i_m_@nkan @AnkanMatrix

INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 1 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a new skill. Watch it and Bookmark it now

Swati Gupta @hrswatigupta

a month ago

x.com/i/article/2060…

14 178 778 2.8M 3K

Terraform best practices for AI coding agents github.com/antonbabenko/t…

This is an official ANTHROPIC 33-page PDF blueprint for building "Effective AI Agents." Not theory. Architecture patterns with real case studies from Claude, Coinbase, Stripe, Intercom, and others. Perceive → Decide → Act → Evaluate → Repeat Five patterns, from simple to complex: • Single agent: one model in a loop. Handles 80% of use cases. Don't over-engineer. • Sequential workflow: fixed steps, each agent hands off to the next. Predictable and auditable. • Parallel workflow: fan out tasks across agents at once, merge results. Speed through concurrency. • Hierarchical: a supervisor delegates to specialists. Like a team lead managing experts. • Evaluator-optimizer: one agent generates, another pushes back. 2-4 cycles until quality is met. The key insight: multi-agent systems outperform single agents by 90.2% on complex tasks. Match complexity to value. Read it now, then explore the article on agentic "Loop engineering" below.

Codez @0xCodez

3 weeks ago

x.com/i/article/2064…

121 1K 6K 7.5M 21K

A senior Anthropic engineer just dropped 11-page PDF on "Loop Engineering" for agentic systems. The shift: you stop prompting the agent. You build the system that prompts it instead. Schedule → Discover → Build → Verify → Repeat Every loop runs one turn, five moves: • Discovery: it finds its own work - failing CI, open issues, recent commits - instead of being handed a list. • Handoff: each task gets an isolated git worktree so parallel agents don't collide. • Verification: a second agent, told to assume the code is broken, reviews the first. The "thing that can say no." • Persistence: results get written to disk, never left in a context window that gets flushed. • Scheduling: an automation wakes it on a timer. That's what makes it a loop. The key insight: an agent grading its own work always praises it. This 11-page PDF changed how I'm building agentic systems today. Read it now, then explore the article below.

Codez @0xCodez

3 weeks ago

x.com/i/article/2064…

121 1K 6K 7.5M 21K

Head of Canva AI at Claude: "90% of our engineers use Claude’s subagent harness to build the world’s #1 design tool. we use a subagent harness every day - a main Sonnet agent that delegates tasks to Opus or Haiku." in a 30-minute speech, the Head of Canva AI explains how they built an agentic harness from scratch. Worth more than 100 YouTube videos on building agents.

Codez @0xCodez

2 weeks ago

x.com/i/article/2066…

27 116 765 207K 1K

how to build an agent that maps out competitor products and improves your own this would probably be the agent workflow I'd create if I joined this hackathon 1. from the outside you only see their landing page and pricing. the rest is hidden, the onboarding, the emails, where the paywall hits, the upsell, you dont see any of it until you pay 2. so doing this by hand is slow. you sign up, pay, click through the onboarding, hit the paywall, see the upsell. do that for five competitors and its a week of work nobody has time for 3. an agent that can pay fixes that. it signs up, pays, and goes through the whole thing itself, on its own time, while you do other work 4. it writes down every step as it goes, the onboarding screens, each email when it lands, where the paywall hits, the upsell, and the order it all happens in 5. then it does the same for as many competitors as you want, so you get them side by side, how each one takes someone from free to paid 6. you end up with a clear writeup of each funnel, what they do to convert, where they push, what to copy and what to skip, saved to your brain 7. last step, it points it at your own funnel. it lines you up next to every competitor and shows where you lose people they keep, so you fix your onboarding and emails off what you saw, not a guess AI make the things that didn´t make sense due to negative roi of time positive.

