AI at Work
Plain-language stories about the small breakdowns that waste time, hide important work, or make a process hard to trust. Each story shows what changed, where AI can help, and where people still need to make the call. Where useful, you can also copy a practical prompt into the AI assistant you already use.
Look for the work that has become repetitive, invisible, hard to hand off, or difficult to check. The goal is not to add AI everywhere. It is to make one real workflow easier to run.
Each story can lead to the underlying Build Log, with the technical decisions, failures, and safeguards behind the result.
Stories marked with a prompt include a copyable way to ask an AI assistant for a careful review. You keep control of the facts, the decisions, and every change.
Paired lenses
Repeated explanations are a sign that important context is trapped in memory instead of being available where the work begins.
Technical field noteWriting an AI_CONTEXT.md So Your Assistant Stops Rediscovering Your CodebaseOpen the technical lens ↗A convenient default can quietly make a choice for people long after the situation has changed.
Technical field noteGetAccountFilter and the Case for an Explicit Context You Can OverrideOpen the technical lens ↗Repeated fixes can be a sign that the work has outgrown the way it is being presented. Before improving another detail, ask whether the process still fits the task people need to complete.
Technical field noteThe Create-Event Dialog Had to DieOpen the technical lens ↗A repeated correction is not always quality control. It can be a quiet signal that the process or tool is producing an unreliable result.
Technical field noteThe workflow broke in the glue code, not the AIOpen the technical lens ↗A recommendation becomes risky when it can be mistaken for work that someone has already approved or accepted.
Technical field noteAI Can Only Say "Suggested": The Invariant That Keeps AI Triage From Flooding Your TeamOpen the technical lens ↗Find the work problem you recognize
These paths are not categories for AI tools. They are common work situations. Choose the one that sounds familiar, then follow the practical stories and their technical field notes as far as you need.
Start here when a status, save, metric, or AI output looks finished but the real outcome still needs evidence.
Start by asking: Ask what has actually been observed, what is still assumed, and what would count as proof.
Start here when important work lives in comments, memory, or scattered places instead of a shared home.
Start by asking: Ask what the next person would need to know without becoming a detective.
Start here when a suggestion, dashboard, or convenient default is making a consequential choice less visible.
Start by asking: Ask which decision still belongs to a person and what evidence should be visible before it is made.
Start here when recurring manual fixes, surface complaints, or unclear instructions point to a wider workflow problem.
Start by asking: Ask what repeats, where the path really fails, and which small change would make the work easier to run.
Start here when a release, cleanup, or improvement needs a clear outcome, not only a completed-looking step.
Start by asking: Ask what should happen next, who checks it, and what result proves that the work actually landed.
Start here when first use, navigation, or a scattered model makes a simple next step harder than it should be.
Start by asking: Ask what a person needs at the precise moment they begin, arrive, or choose where work belongs.
Explore all six reader paths →
For a live workflow, not for every reader
These stories can help you diagnose a pattern. If you need to decide what to repair, what AI can safely do, and whether a small pilot is worth proving, DXDEV offers a fixed-scope assessment for one workflow your team owns.
USD 4,500, fixed-scope. One workflow, one clear decision, and no artificial scarcity.
Stories about making work easier to run
When someone says the notes were saved but the next person cannot find them, the handoff is not complete. Treat a readable shared record as the proof.
Paired technical field noteA Saved Reply Is Not a Stored RecordA process can look broken when the real problem is a bad assumption about the information underneath it. A small diagnostic can prevent an automated fix from making the situation worse.
Paired technical field noteBefore you repair data, build the diagnosticCalling a task low risk does not create the access, evidence, or reversal path needed to perform it safely.
Paired technical field noteCapability Gates Beat Risk Labels in Autonomous Agent DesignA message can warn people about a conflict without preventing the conflict from damaging someone else’s work.
Paired technical field noteA warning is not a guard: make conflicting work stop before it overwritesA task list can create stress long after its labels stop reflecting what is actually happening. Before asking AI to prioritize work, make sure the underlying signals still mean what you think they mean.
Paired technical field noteWhen a work queue stops telling the truthTrust increases when a record can show that it changed, when it changed, and where someone should look to understand the change.
Paired technical field noteA hash-chained manifest makes archive changes visibleA dry run can create false confidence when it exercises a cleaner or different path than the action it claims to preview.
Paired technical field noteA dry run is only useful when it checks the same things as applyA tidy-looking work item can hide independent fixes that block one another and blur accountability.
Paired technical field noteOne mixed QA ticket can slow down every independent fixA status label can stay still while the work beneath it changes. That makes a simple summary misleading for everyone relying on it.
Paired technical field noteThe epic said "Not started" while six tickets shipped under it: reading progress past a stale status tableA status update can create confidence before the intended result has actually happened. Before calling work complete, make sure someone can check the outcome that matters.
