Skip to content

Instantly share code, notes, and snippets.

@fatso83
Last active March 3, 2026 05:59
Show Gist options
  • Select an option

  • Save fatso83/73a91ed6b6b7e8b3d01bc5e3750ea69c to your computer and use it in GitHub Desktop.

Select an option

Save fatso83/73a91ed6b6b7e8b3d01bc5e3750ea69c to your computer and use it in GitHub Desktop.
2026-03-01 AI Dev Day at TRYDig

https://try-management-app.vercel.app/ai-dev-day?v=4

Pictures from the presentations

There might actually be a video at some point I can link to instead

Håkon Bogen - delete your Claude.md

Better to delete a Claude.md than to pollute your context with outdated info.

Only info worth putting into the claude.md is the things it don't get right. Update it when you have to correct it.

Magnus Bergman - Vibe Coding

Vibe Coding is now at a level where it is at my level or has surpassed me

Lets me focus on problem solving. The code has always been the medium. Getting the AI to produce beautiful code is almost as satisfying.

Makes it possible to be productive in languages I do not know.

Never ever ask the AI to start coding before discussing first. Always produces shit code immediately.

The process

I want to tell it what to do and discuss before it does anything.

90% in brainstorming mode A skill that I use to juggle back and forth with the AI to discuss solutions. Which side effect certain designs have.

Creates plan files using the skill.

He keeps them in the project, but does not commit them. The plans should be committed. Was not sure if he wanted or not, but they should be.

We need to find a way to do that properly.

Håkon has set up all his skills to delete the plan files once they are done.

Magnus really wished there was a simple way of using them as documentation. Feels there is a lot of value in the designs.

Agree that outdated documentation is not great, but it would be good ...

Context rot

If you do not clear the context at regular intervals, or do too much, you run into implementation plans where nothing of what was asked was actually done.

Important: even though you try to be explicit, you can end up with vibe coding results.

Spend more time in initial phases. Spend extra time there where you know you are actually good.

It will accumulate errors in the context, also when compacting.

Better to start over fresh.

Better to be careful and not run into compacting.

The cleaner yoru context is, the better yoru plans are, the better the results it will end up with.

Don't say: "Don't think about the pink elephant!"

It will then always have it in the context. It will pollute your context and thinking.

Most important tip: Try the skill Superpowers

It will transform your workflow.

If anyone needs help getting into it, Magnus can try.

https://github.com/obra/superpowers

https://skills.sh/obra/superpowers/brainstorming https://skills.sh/obra/superpowers/systematic-debugging https://skills.sh/obra/superpowers/test-driven-development https://skills.sh/obra/superpowers/writing-plans

Right now, I am the bottleneck

If he could have more arms and windows, he would be more productive. He is the current bottleneck for what could be done.

Agent teams.

You have to add a setting to Claude Code. Makes it a complete team with a team lead. Useful for bigger tasks.

Even bigger team than sub-agents.

Magnus: the AI cannot think for itself. I do not want it to think it is the team lead. You need to manipulate the AI to think correctly.

Audience (Martin): never got sub-agents to work, but teams is crazy good. Not necessarily huge tasks. Testing sub-agent that runs the browser window or testing output.

Sanna Jammeh

Fullstack engineer

Next and Caching

The agent works for you

Adept to your needs

LLMs are proediction engines

humans interact.

No right or wrong. Just good and bad variations.

The most efficient ways of getting agents to do wthat you wnat

Shortcut problem

From A to B. From prompt to solution.

Consders

  • cost
  • speed of route
  • conenience Takes shortcuts

The dirt road for CLI agents

  1. Hallucinate APIs
  2. Use deeprecate code. Trained on old code / library names.
  3. Quality is perfect, but does the wrong thing.

Scenic route

What it thinks you want, not what it knows you need

  1. Skips critical parts. avoids complexity
  2. Pure lazyness.

Upload a better map

The best map is what works for your workflow

  1. Configuration
  2. ..
  3. ...

Set of rules for every agents session.

Global Claude.md

HOME/.claude/CLAUDE.md

Consistency Align with expectations

Project Claude.md

Minimal For everyone working on the project Respected most of the time Should update quite often Consise as possible

/init

Skills

Set of instructions to

  • perform actions
  • gain knowledge

http://skills.sh npx skills add skills

Agent Browser

Local Claude.md + agent browser = 💨

When performing frontend dev always

  • check localhost, if not running, as k the user to start it, do not start yoruself
  • use agent browser skill to verify your work visually
  • use agent browser skill to check scope of bug tasks before starting
/clear

users are reporting tahat on the https://raumagarn.no/forhandlere" we see a wierd looking input. Please check it and to try to fix it in code. Deveserver is running

....
Skill: agent-browser
...


/clear 

users are reporting tahat on the https://raumagarn.no/forhandlere" we see a weird looking input. Please check it and to try to fix it in code. Deveserver is running. Please. Also use the agent browser.

...

agent-browser opens http://localhost:3000/forhandlere

Screenshot saved to ... 

I can see the issue clearly. Search input with two overlapping placeholder texts. 'Søke etter forhandler' and 'Søk etter sted' is overlapping

Fix: changed ...

Compact or clear frequently

Stay away from 1M Context models for better performance.

Agent compactions and context reset

Asking the agetnt to summarize its current work

  • clear all clutter
  • 190k tokens -> 20k Auto compact
  1. Task too big
  2. multiple tasks within same
  3. youre getting less quality clode

/clear

  • start from scratch

Spec driven development

LLM assisted scoping

Planning ahead a

Accurate specifications reflecting bheavior

Openspec.dev

Minimal can be used for any changes of any size

Workflow propoosal design tasks spec

Git worktrees

Multi-task

Spin up new versions of the same project

pwt.skala.sh

bun install -g pwt-cli

Git worktrees let you check out multiple branches simultaneously in speearte directoreies. Instead of stashing or commiting...

PWT simplifies worktree management.

agent browser

NPM utility. designed for AI agents.

Eirik Eikas - Real-time AI Media Training

Live demonstration of AI-powered crisis management and media training prototype

STT - speech to text TTS - text to speech

Can use Norwegian number. SIP trunking. Must talk to Telia.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment