AI Agents Enter the Mainstream: From Coding Assistants to Autonomous Workflows
The Agent Revolution Is Here
Today's AI landscape reveals a community grappling with the rapid maturation of coding agents. The conversation has shifted from "will AI replace developers?" to "how do we work effectively alongside autonomous agents?"
Best Practices for Agent-Assisted Development
Several prominent developers shared their workflows for maximizing agent productivity:
- Jon Kaplan advocates for always starting with Plan Mode, iterating in natural language before execution, and leveraging AI for code review
- Michael Truell (Cursor) recommends test-driven development as the feedback loop, reverting when things go sideways, and running multiple agents in parallel via git worktrees
- Eric Zakariasson emphasizes "plan sync, implement async" - aligning on plans quickly before handing off to cloud agents, and creating validation environments for self-checking
The Rise of Autonomous Loops
The "Ralph" pattern continues gaining traction - autonomous task processing loops that work while developers sleep. As one developer noted: "last night, I had a half-finished workflow and no energy to keep going. So I started Ralph, closed my laptop, and went to bed. This morning, 6 updates. Everything working."However, not everyone is convinced. Steve Krouse offered a contrarian take: "Managing lots of Claude Codes is super dumb... You're alienated from the work. Your feedback loops are terrible." He argues for being a "craftsperson with a powerful tool" rather than a manager of AI workers.
Infrastructure Developments
- GitHub Copilot now supports OpenCode's open-source agent without additional licensing
- Ollama gained compatibility with Anthropic's Messages API, enabling Claude Code workflows with open-source models running locally
- Remotion launched Agent Skills for video creation via Claude Code
- X open-sourced its algorithm, prompting immediate analysis from AI tools
The Human Cost
A poignant thread from Sofía López resonated widely: "I work in AI and I'm scared." The accompanying article discusses burnout among early adopters who struggle to keep pace. Another developer observed someone at 3am running their "tenth parallel agent session" and wondered: "in that moment I don't see productivity. I see someone who might need to step away from the machine for a bit."The Bigger Picture
Addy Osmani provided historical context through Jevons Paradox: every time we've made software easier to write, we've written exponentially more of it. The shift isn't about replacement but about "what orders of magnitude increase in knowledge work output are we about to see?"As Damian Player put it: "the people learning this now will be untouchable in 3 months." Whether that's aspirational or cautionary depends on your perspective.
Source Posts
D
🔥🚨BREAKING: Digital artists are in a panic after this creator showed the current power of creating art with the help of AI which has digital artists fearing that they could become obsolete before 2026 is over.
https://t.co/OQPucL74SR
I
I bet this graveyard has 100+ ideas that would make $3M per year.
Just because they failed, doesn’t mean you would.
They needed VC capital
They needed a team.
They needed to be in Silicon Valley.
They needed $1B valuations
You don’t need that.
You have AI now.
You have better tools.
Good luck I’m rotting for you.
a
aditya
@adxtyahq
Someone curated 925 failed VC-backed startups, broke down why they failed, and how to make it work with today’s tech - https://t.co/NFUhrhe7P2 Cool fr🙌 https://t.co/vOv2fUDnhY
ℏ
when the creator of node.js says the era of humans writing code is over, just one week after Linus tries out vibe coding, you know a chapter in technology is slowly closing to give way for a new one.
you can be emotional about coding by hand and insist that AI coding sucks, but it doesn’t make you any less delusional.
R
Ryan Dahl
@rough__sea
This has been said a thousand times before, but allow me to add my own voice: the era of humans writing code is over. Disturbing for those of us who identify as SWEs, but no less true. That's not to say SWEs don't have work to do, but writing syntax directly is not it.
R
Here's how we created the above video!
Full prompt history: https://t.co/OhyuqqsD0o https://t.co/h1T4JwCIKS
e
exactly how i code with agents. some more:
4. plan sync, implement async. if you can quickly align on a plan, you'll have higher confidence when handing off to a cloud agent
5. create validation environments, so you can ask agent to check its own changes
J
Jon Kaplan
@aye_aye_kaplan
My top 3 tips for coding with agents: 1. Always start with Plan Mode. It's better to iterate in natural language and then execute once you know what the agent is going to do. This will save you time, effort, and tokens! 2. Start new chats frequently. Remember that your role is to point the Agent in the right direction to make the changes you need. If you change topics, the context window will get muddied. You will also be spending more tokens on longer chats. 3. Leverage AI to do your code review. If you know the failure case, ask a model. One prompt I often use is "scan the changes on my branch and confirm nothing is impacted outside of my feature flag". As a safety net for everything outside this issues-you-expect umbrella, use Bugbot.
S
MANAGING LOTS OF CLAUDE CODES IS SUPER DUMB
That's like in the 1950s thinking that TV is just radio announcers at a desk reading from a script. Nope. It's sitcoms, movies, YouTube, TikTok.
Or in the 1970s thinking that the future of accounting would be managing a bunch of number crunching "agents". Nope. It's Excel or Quickbooks.
Managing SUCKS. You're alienated from the work. Your feedback loops are terrible.
