INSIGHTS
AI & Automation Insights for Operators
Practical guides on AI assistants, workflow automation, lead intelligence, and field operations. Written for business owners and operators who want results, not hype.
Automated Texts Not Delivering? Count Segments, Not Sends
Automated text messages usually fail on carrier limits that are counted in message segments per registered business, shared across every phone number, campaign, and platform under the same EIN. Buying more numbers adds no capacity, and a single non-ASCII character in an AI-written message body cuts the segment size from 160 characters to 70, tripling what one reminder consumes.
Two-way sync keeps overwriting your good data
A two-way sync overwrites good data because the sync's own write updates the last-modified timestamp it uses to decide who wins, so the receiving system looks newer on the next pass. The fix is to assign every synced field to one owning system and run two one-way syncs over field sets that do not overlap, instead of one bidirectional sync with a conflict rule.
Automated Emails Going to Spam? Check the From Domain
Automated emails usually land in spam because of the domain they were sent from, not the copy inside them. Gmail and Microsoft both apply bulk-sender authentication rules per From: domain at 5,000 messages a day, and both treat crossing that line as permanent, so a nurture sequence that shares a domain with your invoices drags the invoices into the same reputation.
Automation Running an Hour Off After Daylight Saving?
A scheduled automation drifts by an hour for two different reasons, and only one of them is a setting you can fix in five minutes. The harder failure is that a daylight saving day runs 23 or 25 hours, so a step that looks back exactly 24 hours on a fixed daily schedule double-processes an hour of records every March and skips an hour every November, with no error in the run log either time.
Why Your Automation Keeps Asking You to Reconnect
Automation connections break for four reasons, and the refresh token lifetime a vendor advertises is rarely one of them. The two that actually bite are a rotating refresh token your side failed to save, and an automation that runs too rarely to keep its token alive. Both are fixed by design choices made before the connection dies, not by clicking reconnect again.
RAG Document Permissions: Where ACL Filters Leak
In a RAG system the permission check runs at query time against a copy of the document's access list that was written into the index at ingest time, not against the source system. That copy fails in three ways a correct filter expression cannot fix: chunks that never inherited the parent document's access list, permission changes made at a parent folder or site that never re-sync, and an identity string the application supplies instead of a validated token.
Why Your AI Agent Calls the Wrong Tool
An AI agent calls the wrong tool mostly because two or more of your tools plausibly match the same request, not because you have too many tools. The published thresholds (Claude's tool selection degrades past 30 to 50 tools, OpenAI advises staying under 20) describe context dilution at scale, but the wrong-tool calls most operators hit happen at six to twelve tools and are overlap failures. The fix is an explicit do-not-use boundary in every tool description plus an escape-hatch tool for requests nothing covers.
RAG Reranking: Fix the Wrong-Chunk Problem
A reranker is a second-stage model that re-scores the passages your vector search returned, reading each one against the full query to push the truly relevant chunk to the top. It fixes precision, so reach for it when your RAG finds the right document but ranks the wrong chunk first, not when it misses the document entirely.
How to Delete Customer Data From Your AI Stack
Deleting a customer from an AI system is not one DELETE statement, because the stack has already made derived copies in a vector index, an execution log, a provider-side file store, and sometimes a fine-tuned model. Sort every copy into one of three groups by the verb it supports (delete now, expire on a schedule, or cannot be removed at all), then confirm the expiry schedules are shorter than your statutory deadline before a request ever arrives.
When to Use an AI Browser Agent Instead of an API
Use an AI browser agent when the target system has no API and the task only reads data. Anything that writes should go through an API or a person, because a browser agent finishes a run with a screenshot and a model's opinion rather than a confirmation ID, so you cannot tell a completed action from a half-finished one and cannot safely retry.
Voice AI Latency: What Fits in a One-Second Budget
An AI phone agent has roughly one second between the caller finishing and the agent needing to speak, and 400 to 800 milliseconds of that is the endpointing silence window that runs before any AI does. What is left decides which lookups and tool calls the agent can afford during a live call.
Does Your Chatbot Have to Say It's AI? 4 State Laws
In most US states there is no general law requiring a business chatbot to announce it is AI. Four states regulate it, and each uses a different trigger: Maine when a reasonable consumer could be fooled, Utah when the customer asks directly, California only when the bot is used to deceive for a sale or a vote, and Colorado from January 2027 when automated tech drives a consequential decision. A disclosure banner satisfies Maine. The other three are runtime behaviors.
Want a system like the ones we write about?
We build practical AI and automation systems for businesses that need better workflows, connected tools, and cleaner operations.
Request a Workflow Review