Çoklu Ajan Görev Sözleşmesi
Çoklu ajan iş bölümünü açık sorumluluk ve devir kurallarıyla düzenler.
HAZIR VE KOPYALANABİLİR
Prompt Kütüphanesi
315+ test edilmiş prompt şablonu; yazıdan koda, görsel üretiminden kariyere kadar. Değişkenleri ({böyle}) kendinize göre doldurup doğrudan kullanın.
15 non-obvious ways developers are using terminal coding agents right now
Hi all, saw a few of these "what devs are actually doing with AI agents" threads floating around and wanted to compile a cleaner list before asking my own question, because most of the "what's your workflow" posts I see get buried under generic "I use it to write boilerplate" replies. These are 21 specific things people are doing with terminal coding agents (Claude Code, Codex,
4 Workflow AI Prompts to Prepare for a Productive Workday
A productive workday begins with intentional mental alignment before tasks take over your attention. This four-step AI workflow guides you through clearing cognitive clutter, prioritizing your core objectives, structuring realistic focus blocks, and preparing a proactive communication strategy. Mental Brain Dump and Priority Extraction This is the first step of your morning rou
AI content creation made me spend more time fixing stuff than creating
starting to think having a good workflow matters way more than chasing the newest model every week. curious how everyone else is building their setup these days. are you sticking with one tool or mixing a few together depending on the project? anyone else hit this point where ai content creation was supposed to speed everything up but now half the job is fixing weird little thi
AI implementation keeps stalling in mid-size organizations, not due to tech
For many organizations, AI adoption looks great on paper. But beyond that, it just kind of fizzles. John Munsell explained this as: you need 3 things moving together at the same pace: How much efficiency people are actually gaining day to day. How complex the systems and workflows getting built are. Governance- the rules and oversight that keep things from spiraling. Miss the s
anthropic quietly released free industry packs that turn claude into a specialist. the legal one reviews a contract the way a lawyer would
Most people run general Claude for everything and never touch these. They're free, official, and each one loads Claude with the workflows an actual specialist in that field uses. The legal one is the standout. Install it, then: Review the attached contract. Flag every clause that deviates from standard terms, classify each risk as low, medium, high or critical, and generate red
Building a persistent memory + orchestration layer for Codex — what should I use instead of repeatedly re-reading the repo?
I’ve been building a fairly serious agent workflow around OpenAI Codex for a Laravel/React project, and I’ve hit a point where the orchestration works, but the context/memory side clearly does not. My setup currently looks roughly like this: A serial orchestrator with route types like FAST_UI / STANDARD / CRITICAL Context Resolver → Implementer → Reviewer flow for non-trivial t
Built this over the weekend because I was tired of doing the same browser task
I had this annoying habit of opening the same websites every morning. GitHub. Linear. Our internal dashboard. A couple of docs. One admin panel. It wasn't hard work, just the same clicks every single day. Over the weekend I spent an hour turning it into a WebCmd & Playwright workflow instead. Now I don't think about the steps anymore. I just run it, grab what I need, and move o
Context compression is probably more important than prompt engineering
Hot take: For long AI workflows, context management matters more than prompt engineering. A perfect prompt can't save a conversation that's 80% irrelevant context. I've started treating long AI sessions like this: Persistent project brief Decision logs Context checkpoints Compression summaries Reusable templates The quality difference after 50+ messages is huge. Does anyone els
How are you versioning prompts when PM edits and code deploys keep crossing wires
We’ve built two release systems for one support agent and now we’re struggling to figure out which prompt is actually in production. PMs tune the conversational parts in a playground. Engineers keep fallback text, tool instructions and safety rules in code. Both workflows are reasonable on their own. But, last week a hotfix changed the system prompt and unfortunately, the evalu
How long of a chat thread do you use to fix a bug or implement a feature using your AI coding agent?
I am interested in understanding how people interact with an AI agent performing coding tasks for you. For example, for a bug fix, do you explain the bug, then iterate with the AI agent in the same thread until the bug is fixed, tested, and deployed? Or do you use separate chat threads for each stage of your development workflow? Similarly for new features, do you scope the fea
I distilled Google's official Gemini agent guidelines into a battle-tested agentic workflow system prompt
If you have built autonomous agents or multi-step tool-calling workflows with LLMs, you have likely run into the standard failure modes that break production agents: Premature Action Bias: The model fires off tool calls or answers the user before mapping out prerequisites and the logical order of operations. Fragile Error Handling: When an API call fails or returns unexpected d
I found a prompt that turns 80 pages of course material into 20 pages of comprehensive notes - Norra NotebookLM
So long story short notebookLM has been a game changer and has helped me get good grades and save tons of time and while I was exploring this is the best workflow that helped me huge chunks of data into small comprehensive course Phase 1: Preparation and Segmentation Split the Module (Crucial Step): I upload my module (usually 300–400 pages) to ILovePDF and split it into indivi
I was tired of repeating myself in every new AI chat, so I connected Personalisation with Google Drive
The biggest problem I had with AI wasn’t the quality of the answers. It was forgetting what we had already done. I would spend hours working through a project, fixing a workflow, testing different approaches and explaining how everything should work. Then I’d open a new chat and find myself explaining the same context again. “We already tried that.” “Don’t change that part.” “T
Is prompt-to-video actually the wrong workflow for longer AI videos?
I’ve been messing around with full music-video workflows in MusVideo Ai lately, and honestly, I started noticing something pretty quickly. A lot of my failed generations weren’t actually video problems. The mistake usually happened earlier. Wrong face, weak composition, inconsistent clothing, bad lighting continuity — all things that were already visible before anything started
Stop organizing your prompts by topic. Organize them by verb.
I've been reusing prompts heavily across ChatGPT and Claude for about a year. The thing that finally made my library actually usable wasn't a better tool — it was one change in how I categorized things. (Full disclosure since it's relevant: I ended up building a small tool around exactly this workflow. Not going to link it in the post — happy to drop it in a comment if anyone w
What’s the best ChatGPT skill/prompt for making it challenge its own answers using multiple personas?
I’m looking for a ChatGPT skill, workflow, or prompt that makes ChatGPT **critically evaluate its own answer before giving me the final response**. My goal is something like an internal “panel” of different perspectives. For example: **Expert:** develops the initial answer. **Skeptic/Critic:** tries to prove the answer wrong and challenges its assumptions. **Alternative Thinker
Why passive AI automation is a trap and how to use LLMs as a "flight simulator" for executive function
Most AI workflows right now are designed around passive automation: hand off a task, let the model generate text, copy-paste, and move on. The problem is that over-relying on LLMs for core thinking causes critical thinking and executive function to atrophy. When you use an AI purely as a ghostwriter or answering engine, you're interacting with a system programmed to be sycophan