The Categorization Skill That Never Changed The Categorization Skill That Never Changed The problem An internal expense-report assistant I worked on started with exactly one job: categorize expense line items, meals, travel, software, other, against a fixed policy. It worked well, and it stayed simple because it only had to do the one thing. Then,
The Breakeven Point Nobody Was Watching For The Breakeven Point Nobody Was Watching For The problem A media company I worked with generates automatic captions and summaries for its video archive using a per-minute-billed vendor API. That decision got made once, at launch, and never revisited. I modeled the company's actual 24-month
The Box That Already Shipped - Rollback by Reversibility Type The Box That Already Shipped - Rollback by Reversibility Type The problem I built an internal IT helpdesk agent, running against the same kind of Intune and Entra ID stack we use at Improving, to provision a laptop for a new hire. Three things happen in sequence when it runs: it
The Benchmark That Never Gets a Vote The Benchmark That Never Gets a Vote The problem A team I watched needed to pick a model for a support-ticket triage agent. The job was narrow on paper: read an incoming ticket, sort it into one of eight categories, billing, bug, feature request, account access, integration, performance, security,
The Backward Rerun - Attribution for a Failure Three Weeks Late I ran a three-agent inventory-reordering chain, forecast, supplier-selection, order-placement, over a sixty-day simulated retail scenario. On day twelve, the supplier-selection agent picked a cheaper supplier with a longer lead time for a key SKU. Every node scored well at the moment it acted. The
The Auto-Send Button Nobody Had Earned Yet The problem I built a sales-proposal drafting tool with two modes. The first, suggest mode, drafts a proposal section and waits for the account executive to approve it before anything moves forward. The second, auto-send mode, drafts a proposal and sends it straight to the client with no
The Attribution Budget - Why Telemetry Never Answers Why I watched this play out on an agentic data-pipeline-repair system I built, an agent chain that diagnoses and patches seeded ETL failures, schema drift, null-handling bugs, timeout misconfigurations. I shipped genuinely complete, well-structured telemetry, one span per node, and treated that as sufficient for post-incident
The Approval That Expires - Building a Vendor Gate on Evidence The problem I built a small governance agent to answer one question employees kept asking: can I use this third-party AI vendor on a client's documents. The obvious first version checks a single allow-list, a flat table of vendor names marked approved or not approved, updated
The Approval Step I Wasn't Allowed to Collapse Yet The problem I built an onboarding workflow for new-hire access provisioning that had to survive a redesign, and I want to walk through what happened when I gave in to the obvious speed win. The existing human process was sequential: a manager signs off that a new hire needs
The Accuracy Number That Was True Once The Accuracy Number That Was True Once The problem I watched an internal knowledge-base Q&A agent launch against a RAG index built over the company's own policy documents, HR and IT material, the kind of thing employees ask about constantly. At launch, the team ran
The 503 That Kept a Chat Interface Honest The problem I gave myself two weeks to build an internal benefits assistant for a company's employees. I called it PolicyBot, because naming a pilot project is the one part of this job that never gets harder. The ask was simple: let an employee ask about PTO accrual
Ten Nodes, Forty-Five Connections, and a Throughput Drop Nobody Modeled The problem I built a five-agent content pipeline for a marketing production workflow: a research agent, a draft agent, a brand-check agent, an SEO agent, and a publish agent, each handing a piece of content to the next. Scaling that up looked like the obvious move: put a
Ten Days of Miscalibrated Sensors Before the Calendar Noticed Ten Days of Miscalibrated Sensors Before the Calendar Noticed I built a predictive-maintenance model once that scored vibration and temperature readings from forty machines to predict equipment failure seven days out. On day twenty, a firmware update recalibrated the vibration sensors, shifting the feature distribution without changing what normal
Sixty Snippets a Rule Check Could Have Caught Sixty Snippets a Rule Check Could Have Caught The problem I built a compliance review pipeline for marketing copy: two hundred snippets that need clearing before they can publish, checking for banned words, missing disclaimers, broken links, and the harder stuff that actually requires reading the copy and judging whether
Short, Bounded Pipelines - Trading a Seamless Run for a Shorter Leash on Drift The problem Ask a travel-planning agent to plan a five-day trip end to end in one uninterrupted run: interpret the traveler's preferences, search flights, search hotels, search a car rental, build a daily activity itinerary, check the result against a budget cap, reconcile schedule conflicts, and
Seventy Easy Questions Paying Premium Rates Seventy Easy Questions Paying Premium Rates The problem I ran a hundred requests through an internal help-desk triage agent, the kind of thing that answers whatever an employee types into the IT support channel. Seventy of those requests were trivial: what's the guest wifi password, how do
Seven Out of Ten Stopped Meaning What It Used To Seven Out of Ten Stopped Meaning What It Used To The problem I watched a marketing-copy pipeline auto-approve AI-generated ad copy for publication whenever an LLM judge scored it seven out of ten or higher on being on-brand and high quality. Anything under seven went to
Quality Gates at Every Transition - Stopping a Bad Value Before It Becomes the Next Step's Input The problem Take an eight-step insurance claims pipeline. OCR extraction reads the claim form. Field validation checks that the extracted values are well-formed. Policy lookup matches the claim to a record. Coverage determination decides what the policy pays for. A fraud flag screens the claim. Payout calculation sets
Order 31 and the Refund That Never Went Through Order 31 and the Refund That Never Went Through The problem I built a small order-support agent to watch a specific failure happen under controlled conditions, because I don't trust an intuition I haven't put through a project of my own. It handles a batch
One Flag Per Claim Isn't an Audit Trail - Telemetry at the Call Level One Flag Per Claim Isn't an Audit Trail - Telemetry at the Call Level The problem I built a research assistant for adjusters at a fictional insurance carrier, one I called ClaimAssist, and ran it through a short multi-step session per claim: a policy lookup, a medical-notes
One Exemplar Is Enough, and a Second One Leaks One Exemplar Is Enough, and a Second One Leaks The problem I built a receipt-digitization tool that pulls line items, name, quantity, unit price, total, out of OCR'd restaurant receipt text and into structured JSON. The prompt I started with included five few-shot examples of the
One Clause at a Time - Previewing Every Edit Before It Commits The problem I built a contract-redlining agent for legal-ops that reviewed vendor-contract clauses and proposed edits: tightening a liability cap here, adding a termination-for-convenience clause there. The first version I shipped auto-applied every proposed edit directly to the working document. There was no preview
One Bad Ticket, One Cleared Connector - Segregating Sensitivity by Chunk One Bad Ticket, One Cleared Connector - Segregating Sensitivity by Chunk The problem I built a customer-support assistant for a fictional broadband provider, one I called HelpDesk Copilot, retrieving from three different sources: a CRM export, a public product and policy handbook, and a set of support-ticket transcripts. Each
Load the Schema, Don't Paste It Load the Schema, Don't Paste It The problem A procurement automation agent I worked on extracts purchase-order documents into structured JSON against a forty-field schema, vendor info, line items, shipping terms, payment terms, all of it maintained by a data platform team as the canonical source
Every Ticket Went to the Expensive Model, Just in Case Every Ticket Went to the Expensive Model, Just in Case The problem A freight-logistics operation I worked with handles shipment exceptions: customs holds, missed connections, damaged-goods claims. An assistant drafts a resolution for a human dispatcher to approve on each one. I ran 600 tickets through it, spanning