Shann³ @shannholmberg

2 weeks ago

nvidia, stripe and nous teamed up on a hackathon for agents that can earn, spend, and run operations here are 4 I'd like people to build for marketing: > a media-buying agent for unconventional placements, the experimental stuff outside the mainstream platforms. newsletter

13 1 41 21K 38

Anthropic pays $750,000+ a year for engineers who can build LLM architectures from scratch. Stanford taught the entire thing in 1 hour lecture & released it for free. Bookmark & watch this today before someone takes it down and read this article below

Swati Gupta @hrswatigupta

a month ago

x.com/i/article/2060…

14 178 778 2.8M 3K

build your revenue-generating ai systems first here are 10 agents I would build before any content or ops agent, each one wired into the same company brain and CRM: > instant sales call feedback. the rep hangs up and an agent has already pulled the transcript, scored the call against your framework, and sent back what they missed, which objection they fumbled, and the line to use next time. reps get better between calls instead of in a quarterly review > proposal generator. pulls the call transcript, scrapes the prospects site and context, layers in your sales managers notes and the closest past wins, and drafts the proposal in your format. the rep edits instead of starting from a blank page, and it goes out same day instead of three days later > inbound lead qualification. a lead comes in, the agent enriches it, scores fit, and replies in minutes. if they qualify it either gives them real value straight away or drops a direct link to book a meeting, so you never lose a hot lead to a slow inbox > CRM agent. has company-wide context and keeps the pipeline clean, enriches every record, surfaces insights, and nudges reps when a deal goes stale or a step gets skipped. it keeps the whole sales team consistent instead of each rep running their own system in their head > automated follow-ups. every lead that goes quiet gets a full sequence, not one "just checking in." the agent writes each touch off the actual context of the deal, so the follow-up adds something instead of nagging > contract generator. takes the agreed terms off the deal, drafts the contract in your template, flags anything off-standard, and routes it for signature. cuts the gap between verbal yes and signed from days to minutes > upsell agent. watches your company brain and CRM for the moment a client is ready for more, hit a usage cap, mentioned a new goal on a call, growing fast, and hands the account owner the opening with the context to act on it > churn fire-fighting agent. a head of accounts that spots a client going cold before they tell you, slow replies, dropped meetings, a short reply that used to be warm, and loops in the team to save it while theres still time, not after the cancel email lands > lead reactivation agent. goes back through lost and ghosted deals, enriches each one with whats changed since, builds a plan to reopen it, then executes. your dead pipeline becomes a list the agent works on its own > invoice payment follow-ups. an agent owns the dates, knows when each client should pay, and starts the follow-up the moment its late, so you stop financing clients for free and cash lands faster with nobody chasing it by hand

How to build your first AI agent (Full guide)

Rahul @sairahul1

3 weeks ago

x.com/i/article/2064…

30 96 468 725K 1K

A Google Cloud engineer just showed how to build a full app with Claude from scratch he spent 26 minutes live on stage doing what most teams take weeks to do worth more than any $500 vibe-coding course here's what he covers: > zero to deployed app in a single session > handling five engineering roles alone with Claude > the exact workflow Google uses internally > no team, no setup, just Claude and a goal the people who figure out what Claude can actually do are building things everyone else thinks requires a team that's exactly why I wrote a step by step guide on how to build your first AI agent the guide is in the article below