What's better?
Being a craftsperson with a powerful tool
My brother in christ, you can only think of 7 things at a time, and if you're running 2 Claude Codes, each has a couple details that need your attention, so you're already all maxed out of things to think about, so you can't even notice how un-productive you're being
Yes, I get the instinct to RUN AS MUCH INFERENCE AS POSSIBLE
LLMs seem like super cheap employees. If you aren't giving them the MAXIMUM work, you're leaving money on the table
I have a suggestion for you. A way for you to run LOTS OF INFERENCE.
Let's go back to my boy @worrydream
INTERACTIVITY CONSIDERED HARMFUL
There is so much context stored in my github repo, my issues, my commit history, also my email inbox, etc.
If you could somehow be passively ingesting all that and running all sort of inference on it WITHOUT ME HAVING TO MANAGE IT, that sounds awesome
There is so much cleaning up that I'd love someone to do on my GitHub Issues backlog
Or if you want to go ahead and try to end-to-end solve some of my tickets and ONLY NOTIFY ME WITH A FULLY WORKING PULL REQUEST, TOTALLY VERIFIED, THAT OTHER AGENTS HAVE REVIEWED, WITH AN AMAZING PR EXPLAINER THATS SUPER CONCISE AND NOT SLOP, oh my god, take my money
Can you do something similar for my email inbox? I'll name my first born after you.
I want LESS management.
LESS slop.
If I wanted more management and more slop, I would hire interns or offshore contractors
I hire the best engineers I can find who give me less to manage, less to edit their writing
I want AI to do the same
k
node js creator: coding is dead
avg mid miderson: i will never trust llms!!! I need hours of convincing to help my skill issues
R
Ryan Dahl
@rough__sea
This has been said a thousand times before, but allow me to add my own voice: the era of humans writing code is over. Disturbing for those of us who identify as SWEs, but no less true. That's not to say SWEs don't have work to do, but writing syntax directly is not it.
v
AI Agents 102
AI Agents 102
So, you've built an agent that kinda barely works in demos and now you want to deploy it for real users with real use cases. Demos and production have...
J
Created this video without writing any code, but also without needing After Effects skills.
Yet I was able to control every detail! Never felt so powerful 🧙🏻
R
Remotion
@Remotion
Remotion now has Agent Skills - make videos just with Claude Code! $ npx skills add remotion-dev/skills This animation was created just by prompting 👇 https://t.co/hadnkHlG6E
G
GitHub Copilot now supports OpenCode's open source agent. No additional license needed.
https://t.co/yfMJnw1Gg5
J
Palantir CEO Alex Karp says people think we’re in an AI bubble because a lot of AI just doesn’t work:
“If you just buy LLMs off the shelf and try to do any of this, it won’t work.”
“It’s not precise enough. You can’t do underwriting. You can’t do these things that are regulated.”
“People have tried things that just can never work. You buy a LLM, put it on your stack, and wonder why it’s not working.”
“What you’re going to see, especially in America, is people trying to do something like Ontology by hand.”
“Once you build a software layer to orchestrate and manage the LLMs in a language your enterprise understands, you actually can create value.”
“There’s a lot of discussion on if we’re in an AI bubble. What is the meaning of this bubble? If anything, we’re just in a lag. There’s a lot of AI, some of it works.”
“Go back to the battlefield context: everybody in the world assumed this would not work. But now it does work. Now the question is, ‘How can I get it to work for my country?’”
“Palantir barely has a sales force. In fact, it seems to be getting smaller and smaller every time I go see them.”
J
Just had coffee with a guy doing AI implementation for mid market firms
Last client went from $250M a year and $4M in ebidta to $400M run rate $40M in ebidta
In a PE world where an exit means you capture a multiple of ebidta in the transaction
This is hundreds of millions of dollars in value creation
The alpha is in the upside. The ownership.
If you can do this. That’s where you should be selling
E
I gotta say, I am surprised at how easy the terminal plugin was to install for Obsidian.
Now I've got Claude cooking on finding the stuff I remember that's related to the (very) short story I wrote last night, & am ready to put together my list of things to do for the day. https://t.co/Da2rtb2sF4
C
The VS Code extension for Claude Code is now generally available.
It’s now much closer to the CLI experience: @-mention files for context, use familiar slash commands (/model, /mcp, /context), and more.
Download it here: https://t.co/q95Cw4soMk https://t.co/3BCWPvybdZ
B
Lunch w/ an exited founder who helps fortune 500 companies adopt AI.
Insane reality check:
Some of the biggest companies on earth use *zero* AI tools.
Not even ChatGPT.
Execs only recognize: ChatGPT, Copilot, Gemini (maybe Perplexity).
Everyone feels behind.
Nobody knows what to buy or how to plug it in.
The "AI saturation" narrative is another example of what a bubble Silicon Valley is.
Rest of the world hasn’t started yet.
We have to build for the 99%.
