https://www.letrelay.com/blog Playbooks for running a calm, fast internal help desk. en https://www.letrelay.com/blog/internal-help-desk-satisfaction-survey https://www.letrelay.com/blog/internal-help-desk-satisfaction-survey Thu, 24 Sep 2026 03:29:00 GMT How to measure satisfaction with an internal help desk without annoying everyone — one question after resolution, a follow-up only on bad scores, response rates, CSAT vs effort vs NPS, and turning answers into changes. https://www.letrelay.com/blog/llm-tool-calling-internal-assistant https://www.letrelay.com/blog/llm-tool-calling-internal-assistant Thu, 24 Sep 2026 03:28:00 GMT How to give an internal AI assistant tools — reading workspace data with the user's permissions, formatting results for the model, native function calling vs a routing step, limits on how many tools run, and answers that stay inside the data. https://www.letrelay.com/blog/facilities-request-management https://www.letrelay.com/blog/facilities-request-management Thu, 24 Sep 2026 03:27:00 GMT How to run facilities requests like a proper service — categories, location on every request, safety issues that skip the queue, vendor work, recurring maintenance and the numbers that show where the building needs attention. https://www.letrelay.com/blog/multilingual-chatbot-romanized-text https://www.letrelay.com/blog/multilingual-chatbot-romanized-text Thu, 24 Sep 2026 03:26:00 GMT Real users mix languages and scripts — Nepali in Devanagari and in Latin letters, Hinglish, English with local words. How to route, retrieve, parse dates and reply in the right script, with lessons from a production assistant. https://www.letrelay.com/blog/on-call-rotation-small-it-team https://www.letrelay.com/blog/on-call-rotation-small-it-team Thu, 24 Sep 2026 03:25:00 GMT How a small IT team can cover urgent issues out of hours without burning out — what's worth being paged for, rotation length, handovers, runbooks, compensation, and reviewing every page. https://www.letrelay.com/blog/stop-chatbot-hallucinations-product-help https://www.letrelay.com/blog/stop-chatbot-hallucinations-product-help Thu, 24 Sep 2026 03:24:00 GMT A help chatbot that invents buttons, settings and features is worse than no chatbot. How we fixed ours — a feature registry checked against the real UI, retrieval that finds the right page, strict grounding rules, link guards and must-not-include evals. https://www.letrelay.com/blog/it-asset-management-small-company https://www.letrelay.com/blog/it-asset-management-small-company Thu, 24 Sep 2026 03:23:00 GMT A practical IT asset management setup for small companies — what to track, one record per asset, lifecycle states from purchase to disposal, linking assets to people and requests, and the security reasons it matters. https://www.letrelay.com/blog/supabase-pg-cron-scheduled-jobs https://www.letrelay.com/blog/supabase-pg-cron-scheduled-jobs Thu, 24 Sep 2026 03:22:00 GMT How to run scheduled jobs inside Postgres on Supabase with pg_cron — idempotent schedules in migrations, catch-up logic, locking down job functions, outbound HTTP with pg_net, monitoring runs, and the free-tier pause. https://www.letrelay.com/blog/hr-service-desk https://www.letrelay.com/blog/hr-service-desk Thu, 24 Sep 2026 03:21:00 GMT How an HR service desk works — categories for pay, leave, contracts and benefits, privacy that's enforced not promised, targets that respect deadlines like payroll, self-service for policy questions, and the metrics HR can use. https://www.letrelay.com/blog/caching-llm-responses-safely https://www.letrelay.com/blog/caching-llm-responses-safely Thu, 24 Sep 2026 03:20:00 GMT Caching LLM answers saves tokens and latency — and can leak one user's data to another if done carelessly. A safe design: cache only answers that are identical for everyone, key on normalized question plus content version, expire, and lock the cache down. https://www.letrelay.com/blog/it-outage-communication-template https://www.letrelay.com/blog/it-outage-communication-template Thu, 24 Sep 2026 03:19:00 GMT Clear outage messages cut duplicate tickets and frustration. Copy-ready templates for the first notice, updates, resolution and the follow-up review — plus who sends them, where, and how often. https://www.letrelay.com/blog/validate-nextjs-server-actions-zod https://www.letrelay.com/blog/validate-nextjs-server-actions-zod Thu, 24 Sep 2026 03:18:00 GMT Server Actions are public POST endpoints. How to validate every input with Zod, check authentication and authorization inside each action, return safe errors to forms, and keep secrets and database logic server-only. https://www.letrelay.com/blog/shared-inbox-vs-help-desk https://www.letrelay.com/blog/shared-inbox-vs-help-desk Thu, 24 Sep 2026 03:17:00 GMT A shared inbox is fine until two people answer the same email and a third goes unanswered. What a shared inbox does well, where it breaks, what a help desk adds, and the signals that it's time to switch. https://www.letrelay.com/blog/intent-routing-small-llms https://www.letrelay.com/blog/intent-routing-small-llms Thu, 24 Sep 2026 03:16:00 GMT How to route chat messages to the right action or tool with a small, fast language model — a flat strict schema, deterministic argument extraction, rules before the model, a short timeout, and a 51-case evaluation — using measurements from a production assistant. https://www.letrelay.com/blog/access-request-approval-workflow https://www.letrelay.com/blog/access-request-approval-workflow Thu, 24 Sep 2026 03:15:00 GMT A secure, fast workflow for access requests — what to ask for, who approves (the manager and the data owner), time-limited access, separation of duties, provisioning, and periodic access