Anatoli Kopadze @AnatoliKopadze

3 weeks ago

x.com/i/article/2062…

27 107 676 2.3M 2K

what is agent looping for the last two years we prompted agents one task at a time. that is starting to change instead of asking an agent to build the landing page and then driving every step yourself, you set up a loop that handles discovery, planning, the work, checking, and iterating until the goal is met looping is a setup you build. almost any agent harness can run it, it just depends on how you wire it up at its simplest, looping is one agent working on itself: > researches > drafts > checks the draft against a goal > fixes what is weak > runs that cycle again until the work clears the requirements you are not prompting each step anymore. the agent repeats the cycle for you the bigger version is a fleet looping. you give an orchestrator agent a goal, it breaks the goal into pieces, hands each piece to a specialist agent, and those specialists hand smaller jobs to their own subagents the whole tree keeps looping through discovery, planning, execution, and verification until the goal is met one agent looping is like a person redoing their own draft. a fleet looping is a whole team running a project end-to-end you create a goal, and the system runs the loop until it finishes within the reqs you set open and closed looping: OPEN LOOPING is exploratory. it still has conditions and a goal, but you give the agent or the fleet a wide space to move in. it can try different paths, discover things, build something you did not fully spec out this is the exciting end, it is what Peter and others are doing, and tbh it is where I want to spend more time the catch is cost, an open loop with real room to explore burns an insane amount of tokens. for the 90 percent of people without an unlimited budget it is not runnable yet, and pointed at projects with a loose standard it turns into a slop machine CLOSED LOOPING is bounded. a human designs the end-to-end path first: > clear goal > defined steps > an eval at each step > a point where it stops or hands back to you (and feeds back performance data) the agents still loop, but inside framework you built. it gets better every run because each pass feeds the next, and it runs on a normal budget because the path is tight. for most marketing work, closed is the one that pays off today. > the orchestrator owns the goal > the specialists own the steps > the subagents do the narrow work > an eval gate make sure its not slop

Peter Steinberger 🦞 @steipete

3 weeks ago

Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.

2K 1K 20K 8.4M 14K

Is this a bug in AVD or just poor integration between it and the VM layer because I see this a lot where it still thinks there are (active!) sessions despite the VMs being shutdown (not hibernated - it's not enabled) so without reincarnation mode (I made that up!) reconnection is impossible. The problem is it causes problems when the "connected" user tries to get a session

how I’m building an agent company inside my agency. the structure looks like this: Agency gBrain → Orchestrator Hermes Agent → Department verticals → Specialist agents → Scoped sub-agents gBrain is the company brain. It gets ingested with the data and experience we already have: > transcripts > chats > previous campaigns > client learnings > strategy docs > internal workflows > examples of what good looks like That brain is maintained by a human champion plus an orchestrator Hermes Agent. Under the orchestrator, we have different department verticals inside the agency. Each vertical has its own specialist agents. Some of those specialist agents have even narrower scoped agents underneath them. I’ve found that narrow scope improves output quality and reduces drift. > a general “marketing agent” is too vague. > a lifecycle email agent with access to the right campaigns, voice rules, approval gates, and examples can get very good. > a technical SEO agent with its own tools, checklists, and source standards can get very good. > a content research agent with narrow inputs and a clear definition of done can get very good. The narrower the job, the easier it is to improve the agent. I use different harnesses for this. Mostly Hermes Agent, but also CLI harnesses like Codex and Claude Code depending on the job. I’m still looking for a good bare-bones harness for model routers to run on. To keep track, I maintain an org chart inside the company gBrain. The org chart shows: > top-level orchestrator > department verticals > specialist agents > scoped sub-agents > which brain each agent reads from > which tools each agent is allowed to use > where human approval is required For clients, I do downstream pods. Think of them as new agent companies that are isolated from the agency brain, but can still communicate with our agency agents when needed. A client pod has its own: > client gBrain > client orchestrator > client specialist agents > client-specific workflows > client-specific approvals > client-specific memory This is important. You do not want client context bleeding across accounts. You do not want one agent with every client’s data, every tool, and every permission. Scope is what keeps the system useful. The powerful part is that once you build one vertical agent well, you can fork it. Not copy-paste blindly. You still need to customize the context, examples, approvals, voice, tools, and workflows. But you are not starting from zero. You might have 75% of the agent already done. That changes the agency model. You no longer need a full traditional department for every function before you can deliver a well-rounded marketing service. One or two strong marketing engineers can run an output surface that used to require a much larger team. But this only works if the agents are actually good. It takes iteration, taste, source material, QA, workflow design, and real marketing experience. Bad agents do not become good because you connected more tools. Vague agents just create vague output faster. TLDR: > turn the agency’s knowledge into a brain > turn repeated work into scoped agents > turn each client into an isolated pod > let skilled operators run the system

