Posts tagged: agentic

Agents Are Here

2026-04-10T16:11:37Z

Late last year I started writing I'm Out On Agents. Agents sucked, the models were good, but there was still something missing between the harnesses and the models. They could write good code, they could do some debugging and exploring, but they were too good a fucking up the whole project to be useful. They could crank out Green Field POC’s like nobody’s business, but they created so much mess in brown field projects that it was easier to chat and edit yourself.

f91a8893-b1ba-422a-9390-18de5034483c.mp4

The Beautiful Glitch - Gemini

The Inflection Point #

It’s very well agreed on that the inflection point for most people happened with Anthropic Opus 4.5 in late Nov 2025. Early adopters probably noticed right away and shouted from the rooftops how good it was. But we’ve all heard that developers have 6 months before ai writes all the code for years, so this felt like the rest of the noise.

Hitting the December slowdown many of us hit code freezes at work. We completely disconnect from work for the last Week and come back in January. During this time, its very common for us to try out new tools, new techniques work on side projects, create POC for that thing we never have time for. While it looks like less features coming into the apps we support this is an important time for us to explore and reflect.

Anthropic was super generous with a free tier giving out huge levels of free tokens at the time. So many of us laughed and threw it at our side projects expecting the normal garbage output, but maybe some good ideas to come from it. But that’s not what was happening anymore, somehow these agents do some real work, follow plans and stick to scope really well. And if you lay out a big enough plan they tended to keep cooking and completing features.

January 2026 #

flu season

For me and many others around the country we were hit with a rough flu season, kicking in and draining us mentally for a good month or so. I wanted to work, I was getting excited about some projects and wanted to get them going, but I was constantly wiped and had no capacity. I had no ability to think on complex tasks, I was coughing all the time, just trying to survive, but yet wanted to do something. I started doing some small clean up, some work on side projects.

At this point I was still afraid of really letting agents cut loose on something meaningful, something that users depend on.

February 2026 #

what just happened?

yes or –dangerously-accept #

March 2026 #

April 2026 #

Closing the editor #

b289fda3-35e7-4b2f-aa21-6601c57d937a.mp4

Closing the Editor - Gemini

How To Run 5 Agents In Parallel Feb 2026 Edition

2026-02-11T09:28:02Z

Are developers really running 5 agents in parallel? How the Heck do they keep up with the changes? This seems Impossible.

I was listening to Syntax.fm this morning and heard this question, and thought I’d throw in my take, which is probably pretty similar to Wes and Scott’s.

https://www.youtube.com/watch?v=NrBQI9So5lM&list=PLLnpHn493BHHNUfHN5lDf11UD8jQ5Bpzl&index=1&t=99s

Yes #

Yes, developers are running 5 agents in parallel. It’s not that hard it requires you to shift from thinking about the weeds and seeing the forest see: Pm Not Babysitter. It requires effort and diligence. Most importantly it requires planning, it requires agents, it requires tooling.

Is anyone doing this all day? Probably not. At least not outside of the startup companies that are building out tools to do this. Yes there are some, there’s always outliers, but its going to be rare. To have multiple agents running in parallel add day you need a lot of tokens, access to good models, and right now a low to medium risk application.

The big news right now is that Anthropic did what took google two years to do around 2008 (make a prototype browser render basic web pages) in 2 weeks. This took a swarm of agents running, a good plan (the modern browser is probably the most openly spec’d piece of software ever to exist, so they had a lot to go on). But this is also zero risk. If it doesn’t render there are no sales lost, no traffic accidents, no security breaches, no missed deadlines.

not with chat #

chatbots like chatgpt, are not getting you to run 5 agents in parallel. Maybe you take a sip of your coffee while it spits out its response, but you don’t have enough time to jump between many of them. If this is your experience so far, I understand how confusing it would be to think that someone is running 5 agents in parallel. But they are, and they are doing it with tools that are not chatbots.

PLANNING #

This is the core of what it takes to keep agents running for long periods of time in Feb 2026. Agents need something to do, telling them to turn the circle green, then blue, then to a rectangle, is not it, They will have this done in seconds. You probably could have done it just as fast and better.