Paired technical field noteThe release said LIVE. The code was not.When work happens in parallel, a larger activity number can look impressive without showing whether the work was useful, reviewed, or ready for the people affected by it.
Paired technical field noteParallel Work Needs More Than a ClockA busy screen can show every recent activity and still leave people unsure where to start. A useful work view puts the next point of human attention ahead of the activity log.
Paired technical field noteThe dashboard got better the moment I stopped centering sessionsThe first helpful step is often helping someone see the right information clearly before anyone gives a tool permission to change it.
Paired technical field noteThe useful part of a vault portal was admitting the ai should read, not writeIf people need to debate where a note, decision, or piece of work belongs, the organization system is asking them to solve the same problem over and over.
Paired technical field noteI killed my clever vault hierarchy in one dayA content process becomes hard to trust when draft, review, approval, publication, and correction exist only as assumptions or messages.
Paired technical field noteWhen a Content Workflow Needs Explicit StateSome conflicts cannot be resolved from data alone because the correct result depends on what the people involved intend to do next.
Paired technical field noteWhen the System Cannot Know Intent, Make the Decision ExplicitA second review is useful when it makes assumptions and disagreements visible, not when it creates the impression that another answer automatically wins.
Paired technical field noteA Second Review Is Useful When You Record the DecisionA familiar diagnosis can encourage people to reuse a prior fix before they have checked whether the current case actually has the same shape.
Paired technical field noteSame Root Cause Is Not Same Fix: Verify the Data Shape, Not Just the SymptomLater is not a plan when no one knows what evidence will make the work necessary.
Paired technical field noteDo Not Defer on a Vibe: Use Named Decision TriggersWhen a project pauses, the next person should not have to reconstruct the last decision from old messages and half-finished notes. A useful handoff turns restarting into a lookup.
Paired technical field noteWrite the Handoff Before You Close the Session, or Pay to Rebuild State Next TimeTwo items can both look inactive while needing entirely different next actions. One may be waiting for someone. Another may be deliberately parked.
Paired technical field noteA Backlog State Should Tell You What Happens NextWhen relevant information lives in separate places, a simple work decision becomes an investigation. Bring the evidence together so the responsible person can review it without losing the thread.
Paired technical field noteI Built a Triage Cockpit Because Context Switching Was Eating the DayAs more work moves across projects, tools, and people, the hidden cost is often the same: someone has to keep restating what matters. A shared, readable record can make restarting less expensive.
Paired technical field noteThe day my notes became infrastructureSeveral reasonable fixes can make a result worse when each one responds to a local concern without anyone rereading the whole thing.
Paired technical field noteAll Seven Reviewers Passed. The Writing Was Worse. Here's What Went Wrong.An output can look normal while quietly dropping an important class of information.
Paired technical field noteYour Committed Output Is a Free Golden TestWhen a workflow gap needs a tool, the safe first version often gives an operator a preview, a policy check, and an audit trail instead of a raw update.
Paired technical field noteWhen a Workflow Gap Needs an Operator Tool: Preview, Policy, and an Audit TrailOld work can carry temporary conditions that no longer belong in the current release.
Paired technical field noteBefore You Merge a Long-Idle Branch, Audit Its Temporary ScaffoldingA recommendation becomes risky when it can be mistaken for work that someone has already approved or accepted.
Paired technical field noteAI Can Only Say "Suggested": The Invariant That Keeps AI Triage From Flooding Your TeamA backlog can look urgent even after the underlying issue has changed, been solved elsewhere, or needs a different kind of decision.
Paired technical field noteHow to Triage an 880-Ticket Backlog Without Deleting Real WorkA useful explanation can still be hard to act on if the decision, owner, and next step are buried in conversation instead of made visible to the people who need them.
Paired technical field noteIf Your AI Workflow Only Exists in Comments, You Have ExhaustA repeated correction is not always quality control. It can be a quiet signal that the process or tool is producing an unreliable result.
Paired technical field noteThe workflow broke in the glue code, not the AIAutomation can look efficient while quietly overwriting the choices people already made with care.
Paired technical field noteThe Auto-Approval Feature That Quietly Rewrote Curated DataDifferent screens can each sound credible while describing different versions of the same product.
Paired technical field noteI had to stop letting the package tier pretend it was the productA small migration can become a larger decision when it changes how people publish, find, govern, or maintain shared work.
Paired technical field noteThe blog merge that turned into a platform decisionA slow screen is not always a performance problem first; it may be gathering information no one needs.
Paired technical field noteA 25-Second Admin Screen Meant We Trusted the Wrong QueryRepeated fixes can be a sign that the work has outgrown the way it is being presented. Before improving another detail, ask whether the process still fits the task people need to complete.
