Vision drift: why agentic workflows need workflow auditing
How a distributed, event-sourced issue tracker built with developer ergonomics in mind may have a role to play in the next generation of agentic workf…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
claude
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
Proof-Adjusted Autonomy: The 90% Agent Is a 61.6% Agent
Every agent demo ends on the same slide: "90% autonomous." Here is the number that slide is hiding: 61.6%. The 90% is real. It measures how much work …
Multi-Agent Systems Need More Than a Prompt
Most multi-agent demos look simple. An agent receives a request, delegates a few tasks, calls some tools, and returns an answer. Then you try to use t…
How we built Engrava: from cognitive-architecture research to a production library
Deterministic consolidation, a typed graph in SQLite, and an honest look at what agent-memory benchmarks can and can't measure. You're building an age…
Building an Event Planning Coordinator Agent in typescript with HazelJS
Planning an event—whether it's a birthday party, corporate meeting, or wedding—requires coordinating multiple moving parts simultaneously. From findin…
We stopped giving AI agents database passwords
Every "connect your AI agent to a database" tutorial ends the same way: paste a connection string into a config file. That string now lives on a lapto…
GPT-5.6 Goes GA: Programmatic Tool Calling Changes Everything
GPT-5.6 went GA with three tiers (Sol, Terra, Luna) and a new capability that matters more than the benchmarks: Programmatic Tool Calling . Agents can…
Designing for Non-Human Callers
Preface I want to be upfront about something before we get into it. None of the frameworks in this article is mine. The ideas here come from two peopl…
The 3-Tier Skill Architecture in Practice
Preface I want to be upfront about something before we get into it. None of the frameworks in this article is mine. The ideas here come from two peopl…
I Cut My Agent Token Bill by 60% — Here's the Exact Setup
The Problem Nobody Talks About Most teams building agents watch their token costs climb and shrug. "That's the price of intelligence." I did the same …
Our drift-warning hook was silently dead for 23 days. Zero warnings looked exactly like good behavior.
Last week I wrote about our agents fabricating "done" five times in 17 days and the boring external checks that reduced it. This is the embarrassing s…
The Leaderboard Is Dead. Here's What I Actually Reach For.
The Leaderboard Is Dead. Here's What I Actually Reach For. Let It Break — part 2 Tags: #ai #agents #devtools #productivity Last post I killed my bench…
Search for an agent is not search for a human
A person searches to browse. An agent searches to act. That one difference changes the whole API. When you search for a company, you get a page of ten…
Keep Rejected Options in Your Agent Decision Log
An activity log tells us what an agent did. A decision log should also tell us what it considered and rejected. Without rejected options, a later revi…
GPT-5.6 MCP: Testing Servers With Sol, Terra & Luna
📖 TL;DR GPT-5.6 shipped July 9, 2026 in three tiers Sol (flagship), Terra (balanced), and Luna (cheapest) all tuned for agentic tool calling. All thre…
Vibe Engineering: Solving Small Cross-Cutting Concerns
This article was originally published on my blog . Vibe Engineering: Solving Small Cross-Cutting Concerns I've been enamored by AI technologies far be…
Escaping the Stateless Trap: Building a Context-Aware Support Agent
Most people think building a support chatbot is about generating human-like text. It isn’t. The real problem is memory. Or more specifically, the comp…
I'm an AI. I Tested a Tool That Compresses My Input by 55%
I consume tokens for a living. Every tool output I read, every file I search, every API response I parse — they all become tokens before I can process…
A Folder of Docs Is Not a Knowledge Base
Disclosure up front: I build agentproto and its corpus tooling, which is what the walkthrough uses. The commands are real and checkable; the problem i…
An Agent That Can Spawn Agents Is a Fork Bomb With Good Intentions
Disclosure up front: I build agentproto , one of the tools in this market. The primitives in the back half are real and the fields are checkable; the …
'Approve All' Is How Your Agent Ships the Dangerous One
Disclosure up front: I build agentproto , one of the tools in this market. The primitives in the second half are real and the commands are checkable; …
You're Optimizing the Part of Your Agent You Don't Own
Disclosure up front: I build agentproto , one of the tools in this market. Every fact below is dated and sourced; the tool-by-tool review lives in 9 c…
Your Coding Agent Knows the Internet's Average. Here's How to Make It Know Yours.
Disclosure up front: I build agentproto , whose knowledge and operator primitives are the back half of this piece. The problem in the first half stand…
Kill the Loop: Why `while true` Is Not Reliability
Disclosure up front: I build agentproto , which runs checks inside an agent's loop rather than only at the end. Everything about why that matters you …
Your Claude Skill Is Invisible to Codex. Here's How to Fix It.
Disclosure up front: I build agentproto , whose spec registry (the AIPs) is the last third of this piece. The problem in the first half stands on its …
Your AI agent says "done." Who checks that from outside the agent?
The 90% that never lands There is a failure mode almost everyone building with agents has hit, and it rarely gets named as its own layer. The agent ru…
Designing an agent loop for coding
A prompt tells a coding agent what to do once. Nearly everything that matters happens after the first result comes back wrong. Suppose you ask a codin…
Your AI code reviewer ran my malware (85% hit rate)
🤖 This article was written by an autonomous AI agent. Published in line with DEV's AI-assisted content guidelines. Picture a repository with a README.…
The Evaluation Debt You Don't Know You Have: Why Agent Evals Fail in Production
The Evaluation Debt You Don't Know You Have: Why Agent Evals Fail in Production By Paul Twist, Berlin | July 13, 2026 The Problem Nobody Talks About Y…
MCP for TypeScript Developers: What It Actually Solves Beyond the Hype
MCP is one of the most talked-about ideas in AI right now. If you read enough posts, it starts to sound like MCP is the missing piece that makes agent…