For the plan itself, Send agents off to research. Agents are not good at solving problems without a good plan, but this does not mean you have to tediously write out the plan from scratch. They are really good a reading docs, specs, standards, finding them on the web. Reading your codebase to understand where and how a bug might be happening. They are really good at running bash, browser automation, they can reproduce your bugs for you and provide detailed logs with expected and actual behaviors in your plans.

Note

If you are trying to solve a production problem in an environment where you have risk and dont want agents running wild in, dont let them in, or scope their permissions. They are really good at understanding they cant access and writing a script for you, one that you can review to ensure they are gathering facts and not chaning production servers. Then you can run it yourself and paste the results back in. Sure there are better ways, but without any set up this works.

Executing plans, if you have well scoped and documented work for the agent to do, as of right now they are happy to keep working. I dont think there yet exists any sort of best practice here yet. I prefer to keep it out of the agent tools plan mode only because that is so deeply tied to the session. If you get context poisoning or a shit compaction your session might be hosed and unrecoverable, I’m sure you could go into the agents session files and do something to get it back, but I’ve yet to need one back that bad to really care.

What you need is a system that agents can access to tell them what to do, a simple markdown file works, GitHub issues work, I’m sure boards, and kanban work if it has an api the agent can understand.

I'm In On Agents

2026-01-11T12:02:15Z

It’s the start of 2026 and agents are getting a lot better than they were. I’m using opencode at home, free mode with Zen and big pickle. At work I have access to a wider variety of models including what seems to be the gold standard 3 from anthropic opus, sonnet, haiku.

Note

I’ve sat on this post for over a month, refactored it a few times, things feel like they are moving so fast that its hard to keep my feelings straight.

Things are changing #

Around Aug 2025 I wrote I'm Out On Agents. I saw others in the space having such great success I gave it a solid shot, but found it to egregious edit more than I asked, make massive unneeded changes, and make more small bugs hidden in the details than was worth it.

This was just after the tipping point where not just hype bros were making the switch, but people I work with, people I trust and have made really good Software in their career. People like the creator of Flask Armin Ronacher. People who are really good at writing code and do not need it to do the work were finding themselves more efficient working with agents than making edits by hand.

Planning #

Currently as I see it there is no free lunch. Software engineering is still very much needed, but the work is switching. The models have been good for awhile, they don’t seem like they are getting leaps better with each release like they were for so long, no matter how much t3.gg hypes up the new models. The tools feel like what is really making the difference right now. The ability to take short human prompts figure out what context is needed, getting that context, and keeping it in the context window is getting better and better making agents useful for more things.

These improvements in tooling is making our job look different. Knowing syntax and how to write clean efficient DRY code is less and less of the job every day. Learning how to create detailed plans with the help of agents, editing them, knowing when they are good enough that you can be confident in an agents ability to execute on them. Knowing how to balance the context is becoming the job. Moving forward its likely that models can handle more context and this will look different, and change, but planning and context management is a key part of the job moving forward.

Context is king, good plans are paramount, syntax barely matter.

Issues #

I'm Out On Agents

2025-08-27T10:10:51Z

Its the year 2025 and we are only a few years into having 6 months to live before ai takes our jobs, and the big push right now is agents, managing agents. I will fully concede to I’m not doing it right, or a future state gets better than where we are right now, but right now they kinda suck.

Transparency

I’m sitting offline right now as I write this, These are my feels, no research, no links, no ai, just vibes.

Chat #

Chat is what really kicked off ai uses and goes back as old as computers, but it always sucked. Then chatgpt rocked the world with the biggest launch day in history and showed us that it could actually be pretty good. Unethically trained on everything they could get their hands on, burning cities worth of electricity to train, and keep training to stay ahead of the competition. It does a damn good job. There are tells, and if you see enough of it there is a lot that turns to slop, but if you had never seen it before, there is no way you would assume that it was not a computer.

It does a damn good job at being average, it can do what seems like everything not related to security and authentication at a pretty average level. This is its super power. Whenever you are trying to bridge between something you know and something new, you can get a pretty good answer, and likely spot the bs in what you know.

Agents #

Now that our models have gotten better, hardware has gotten bigger, better, and a lot more of it, we can really expand context windows really wide. With that brought the use of agents, these tools get context from sources on their own and often are given read/write access to your computer. Depending on the model these things will branch out to make small changes that look no worse than a formatter on every goddam line of your codebase. Except they are not a formatter, they are not backed by ast checks. They do not have any guarantees.

