-code/hero.png) Inbox App ### Setting Up Email Rules Without Writing Code A rule is four decisions: which emails, what context to use, what to produce, and where it goes. None of them is a line of code, and one of them matters more than the rest. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 16, 2026 ](/blog/email-rules-without-code/) [ ![Is Your Company Data Used to Train Models?](/images/blog/is-your-data-used-to-train-models/hero.png) Trust ### Is Your Company Data Used to Train Models? The short answer is no. The longer answer is worth having, because it is the question that decides whether anyone uploads the documents that make this useful. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 16, 2026 ](/blog/is-your-data-used-to-train-models/) [ ![When to Use a Job Instead of a Conversation](/images/blog/job-or-conversation/hero.png) Jobs ### When to Use a Job Instead of a Conversation If you have asked an agent the same thing three times, you have written a job by hand. The difference is whether anyone has to be there. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 16, 2026 ](/blog/job-or-conversation/) [ ![Why a Knowledge Base Beats a Wiki for Agents](/images/blog/knowledge-base-vs-wiki/hero.png) Knowledge Bases ### Why a Knowledge Base Beats a Wiki for Agents A wiki waits to be searched. A knowledge base is read on every question, including inside jobs nobody is watching. That is the whole difference. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 16, 2026 ](/blog/knowledge-base-vs-wiki/) [ ![Your LinkedIn Network, on Autopilot](/images/blog/linkedin-network-on-autopilot/hero.png) Jobs ### Your LinkedIn Network, on Autopilot A scheduled Insulin agent runs LinkedIn prospecting in its own cloud browser — laptop off — and leaves a ranked shortlist with drafts, sending nothing. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 16, 2026 ](/blog/linkedin-network-on-autopilot/) [ ![What the Insulin Agent Marketplace Actually Is](/images/blog/what-the-insulin-agent-marketplace-is/hero.png) Agent Marketplace ### What the Insulin Agent Marketplace Actually Is It has the word marketplace in it and nothing to do with AWS, Azure or Google Cloud. One distributes software to buyers. This one distributes agents to your own team. ![Qiuyang Luo](/authors/qiuyang-luo.jpg "Qiuyang Luo")Aug 16, 2026 ](/blog/what-the-insulin-agent-marketplace-is/) [ ![When the Inbox App Acts, and When It Asks](/images/blog/when-the-inbox-app-acts-or-asks/hero.png) Trust ### When the Inbox App Acts, and When It Asks Insulin never sends email on its own. That is a deliberate default, and the interesting question is which of your rules deserves an exception. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 16, 2026 ](/blog/when-the-inbox-app-acts-or-asks/) [ ![Controlling Which Agents See Which Documents](/images/blog/which-agents-see-which-documents/hero.png) Knowledge Bases ### Controlling Which Agents See Which Documents One agent should know your pricing floor. Another should not. Document scope is set per agent, and the default for org knowledge bases is stricter than people expect. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 16, 2026 ](/blog/which-agents-see-which-documents/) [ ![How AI Learns to Write in Your Own Voice](/images/blog/ai-that-writes-in-your-voice/hero.png) Inbox App ### How AI Learns to Write in Your Own Voice A draft that does not sound like you costs more to fix than to write. How a voice profile is built from your sent mail, and what it can and cannot capture. ![Max Ma](/authors/max-ma.jpg "Max Ma")Aug 14, 2026 ](/blog/ai-that-writes-in-your-voice/) [ ![Build Your Own AI Agent, or Install One?](/images/blog/reusable-ai-agents-build-or-install/hero.png) Agents ### Build Your Own AI Agent, or Install One? Once one person has built a good specialist, the next four should not rebuild it. When to start from a catalogue agent, and when to build your own. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 13, 2026 ](/blog/reusable-ai-agents-build-or-install/) [ ![Who Can Run What: AI Workspace Permissions](/images/blog/role-based-access-for-ai-workspaces/hero.png) Workspace ### Who Can Run What: AI Workspace Permissions Sharing an AI agent across a company raises a question a personal tool never does: who can change it. How roles and install scopes fit together. ![Chengjun Yuan](/leadership/chengjun.jpeg "Chengjun Yuan")Aug 11, 2026 ](/blog/role-based-access-for-ai-workspaces/) [ ![Scheduled or Event-Driven: Timing AI Jobs](/images/blog/scheduled-vs-event-driven-ai-jobs/hero.png) Jobs ### Scheduled or Event-Driven: Timing AI Jobs A job runs once, on a timer, or when something happens. Choosing the wrong trigger is why automation arrives too late or runs constantly for nothing. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 10, 2026 ](/blog/scheduled-vs-event-driven-ai-jobs/) [ ![Keeping a Human in the Loop on AI Agents](/images/blog/human-approval-for-ai-agents/hero.png) Trust ### Keeping a Human in the Loop on AI Agents An agent that can act needs a gate before it acts. How approval works, and the difference between a review that catches things and one people click past. ![Sophia Faria](/authors/sophia-faria.jpg "Sophia Faria")Aug 8, 2026 ](/blog/human-approval-for-ai-agents/) [ ![Why Every AI Answer Needs a Cited Source](/images/blog/why-ai-answers-need-citations/hero.png) Knowledge Bases ### Why Every AI Answer Needs a Cited Source An uncited AI answer asks for trust it has not earned. What citations change about how teams adopt AI, and how to read one properly when it arrives. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 7, 2026 ](/blog/why-ai-answers-need-citations/) [ ![Hybrid vs Vector Search: Which Grounds Better](/images/blog/hybrid-search-vs-vector-search/hero.png) Knowledge Bases ### Hybrid vs Vector Search: Which Grounds Better Vector search finds meaning, keyword search finds exact terms, and business documents need both. How hybrid retrieval works and when to change its weight. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 5, 2026 ](/blog/hybrid-search-vs-vector-search/) [ ![Which Documents Can an AI Knowledge Base Read?](/images/blog/what-documents-an-ai-knowledge-base-can-read/hero.png) Knowledge Bases ### Which Documents Can an AI Knowledge Base Read? File formats, size limits, crawling, and connectors — what an Insulin knowledge base accepts, and which source is the right one to start with. ![Shirley Guo](/authors/shirley-guo.jpg "Shirley Guo")Aug 4, 2026 ](/blog/what-documents-an-ai-knowledge-base-can-read/) [ ![How to Ground an AI Agent in Your Documents](/images/blog/how-to-ground-an-ai-agent-in-your-documents/hero.png) Knowledge Bases ### How to Ground an AI Agent in Your Documents Grounding separates an AI answer you can check from one you must trust. How to attach your own documents to an agent, and what to load first. ![Zee Chen](/authors/zee-chen.jpg "Zee Chen")Aug 2, 2026 ](/blog/how-to-ground-an-ai-agent-in-your-documents/) [ ![One AI Assistant, or a Team of Specialists?](/images/blog/one-ai-assistant-or-many-specialists/hero.png) Agents ### One AI Assistant, or a Team of Specialists? A general assistant knows a little about everything and is accountable for nothing. Why scoped AI specialists behave better, and where to draw the lines. ![Gabriel Paiva](/authors/gabriel-paiva.jpg "Gabriel Paiva")Aug 1, 2026 ](/blog/one-ai-assistant-or-many-specialists/) No articles found matching your criteria. [Get Started](/schedule-demo/) [Talk to Sales](https://www.suger.io/contact-us/)