reviews. https://www.letrelay.com/blog/reduce-llm-token-usage https://www.letrelay.com/blog/reduce-llm-token-usage Thu, 24 Sep 2026 03:14:00 GMT Practical ways to cut LLM token usage — skip the model when rules suffice, send less context, route to smaller models, cache repeated answers, use provider prompt caching and cap output — with measured numbers from a production assistant. https://www.letrelay.com/blog/help-desk-escalation-matrix https://www.letrelay.com/blog/help-desk-escalation-matrix Thu, 24 Sep 2026 03:13:00 GMT An escalation matrix says who gets pulled in, when, and how — by priority and time. A template for internal help desks, functional vs hierarchical escalation, triggers that aren't just time, and how to keep escalation from becoming noise. https://www.letrelay.com/blog/supabase-security-definer-functions https://www.letrelay.com/blog/supabase-security-definer-functions Thu, 24 Sep 2026 03:12:00 GMT In Supabase, public-schema functions are callable over the API — and SECURITY DEFINER ones bypass row-level security. What our audit found in 117 such functions, the real damage paths, and the grants and rules that close them. https://www.letrelay.com/blog/how-to-write-knowledge-base-articles https://www.letrelay.com/blog/how-to-write-knowledge-base-articles Thu, 24 Sep 2026 03:11:00 GMT A practical guide to writing internal knowledge base articles — titles in the reader's words, the answer first, numbered steps, screenshots used sparingly, a fixed template, and ownership so articles stay true. https://www.letrelay.com/blog/timezone-bugs-web-apps https://www.letrelay.com/blog/timezone-bugs-web-apps Thu, 24 Sep 2026 03:10:00 GMT Real timezone bugs from a production app — a due date showing the previous day, "today" starting at the server's midnight, server-rendered times in the wrong zone — why each happened, and the rules that prevent them. https://www.letrelay.com/blog/reduce-password-reset-tickets https://www.letrelay.com/blog/reduce-password-reset-tickets Thu, 24 Sep 2026 03:09:00 GMT Password resets are one of the most repetitive help desk requests. Cut them with self-service reset, fewer passwords (single sign-on), modern password rules from NIST, and a secure verified process for the resets that still reach a human. https://www.letrelay.com/blog/ai-agent-actions-human-confirmation https://www.letrelay.com/blog/ai-agent-actions-human-confirmation Thu, 24 Sep 2026 03:08:00 GMT How to let an AI assistant take real actions — create tasks, request leave, book meetings — safely: propose with structured fields, show an editable confirmation card, execute the confirmed values through existing server code, and report the result. https://www.letrelay.com/blog/help-desk-ticket-categories https://www.letrelay.com/blog/help-desk-ticket-categories Thu, 24 Sep 2026 03:07:00 GMT A practical guide to help desk ticket categories — how many to have, example category lists for IT, HR, finance and facilities, what each category should carry (team, type, target), and how to fix a category list that isn't working. https://www.letrelay.com/blog/rag-internal-documentation https://www.letrelay.com/blog/rag-internal-documentation Thu, 24 Sep 2026 03:06:00 GMT How to build retrieval-augmented generation over your internal docs without a big platform — structuring documents for retrieval, hybrid search, small prompts, grounding rules, permissions, and measuring whether answers are right. https://www.letrelay.com/blog/employee-offboarding-checklist-access https://www.letrelay.com/blog/employee-offboarding-checklist-access Thu, 24 Sep 2026 03:05:00 GMT A step-by-step IT offboarding checklist — timing with HR, disabling sign-in first, transferring ownership, recovering devices, removing SaaS and shared credentials — so former employees don't keep access and nothing important is lost. https://www.letrelay.com/blog/prompt-injection-internal-ai-tools https://www.letrelay.com/blog/prompt-injection-internal-ai-tools Thu, 24 Sep 2026 03:04:00 GMT Internal AI assistants read tickets, documents and messages written by other people — which makes prompt injection an internal threat too. How direct and indirect injection work, and the layered defenses that actually limit the damage. https://www.letrelay.com/blog/it-onboarding-checklist-new-employees https://www.letrelay.com/blog/it-onboarding-checklist-new-employees Thu, 24 Sep 2026 03:03:00 GMT A complete IT onboarding checklist — before day one, day one and the first week — covering accounts, devices, access by role, MFA, security basics and how to run it as a repeatable request so nothing depends on memory. https://www.letrelay.com/blog/evaluate-llm-feature-golden-set https://www.letrelay.com/blog/evaluate-llm-feature-golden-set Thu, 24 Sep 2026 03:02:00 GMT A practical way to test LLM features before shipping changes — a golden set of real inputs, deterministic checks for what must and must not appear, separate evals for retrieval, routing and answers, and running them on free-tier rate limits. https://www.letrelay.com/blog/incident-vs-service-request https://www.letrelay.com/blog/incident-vs-service-request Thu, 24 Sep 2026 03:01:00 GMT An incident is something broken that should work; a service request is someone asking for something standard. How to tell them apart, why they need different targets and workflows, and how to design intake so people don't have to know the difference. https://www.letrelay.com/blog/generative-engine-optimization-geo https://www.letrelay.com/blog/generative-engine-optimization-geo Thu, 24 Sep 2026 03:00:00 GMT How to get cited by AI search — Google AI Overviews, ChatGPT search, Perplexity — based on what the research and the platforms' own documentation say, not guesses. Crawlers, content, structure, and what doesn't work.