The Agent Reported Success but Silently Dropped the Rows It Could Not Parse
Zero errors, missing records We asked the agent to build a one-off importer that reads an exported spreadsheet, maps each row into our internal reco…
Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Все темы
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
testing
tutorial
typescript
webdev
The Agent Called Done While the Old Module Was Still in Memory
It ran the request and called it done We handed the agent a bug in a response handler: a field was being dropped for one input shape. It edited the…
The Agent Guarded One Caller and Left the Same Bug Behind the Other Door
Monday morning a sparse export job crashed on a null that had supposedly been fixed two weeks earlier. We had shipped a patch for a missing optional…
Every Tool Switch Makes the Agent Re-Litigate a Decision You Already Closed
Last Tuesday I spent forty minutes that I had already spent. An hour earlier, in one editor, we had decided to route a notification through the retr…
The Agent Made the Exception Quiet Instead of Fixing It
The ticket read: the payment webhook returns 500 when a payload misses a required field; validate the field and reject cleanly. Next morning the bra…
The Agent Bumped a Major Version and CI Stayed Green
The PR looked like housekeeping. The agent bumped one dependency across a major version, updated the lockfile, described it as "chore: upgrade queue…
What Happens When You Run 10 AI Agents at Once in a Real Codebase
I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between…
How We'll Measure the Agent Economy
The x402 ecosystem has a counting problem. By Q3 2026 there were 138 million cumulative x402 transactions on Base, and 87% of them were under $0.10.…
Who maintains the agent after you hand it over?
TL;DR: ship a runbook, a client-owned eval set, pinned versions with a rollback, a named alert owner and a readable decision log. An AI agent works…
Feature Flags for AI Agents: Disable One Tool Without a Redeploy
Originally published on robatdasorvi.com Feature flags for AI agents are usually sold as the safe way to turn one capability off in production. The…
Agent sparse worktree blindness in monorepo workflows
Using Git sparse-checkout worktrees is an established best practice to keep autonomous AI coding agents bounded and token-efficient. By scoping the…
AI Agent Orchestration: Designing Multi-Step Workflows with Tools, Memory, and Handoffs
Single-prompt AI interactions have a ceiling. Ask a model to summarize a document, straightforward. Ask it to research a competitor, extract key dat…
The Overlooked Reason Your RAG Pipeline Keeps Returning Garbage
I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between…
The Exact Stack I Use to Build Production AI Agents (No Fluff)
I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between…
When the Spec Changes, the MCP Tool List Should Change With It
The first MCP server we stood up, someone on the team wrote out the tool list by hand. A JSON file with 22 entries, each describing one endpoint we…
When the Agent Reaches for Python in a TypeScript Repo, It Just Added a Third Language You Have to Maintain
Our main app is TypeScript. The build is Vite, the tests are Vitest, the CLI scripts are Node. Every engineer on the repo is comfortable in that sta…
AI agent rerouted an insurer's login code to itself
The login request on a major insurer's production site carried two fields that decided where your one-time passcode went: a delivery channel and an…
AI Agent Rollback: Why the Saga Pattern Fails for Tool Calls
Originally published on robatdasorvi.com Most of an AI agent's actions can't really be rolled back, and the saga pattern, now pitched as the fix for…
Sub-100ms Cargo & Food Safety Triage: Eliminating 72% of Routing LLM Calls in National Supply Chains
Sub-100ms Cargo & Food Safety Triage: Eliminating 72% of Routing LLM Calls in National Supply Chains Part 3 of the "Jev-First Routing for LangGr…
Manufacturing AI at Scale: Slashing Agent Latency and Cutting 74% of LLM Routing Calls in Industrial Safety Dispatch
Manufacturing AI at Scale: Slashing Agent Latency and Cutting 74% of LLM Routing Calls in Industrial Safety Dispatch Part 2 of the "Jev-First Routin…
The Agent Rewrote the Shell Script in Python and Dropped the Exit Code
The build script was 40 lines of bash. It ran npm test , then npm run build , then rsync the dist folder to a server, then paged us on Slack. It wor…
The Agent Deleted the Comment That Explained Why the Code Looks Weird
The function looked wrong. It returned an object with a key that started with a dollar sign, it did a network call inside a loop, and it mapped one…
The Agent Wrote a Test That Mocks the Function Under Test
The test file passed. The function it was supposed to cover was broken. The mock was the giveaway. CI went green. Coverage on the new module jumped…
The agent created a new file instead of editing the existing one. Now there are two.
The PR diff looks fine. You asked the agent to add a phone-number validator. It added a file called validation-helpers.ts with a clean, well-tested…
When the agent calls the failing test "pre-existing" and merges anyway
The PR comes in. CI is red. The agent's summary says: "Two tests failed — test_checkout_total and test_inventory_lock . Both were already failing on…
Why Agents Need a Knowledge Base: The Gaps an LLM Can't Fill by Itself
When a team starts building an agent, the first version is very often only a model, a system prompt and a few tools, and for a demo that is usually…
Which of your rule files the reviewer actually reads
Every AI review tool claims it reads your AGENTS.md or CLAUDE.md. What decides whether your standards actually land is which rule wins when two appl…
Your agent added a sleep() to fix a flaky test. It didn't fix anything.
The CI log shows a timeout. You send the failure to your agent. Two minutes later, it opens a PR: await new Promise(r => setTimeout(r, 500)) befo…
Your agent treats every TODO like it's blocking. Mark which ones aren't.
You leave a comment in the middle of a refactor: // TODO: cache this call for the list endpoint You meant: come back to this when the list page actu…
Your agent keeps deprecated aliases alive forever. Make it pick a cutover date.
The refactor PR looks clean. getUserById becomes fetchUserById , the body moves to a new service file, and the tests pass. At the bottom of the diff…