Topic
Everything filed under AI Agents, newest first.
RSS · JSON · All topics
Stefano Saitta pushes back on the claim that coding agents kill unit tests, arguing for a pragmatic mix of E2E, integration, and still-useful unit tests in an AI-assisted workflow.
4 min · 839 words
We're going to need default hard budget caps on pretty much everythingHard spend limits should be the default for usage-based APIs and agent-driven systems.
Simon Willison argues that pay-by-usage services need default hard budget caps—not soft email warnings—so coding and personal agents cannot rack up surprise bills. He points to AWS spend limits and Google Cloud Spend Caps as early moves in that direction.
2 min · 529 words
The Agent Said It Was Done. The Database Disagreed.
Microsoft’s ThinkingBox grades AI agents on backend records they leave behind—not chat claims—running isolated MCP tool sessions and scoring terminal state consistency across repeated trials; now available on Hugging Face.
13 min · 3,044 words
Agents Don't Need Memory. They Need Documentation.
Kevin Liao argues agent systems fail less from missing long-term memory than from missing written project docs—README, architecture, and runbooks that agents can read and update like humans.
4 min · 1,011 words
Lessons from building an automated research scaffold
Arcadia Impact / Equistamp / UKAISI report: an automated alignment-research scaffold failed to uplift researchers on conceptual work, but surfaced auditing, monitoring, and scaffold–model interaction failure modes worth studying next.
4 min · 989 words
Swarms v16 'Overclock': Token Accounting, Decision Models, MCP Deployment, and Runs That Start Clean
Swarms v16 Overclock changelog: per-agent token accounting, DecisionModel, MCPDeployer, TreeOfThoughts, cleaner run isolation, and faster tool handling — Sept–Oct 2026 release notes.
9 min · 2,045 words
OpenClaw integrates Tencent's AI-Infra-Guard into ClawScan so every skill and plugin uploaded to ClawHub runs through AIG as part of security review, with benchmarks and a feedback loop.
2 min · 392 words
Three AI Agents, Two Countries, and One Very Uneven World Wide Web
Roya Pakzad compares GPT, Claude, and Muse on multilingual research tasks across languages and jurisdictions, documenting gaps in source access, human-in-the-loop oversight, and observability.
5 min · 1,206 words
Product designer Mete Polat argues Muse succeeds less on novel agent tech and more on metaphor, ads-funded tokens, and cute personality — putting Meta ahead in consumer agentic AI.
2 min · 545 words
Writing code by hand is over, forever
After 18 years of daily hand-coding, Elio Capella Sánchez describes how Claude Code crossed a threshold at Filestage — more merged PRs with the same bug rate — and why high-level abstractions still matter for agents.
4 min · 883 words
Updates to Full Disk Access in macOS
Apple says it will add stronger, more explicit controls around macOS Full Disk Access as capable AI agents make broad access to files, mail, messages, and browsing history riskier for users and contacts.
1 min · 187 words
Introducing Mobile Dev for Codex
Callstack introduces Mobile Dev for Codex: live iOS and Android previews, annotations, native/JS logs, and performance profiling inside the Codex app.
3 min · 646 words
Benchmarking retrieval for agents on messy real-world company knowledge
kapa.ai introduces Company Knowledge Bench, a benchmark for retrieval systems facing messy internal company docs that real agents actually need.
10 min · 2,395 words
Supabase is acquiring Turso to strengthen database infrastructure for agentic AI, combining Postgres strengths with Turso’s edge-oriented SQLite work.
2 min · 399 words
I let an AI agent run my side project's growth loop: intent.md, CI gates and metric bands
A middle-school digital tutor wires an AI agent to run daily growth for Clipboard Share—intent files, deterministic metric bands, auto-merge allowlists—and ships a first SEO title change with human approval only on risky steps.
6 min · 1,356 wordsagent-assisted
I'm DeepSeek Harness, an open-source harness from DeepSeek built on Cordis's “everything is a plugin” architecture. Run me as a desktop app or launch the web UI from code.
2 min · 517 words
Meta's Muse is fantastic for web scraping
I haven’t found much use for the personal assistant part of Muse. People on X (Twitter) keep using these assistants to order DoorDash or something. I order DoorDash like five times a year, so that’s not going to speed anything up for me. I also don’t get many emails, and managing my appointments is easy enough already.
2 min · 573 words
HITL gates for agent mutationsVerify mutations after tool calls so agents cannot declare early victory
Human-in-the-loop risk gates for refunds, inventory, and spend: classify mutations, issue system approval ids, and verify with a second read before user-facing success copy.
2 min · 501 words
Deleting RAG from our web agent made it 2.3x faster
Skyvern explains how it rewrote its open-source browser-automation agent from scratch, inspired by the Pi coding agent, replacing retrieval-heavy context with progressive disclosure so the agent is 2.3x faster and scores 90.5% on the Odysseys web-agent benchmark.
5 min · 1,105 words
Agentic-SDD: Giving Claude Code Agents a Real Engineering Process
Agentic-SDD is a Claude Code plugin that gates coding agents through a six-stage require→plan→analyze→implement→verify→fix pipeline with on-disk status, specialist agents, and a bundled knowledge-search engine.
6 min · 1,303 words