🔥 TOP SIGNAL

Test suites + harnesses are becoming the real “interface” for deep agents: Cloudflare used an AI agent (Paramigen) plus Next.js tests to recreate a Next.js-compatible framework in a week ThePrimeTime, while LangChain says deep agents require multi-layer evals (single-step → full-turn → multi-turn) in clean, reproducible environments @LangChain. Geoffrey Huntley’s framing clicks: the model is the “reasoning engine,” but the agent harness is the control plane that makes behavior safe and repeatable in production @GeoffreyHuntley.

🛠️ TOOLS & MODELS

• “Too-hard-for-LLM” coding tasks are drying up (gpt-5.3-codex vs opus 4.6): Theo is offering $500/problem for locally verifiable repos that current top models can’t solve, but says almost every verifiable problem sent so far gets solved by 5.3 Codex first try @theo +1. If you’re sharing benchmarks, he wants a git clone-from-scratch command sequence to reproduce the exact state @theo.

• Codex vs Claude (practitioner comparison): Peter Steinberger’s take: Codex “will read much more of your code and usually find a better solution,” while Claude is “more pleasant” but may claim it’s “100% production ready” and then bug out Manuel Corpas.

• Augment’s codebase indexing → better retrieval inside Codex: Theo demos using Augment’s CLI to index a codebase, then switching to Codex where the model immediately uses Augment’s retrieval tool; he claims it finds “exactly what you need and almost nothing else” and returns results in <20 seconds vs 5–10 minutes previously Theo - t3․gg.

• Remote control, minus lock-in: Claude Code’s new “Remote Control” is described as Max/Pro-only and Claude-Code-only in Jason Zhou’s thread; his alternative is Tailscale + SSH for a private network workflow: “Phone terminal → SSH → dev machine,” with “no public IP / no port forwarding / no exposed services” @hqmank +1.

• Cursor cloud agent: desktop Windows VM from a single prompt: Jediah Katz says he got a Cursor cloud agent to run a Windows VM with full desktop display support “with just one prompt,” taking ~1.5 hours on a long-running harness, and then he can snapshot it as a reusable Windows base @jediahkatz +1.

💡 WORKFLOWS & TRICKS

• Deep-agent evaluation stack (LangChain’s production learnings)@LangChain

  • Write bespoke success criteria per datapoint (not one generic rubric) @LangChain.
  • Run single-step evals to catch regressions at specific decision points @LangChain.
  • Add full-turn evals to validate end-to-end behavior @LangChain.
  • Add multi-turn evals that simulate realistic user interactions @LangChain.
  • Keep clean, reproducible test environments so runs are comparable @LangChain.

• Treat your harness as the product (Huntley’s definition you can operationalize)

  • The “agent harness” is the orchestration layer that manages prompts, tool execution, policy checks, guardrails, and loop control (continue/stop) @GeoffreyHuntley.
  • Handy reference: https://latentpatterns.com/glossary/agent-harness@GeoffreyHuntley.

• Narrow-agent teams beat “mega agents” (Riley Brown’s OpenClaw pattern)

  • He reports that as he added more skills, agent dependability dropped: skill use timing got worse, context got “clouded,” and integrations/personalities got “jumbled” Riley Brown.
  • His proposed sweet spot: teams of narrow agents with ~7–10 skills each (vs ~30+) Riley Brown.
  • Concrete coordination pattern: a journal agent in Telegram pings him ~every 30 minutes (sometimes skipping if nothing’s needed), logs useful context into Notion, and other agents read that shared journal (e.g., newsletter agent drafting for a 300,000-person email list with its own conversion goals) Riley Brown.
  • Autonomy lever: narrow agents can run predictable cron-job loops (“three tasks every day”) because they’re optimizing for a small set of goals Riley Brown.

• Agentic engineering tactics you can copy (Peter Steinberger)

  • Treat it like a discussion, not a one-liner; guide it explicitly (“look here, look there”) and assume it starts with zero project context Manuel Corpas.
  • Ask it to propose refactors/pain points when a change touches many parts of a codebase Manuel Corpas.
  • After shipping a feature, ask: “Now that you built it, what would you do different?” to surface what it learned during implementation Manuel Corpas.
  • Speed tricks: provide images as context when that’s faster than writing; use voice input for throughput Manuel Corpas.

• Codebase hygiene under agent acceleration (Theo’s rules of thumb)

  • “Tolerate nothing”: if a bad pattern makes it in, it multiplies—so delete it aggressively Theo - t3․gg.
  • Spend more time in “plan mode”: go back-and-forth until you have a markdown plan you can review, then tell the model to build Theo - t3․gg.
  • When an agent goes wrong, interrogate the path: ask what it’s doing and why, then eliminate bad examples if they’re coming from your own codebase/docs Theo - t3․gg.

• One-prompt infra bootstrap: Windows VM inside an agent box (Cursor cloud agent)

  1. Give a prompt that explicitly asks for a full Windows VM with desktop display support (not just CLI) @jediahkatz.
  2. Let it run under a long-running harness (reported ~1.5 hours) @jediahkatz.
  3. Snapshot the resulting VM as a reusable “Windows base” @jediahkatz.

👤 PEOPLE TO WATCH

• Jediah Katz — practical proof of long-horizon agent setup work: a full desktop Windows VM inside a cloud agent, plus snapshotting for reuse @jediahkatz +1.
• Theo (t3.gg) — running public, verifiable “too hard for LLM” challenges and documenting what actually breaks modern coding models (increasingly little) @theo +1.
• Peter Steinberger (OpenClaw) — high-signal “agentic engineering” habits + grounded tool comparison based on daily use Manuel Corpas.
• Riley Brown (vibecodeapp) — concrete multi-agent “team” design: narrow agents, shared memory via Notion, cron-based loops Riley Brown.
• LangChain team — pragmatic eval guidance from building/testing 4 production agents@LangChain.

🎬 WATCH & LISTEN

1) Riley Brown — why “too many skills” makes agents worse (≈02:33–05:42)

He explains the failure mode (context clouding + jumbled integrations) and the practical alternative: 7–10 skills per agent, then build a team Riley Brown.

2) Peter Steinberger — OpenClaw project update + why he resists one-click installs (≈08:03–12:04)

He describes working to add maintainers and set up a foundation for donations/hiring, and argues that making installs too easy can hide real risks (he calls out prompt injection as unsolved) Manuel Corpas.

3) Theo — codebase inertia + “slop” compounding under agent acceleration (≈18:17–20:02)

A concrete mental model: codebase quality peaks early, bad patterns spread faster than good ones, and “the models accelerate this” Theo - t3․gg.

📊 PROJECTS & REPOS

• LangChain: “Evaluating deep agents — our learnings” (built + tested 4 production agents) — https://www.blog.langchain.com/evaluating-deep-agents-our-learnings/@LangChain +1
• Agent harness glossary (Latent Patterns) — crisp definition of the orchestration layer that constructs context, executes tool calls, enforces guardrails, and controls loop continuation — https://latentpatterns.com/glossary/agent-harness@GeoffreyHuntley
• Cloudflare’s ViNext (Next.js recreation via Paramigen + tests): reported one-week build, 1700 Vitest + 380 Playwright E2E tests, and partial test coverage breakdown (13% dev / 20% E2E / 10% production out of 13,708 cases) ThePrimeTime.

Editorial take: The leverage is shifting from “better prompts” to better harnesses + better tests—they’re what make agents reliable, repeatable, and (increasingly) portable across codebases @GeoffreyHuntley +1.