for anyone asking where to learn this stuff: • RAG → weaviate.io/blog/introduct… • Agentic RAG → weaviate.io/blog/what-is-a… • AI Agents → anthropic.com/research/build… • Multi-Agent Systems → resources.anthropic.com/building-effec… • LangGraph → docs.langchain.com/oss/python/lan… • LangGraph (code) → github.com/langchain-ai/l… • MCP → modelcontextprotocol.io • Memory Systems → letta.com • Evals → docs.smith.langchain.com • Context Engineering → search "Context Engineering Survey" on arXiv and please skip the "build an ai agent in 10 minutes" videos build something, watch it fail, then figure out why.

aditya @adxtyahq

4 weeks ago

again saying there's never been a better time to work on multi-agent systems. learn rag, orchestration, evals, memory, routing, tool calling, validation loops, fix loops, split learning, context engineering. all of it. getting an llm to answer questions is becoming the easy

45 91 849 375K 962

Ultimate guide to new Claude dynamic workflows (cheatsheet):

AI Edge @aiedge_

4 weeks ago

x.com/i/article/2061…

10 58 427 251K 1K

Anthropic engineer: "You can build 5 assistants in one afternoon. Each one handles a task you've been doing manually every single day" in 45 minutes he shows exactly how to do it from scratch, step by step most people are still doing this manually watch the session, then save the guide below

Anatoli Kopadze @AnatoliKopadze

a month ago

x.com/i/article/2057…

82 473 3K 7.8M 15K

the Hermes Agent Operator Handbook a visual thread 🧵

Shann³ @shannholmberg

2 months ago

x.com/i/article/2055…

39 256 2K 1.4M 8K

Anthropic engineer Arnaud Doko: "Saying 'make it better' to Claude Code is the most expensive mistake anyone can make." In 31 minutes, he walks through the exact prompt patterns, planning workflow, and verification setup Anthropic uses in-house. Watch the full talk, then save the config below👇

darkzodchi @zodchiii

a month ago

x.com/i/article/2060…

23 57 535 1.1M 2K

Complete Claude Code Training 6 HOURS. The most comprehensive Claude training on the internet. From A to Z: setup, workflow creation, website deployment, agent team creation, browser automation, client prospecting and pricing your services. All of it without writing a single line of code. In the end: you use Claude Code like a pro and you monetize your skills. Beginner or advanced, everything is there in one place, this course covers it all. It's worth more than all those $500 courses you almost bought. Keep it bookmarked and watch later.

Rahul @sairahul1

a month ago

x.com/i/article/2059…

16 43 221 341K 659

Most engineers think CLAUDE.md is just a README for AI. They’re wrong. It’s the difference between: → Claude acting like a junior intern → Or a senior engineer who’s been on your team for 10 years Here’s what almost nobody talks about 👇 The 4-Layer Context System: 1) Project Memory Your team’s brain in one file Decisions. conventions. edge cases. (Not just what to do — what to NEVER do) Most people stop here. That’s the mistake. 2) Behavior Gates Guardrails before chaos → Block risky actions before they happen → Auto-fix code after every step → Stop secrets from ever leaking AI without this = unpredictable AI with this = reliable 3) Specialized Workflows You stop prompting. You start building playbooks. → Tasks trigger automatically → Each workflow brings its own tools + logic → Claude doesn’t guess — it executes 4) Team Orchestration This is where things get wild → Multiple agents working in parallel → Tasks split, solved, merged → Clean, isolated contexts This isn’t AI anymore. It’s an AI team. Here’s the real unlock: Individually, these are useful. Together, they’re unfair. Hooks enforce Skills execute Agents coordinate CLAUDE.md connects everything Most engineers are still writing prompts. The ones moving 10x faster? They’re building systems.