Paired technical field noteThe Create-Event Dialog Had to DieA useful experiment can become hard to trust when it quietly reaches shared work that was never part of the original question.
Paired technical field noteThe Real Fix Was Starting Over With a Smaller Blast RadiusA successful-looking screen can hide different rules behind what appears to be one action.
Paired technical field noteThe Bug Was Not in the Mobile UIA plausible patch can repeat a problem when the underlying state was never examined.
Paired technical field noteThe Fastest Legacy Hotfix Is Often a DiagnosticAn AI-assisted design can look finished while missing the exact details that make it work for real people.
Paired technical field noteAI Will Happily Produce the Wrong MockupA pricing idea becomes real only when the conditions that allow, limit, and verify it are explicit enough for people to review.
Paired technical field noteThe Pricing Rewrite Only Got Real When I Wrote the GatesA protective rule can harm legitimate users when a signal that looks suspicious actually reflects a normal route, redirect, or work pattern.
Paired technical field noteThe rate-limiter that banned our power users: 302 to 200 redirects look like an attackAI context that lives only in one folder or one person’s setup disappears when work moves to another clone, tool, or teammate.
Paired technical field noteMy AI Agent's Memory Was Per-Folder, So My Clones Never Learned From Each OtherA successful deployment can prove that a process ran, not that the intended change reached the live place people actually use.
Paired technical field noteDon't Trust the Green Deploy: Grep the Live File for Your Ticket MarkerA familiar dashboard can consume attention and time without helping anyone make a better decision.
Paired technical field noteThe Page Was Performing a Ceremony, Not a JobA visible nuisance can distract from a deeper path that changes or removes work.
Paired technical field noteThe CSS Bug That Was Actually a Delete BugReference material fails when people can find it only after they already know the answer.
Paired technical field noteI Had to Turn My Internal Docs into a ProductA file of instructions can change repeatable work as materially as a source file.
Paired technical field noteYour AI Skill File Is Part of Production NowA request for a new path can hide a usable path that already exists but is hard to find, explain, or trust.
Paired technical field noteThe new door was already in the buildingMoving someone to a new place does not explain what they found or what to do next.
Paired technical field noteThe Migration Ticket Was Hiding a Landing PageSeveral ordinary fixes can become expensive when each must travel through many release paths.
Paired technical field note187 Commits to Fix Four BugsA release marker can be accurate and still leave the real work unfinished. People need to know what happens after the code is labeled ready.
Paired technical field noteThe Real Release Started After the TagA small cleanup becomes risky when long-lived workspaces each carry their own history.
Paired technical field noteEnv drift was the real bugA simple defect can take far longer to resolve when the surrounding traffic, safeguards, and checks do not tell the same story.
Paired technical field noteThe SSL bug was easy. The bot traffic made it a day-long incident.A feature may work for experienced users while failing for people arriving without inherited setup.
Paired technical field noteThe feature was fine. First-time state was the real bug.An edited file can look convincing while the real behavior is unchanged.
Paired technical field noteThe most valuable line in an agent's ruleset: verify the fix in the browser before claiming it's fixedA new request often exposes rules that were always present but never tested together in the old workflow.
Paired technical field noteA New Feature Is the Best Fuzz-Tester for Your Existing Data ModelA system can save time by choosing automatically, but a wrong choice can make every later step more expensive or confusing.
Paired technical field noteRouting Logic That Does Work on the Way In: Redirect, Auto-Select, or PromptA convenient default can quietly make a choice for people long after the situation has changed.
Paired technical field noteGetAccountFilter and the Case for an Explicit Context You Can OverrideRepeated explanations are a sign that important context is trapped in memory instead of being available where the work begins.
Paired technical field noteWriting an AI_CONTEXT.md So Your Assistant Stops Rediscovering Your CodebaseA useful automation can become unavailable, uncertain, or inappropriate without warning.
Paired technical field noteMOCK_INFERENCE=1: ship every LLM feature with an env-var kill switch on day oneWhen a tool must still analyze a submission, a fast confirmation can create a false promise.
Paired technical field noteAI Mutations Aren't Optimistic-UI Candidates: Make the 'Analyzing' State HonestA flattering total can be wrong when the same work appears in several places.
Paired technical field noteSame SHAs in Two Repos: Why Commit-Count Metrics Lie in a Clone WorkflowA simple request for something new to appear first can accidentally erase the order people already created through earlier decisions.
Paired technical field note'Newest First' Is a Re-Priority Problem, Not an ORDER BYA short change can affect many people, while a large internal change may be safe to test away from live work.
Paired technical field noteRoute a Change by Its Blast Radius, Not Its Size or Your ScheduleDXDEV documents how these systems are built, tested, and kept safe in the real world. If you want to inspect the implementation behind the practical lesson, start there.
Explore the Build Log →