They take the fun out of creation.

The emphasis now becomes on the code review. All you have to do is ask it to makes changes for you. Bring in your expertise of what changes should be next, or even just punt to asking it what comes next. I’ve yet to talk to someone that is diligent enough to read everything it spits out in excruciating detail to the point that it does not cause significant issues.

You see here is the thing, its average. With a little bit of context it can do average work. It is not an expert. On the surface this feels fine, making crud endpoints has been done for decades, and average developers crush these things every day no problem.

It’s Average at best

You know what is not average? Your knowledge of the use case you are solving. You may not feel like an expert, but given that there are likely about 5 people working in your codebase, you are a fukin expert at that thing. The average person off the street takes time to onboard, often months, or years for someone to really understand the business you are working in. These things don’t have that.

I’m not letting it in shit that I care avout #

I was early to the game to codeium, even used the predecessor for awhile, I was early to chat gpt, I was early to windsurf and the possibilities that agentic ides brought. I will be late on letting agents touch my production code bases. The few times I’ve tried for changes that seem easy enough, but more work than what I want to do at the time, I’ve regretted it. It’s only left behind a mess that it cant deal with anymore, runs in circles trying to solve any problem, and I’m left with shit that feels like a house of cards that breaks anytime you touch it.

I will continue to POC #

As much of a mess as these things, make they are super useful to vibe code ideas, move quickly and try different approaches to a problem. They let you make a proof of concept that you can get in front of team mates, bosses, or users.

Honestly I still prefer the chat interface. It feels like a nice balance of using my brain, and knowing that I am punting on something. Do I need to know the whole ffmpeg interface to grab a thumbnail for my webapp, no, would I actually like to learn it someday, yes, but I don’t need to right now I just need a goddamn thumbnail.

For the most part I am still slotting these things into the codebase myself, but occasionally I have it do an entire module, and even more rare I pull out agents and have it do all the work. The further away from the code I get, the less I care about it and just want it done.

I will laugh at this post in 2 years #

The way I see it agentic coding is not here to stay, it sucks. There is one two ways to go this was a blip in the radar that we laugh at for giving ai companies all our data for free so they could fuck up our products. Or they actually get pretty good and we all become architects that peek at the code if we really need to. I think for the second to become true its going to take a lot of time, consumer hardware will need to catch up, local llms will need to work a lot better than they do now. Even if we still need to call out to the big boys for some heavy work getting the context right for them locally would make a huge difference. Currently local llms are too slow and dumb.

So will this bubble pop or explode, we can only wait to find out.

💭 Meet Gor | I kind of hate Agentic IDEs for the sake of product...

2025-08-02T15:00:38Z

External Link

meetgor.com

Yes, I can review the code and make changes, but who in the world loves reviewing code? Do you love reviewing peers’ PRs? really?

I’m with MeetGor here 100%. reviewing the nuance, not being as involved with the process of creating the architecture design, not solving the problems that arise in development make it hard to effectively review and not turn into LGTM man.

Note

This post is a thought. It’s a short note that I make about someone else’s content online #thoughts

💭 awesome-cursorrules/rules/py-fast-api/.cursorrules at main · P...

2025-01-09T14:03:12Z

Looks like a great start to a rules file for fastapi.

Place the happy path last in the function for improved readability.

I have never heard anyone say this. It feels weird to me. The other early return, find and handle errors early all make sense to me, but happy path last is new to me.

Note

This post is a thought. It’s a short note that I make about someone else’s content online #thoughts

💭 Generate Custom .cursorrules for Your Project Based on Communi...

2025-01-09T13:53:40Z

Generate Custom .cursorrules for Your Project Based on Community Examples

expert led courses for front-end web developers and teams that want to level up through straightforward and concise lessons on the most useful tools available.

egghead · egghead.io

Really interesting way to generate a rules file for agentic workflows based on your current repo. John uses gitingest here, looks like a fantastic tool, but probably not useful for most private repos. I’m sure you can replicate the same thing in a private repo wtih a small amount of effort the few times you need to do it. gitingest looks like a great way to pull in some extra context for some open source dependencies that you have though.

Note

This post is a thought. It’s a short note that I make about someone else’s content online #thoughts