M
It's crazy how after discovering Ralph this stuff feels a bit quaint
All this advice can be automated away with a few lines in a bash loop
J
Jon Kaplan
@aye_aye_kaplan
My top 3 tips for coding with agents: 1. Always start with Plan Mode. It's better to iterate in natural language and then execute once you know what the agent is going to do. This will save you time, effort, and tokens! 2. Start new chats frequently. Remember that your role is to point the Agent in the right direction to make the changes you need. If you change topics, the context window will get muddied. You will also be spending more tokens on longer chats. 3. Leverage AI to do your code review. If you know the failure case, ask a model. One prompt I often use is "scan the changes on my branch and confirm nothing is impacted outside of my feature flag". As a safety net for everything outside this issues-you-expect umbrella, use Bugbot.
H
Anthropic CEO, Dario Amodei:
"we might be 6-12 months away from models doing all of what software engineers do end-to-end"
We're approaching a feedback loop where AI builds better AI
But the loop isn't fully closed yet, chip manufacturing and training time still limit speed
D
Presented the Ralph loop to 2 engineers still using VS Code AI extensions.
My 10x loops GLM-4.7 fixed something their Opus didn't.
They went quiet. Now I'm doing a workshop on it.
No good deed goes unpunished.
R
Remotion now has Agent Skills - make videos just with Claude Code!
$ npx skills add remotion-dev/skills
This animation was created just by prompting 👇 https://t.co/hadnkHlG6E
G
That us engineers will not write most (or any) code by hand doesn’t mean what many replies assume it does - that there won’t be demand for SWEs.
The opposite: I expect more demand for software engineers who can build reliable+complex software with LLMs!
https://t.co/sSfyCm8jk8 https://t.co/0JSgdHxlXr
R
Ryan Dahl
@rough__sea
This has been said a thousand times before, but allow me to add my own voice: the era of humans writing code is over. Disturbing for those of us who identify as SWEs, but no less true. That's not to say SWEs don't have work to do, but writing syntax directly is not it.
A
“How It Works” Educational Dioramas
Gemini Nano Banana Pro Prompt:
Create a clear, 45° top-down isometric miniature 3D educational diorama explaining [PROCESS / CONCEPT].
Use soft refined textures, realistic PBR materials, and gentle lifelike lighting.
Build a stepped or layered diorama base showing each stage of the process with subtle arrows or paths.
Include tiny stylized figures interacting with each stage (no facial details).
Use a clean solid [BACKGROUND COLOR] background.
At the top-center, display [PROCESS NAME] in large bold text, directly beneath it show a short explanation subtitle, and place a minimal symbolic icon below.
All text must automatically match the background contrast (white or black).
J
you kinda seem more like a Claude Cowork user (derogatory)
🇺
Raise Your Kids Right: 10 Books Every Young American Should Read
Raise Your Kids Right: 10 Books Every Young American Should Read
In today's world, instilling a strong sense of right and wrong, self-reliance, honor, and love for country isn't automatic—it's a deliberate choice. T...
M
Our tips on how to use Cursor:
- Start with a plan (Shift+Tab Plan Mode)
- Let Cursor search on its own, don't over-tag context
- Use tests as the feedback loop (TDD + iterate until green)
- When it goes sideways: revert → tighten the plan → rerun
- Keep long chats short; use @ Past Chats for continuity
- Add lightweight .cursor/rules for recurring mistakes
- Use skills + hooks for long-running "grind until tests pass" loops
- Run multiple agents/models in parallel via worktrees
C
Cursor
@cursor_ai
Here's what we've learned from building and using coding agents. https://t.co/PuBtYuhyhd
E
I am no longer using _any_ MCP servers in my local setup [ @code / @GitHubCopilot, @opencode, @claudeai code ].
・Context7 → SKILL + curl
・Tavily → SKILL + curl
・Playwright → SKILL + agent-browser
SKILLs are all you need!
M
@marckohlbrugge Seconded on the YOLO but instead you should create a new layer for it to interact with.
E.g an email for the bot which you forward things onto.
This will probably be the future, we'll have 3 identities:
- Social networks
- IRL
-Agent version of you
K
I tried this but couldn't find option to choose model with opencode :(
A
Addy Osmani
@addyosmani
Vibe Kanban: orchestrate multiple AI coding agents in parallel. Free and 100% open-source. Switch between Claude Code, Codex Gemini CLI, and track task status from a single dashboard. https://t.co/XfZLWpevqM
W
"Software Engineering Will Be Automatable in 12 Months,"
Anthropic CEO Dario Amodei predicts that AI models will be able to do 'most, maybe all' of what software engineers do end-to-end within 6 to 12 months, shifting engineers to editors. https://t.co/7bI7JmTtsb
S
AI made everyone 10x faster. But the faster individuals move, the harder it is to move together.
Speed ≠ Progress when no one has the full picture.
Today we emerge from stealth with $5M led by @GeneralCatalyst to fix this.
Meet @stillaai : The first Multiplayer AI. 🧵 https://t.co/lkRsBjhCIt
C
This is where we're at rn:
I spent the 3-day weekend agent-coding a complex system: advanced networking, orchestration, caching, bare metal, reverse proxies, custom Linux kernel
This would've taken me 1-2 years solo
And the result might be one of the best in its category