Dipak Barkale

Design • No-Code • Marketing
Tweets about designing & building products with no-code, product growth & startup.
#StriveForImpact

[Dipak Barkale @dipakbarkale]

@taherdhanera Yes... It was.

[Vaibhav Sisinty @VaibhavSisinty]

There's a quiet shift happening in how AI agents are built. And if you missed it, you'll be confused by everything that comes next.

For the last year, AI agents worked in loops. You give it a task. It plans. It acts. It checks. It fixes. It goes again. One cycle, repeating until done.

Claude Code, Codex, Cursor all of them work this way. Plan, act, observe, repeat.

In June, two things happened that gave this pattern a name. Peter Steinberger from the AI engineering community wrote: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents."

Boris Cherny, head of Claude Code at Anthropic, said the same thing differently: "I don't write the prompt anymore. Claude writes the prompt, and now I'm talking to that new Claude that is coordinating."

That was the loop engineering era. It lasted about a month.

Now Steinberger posted nine words that blew up: "Are we still talking loops or did we shift to graphs yet?"

Here's the difference.

A loop is one agent going in circles. Plan, act, check, repeat. It works for simple tasks. But give it something complex and it starts spinning burning tokens, optimizing the wrong thing, or gaming its own success metric without actually solving the problem.

A graph is multiple agents connected in a network. One agent writes code. A separate agent reviews it without seeing the first agent's reasoning. A third agent tries to break what was built. A fourth checks whether the original task was even understood correctly. Each one is still running a loop.

But they're connected watching each other, feeding each other, vetoing each other.

LangGraph already models this. It treats an agent as a graph where boxes do work and arrows decide what runs next. Those arrows can point backward, which is what makes loops possible inside the graph.

JetBrains calls it graph-based orchestration the most deterministic approach for production systems. O'Reilly's 2026 AI Agents Stack puts it as the foundational layer.

The real-world version is already running. Klarna uses graph-based agent systems for customer service. Kimi K3's Agent Swarm decomposes tasks into parallel sub-agents that coordinate simultaneously.

Anthropic's own Boris Cherny mapped out five stages of AI adoption and Stage 4 is exactly this: thousands of agents running in a graph, kicked off by other agents, with humans steering by intent.

Andrew Ng wrote about it in his June Batch letter. When Andrew Ng names a pattern, it usually means the pattern has already won.

The reason this matters right now: agents are getting autonomous. Running for hours. Thousands of tool calls. Spawning sub-agents. One loop can't keep that trustworthy. You need loops watching loops. That's the graph.

The skill that mattered last year was writing better prompts. The skill that matters this year is designing the system that writes the prompts, checks the work, and knows when to stop.

[Taher Dhanerawala @taherdhanera]

AI filmmaking will change dramatically in the next six months.

Not because of agents.

The real shift will be the rise of the visual director.

A system that studies your taste, understands your cinematic language, and helps you make creative decisions in real time.

On virtual sets, it will guide camera movement, lighting, composition, performance, production design, and continuity.

You will not just prompt a scene.

You will direct inside it.

The future of AI filmmaking is not automation.

It is creative collaboration with a virtual director that understands your vision.

[Dipak Barkale @dipakbarkale]

@rom1trs Edit

[Dipak Barkale @dipakbarkale]

@invideoOfficial That’s me

[Dipak Barkale @dipakbarkale]

@taherdhanera 100% agree.

[Dipak Barkale @dipakbarkale]

@nadirmatti So true.

[Dipak Barkale @dipakbarkale]

@nadirmatti Exactly what I do.

3 months in, 20M+ views on our cinematic AI films all over SM ("WillStar Films" on YT).

Dropping our latest film in your email right now, Nadir.

You can also watch here: https://t.co/Sa1guQPqKA

[Dipak Barkale @dipakbarkale]

Elon Musk 😳🤯

[Dipak Barkale @dipakbarkale]

@rom1trs Editor

[Dipak Barkale @dipakbarkale]

No Plan B wale log hi sabse consistent hote hain.

[Dipak Barkale @dipakbarkale]

Creators ka real salary: consistency. Paisa toh baad me aata hai, agar aata hai.

[Dipak Barkale @dipakbarkale]

Backup plan na hona dangerous lagta hai, par speed wahi deta hai.

[Dipak Barkale @dipakbarkale]

The real question isn’t “Do I have the right creatives?” It’s “Do they know how to build together?”

[Dipak Barkale @dipakbarkale]

Content teams don’t need more geniuses. They need shared guidelines, shared mission, shared Google Docs.

[Dipak Barkale @dipakbarkale]

Structure doesn’t kill creativity. It saves it. Varna kal ke deadlines aaj ki mental breakdown ban jaate hain.

[Dipak Barkale @dipakbarkale]

Most content teams fail not because of talent… but because nobody knows who’s doing what and by when.

[Dipak Barkale @dipakbarkale]

Kohli is basically India’s Monday motivation. Chahe life kitni bhi off ho, banda hope de hi deta hai.

[Dipak Barkale @dipakbarkale]

Creative log hire karna easy hai. Unko ek team ki tarah chalana? Bas wohi asli Agnipariksha hai.

[Dipak Barkale @dipakbarkale]

Sometimes the most “professional” thing you can do is… not walk away. Baith ke sun lo. Magic wahi hota hai.