-
Human in the loop (HITL)- best practices for agentic worklows
Human in the loop gives the best of both worlds. Best practice in agentic workflow is testing, verification,quality assurance. You name it. Workflow agents are automatons and can significantly enhance productivity, but their true potential is unlocked when combined with a human-in-the-loop (HITL) approach. This ensures that the agent’s actions are verified and refined by human expertise, leading to better outcomes. In addition it provides a feedback loop for learning and enchancing workflow processes. Why Use Workflow Agents with Human-in-the-Loop? Enhanced accuracy Agents may (or may not 🙂 ) on occasiona misinterpret instructions or context and provider infered data that is not what we wanted it to. Human verification ensures…
-
Why bother with Vue composables – 6 reasons to do
Why bother with Vue composables ? So it will make our lifes easier, more straightforward coding and simplified testing to say the least. Composables in Vue.js are functions that encapsulate business logic and allow it to be reused across different components. Your regular dependency inversion, composition or what ever You want to call it. Designed to make it all simple and pleasurable. Why Use Composables? Reusability Composables encapsulate logic that can be reused in multiple components. One ring to rule them all. One place to change them and in a component bind them. Something like pinia store. For example, if geospatial filtering logic is needed in more than one place,…
-
Kaizen in ai agent plan writing
Kaizen — continuous incremental improvement — is the most underrated mental model for building with AI. Not a big-bang plan. Here's how to apply Plan-Do-Check-Act to LLM workflows.
-
MarkItDown: convert 20+ file types to markdown for AI & LLM Ingestion
MarkItDown can convert different file types into AI / LLmeme friendly markdowns. Tool by Microsoft (microslop? to be less sloppy ? 😉 ). Library provides multiple converters for various files like PDFs, Word docs, spreadsheets, presentations and so on into a clean Markdown format. Aim is to make messy documents readable and structured so the input provided will be of higher quality. MarkItDown is a LLM powered library Traditional converters often fail on complex or scanned documents due to rigid rules and have problems handling edge cases that, simply, weren`t taken into consideration. MarkItDown uses machine learning for semantic parsing (hallucinations ? ) therefore achieving higher accuracy (that is of…
-
Dealing with github copilot errors
Dealing with github copilot errors is pretty irritating. Especially when dosing some more complex stuff and suddenly “Bam”. Red message. Easiest thing to do ? Switching the model family often works because some models have different capacity pools or stricter preview limits. GitHub documents vaguely that if you are rate limited, you can wait and try again. Just type “continue” and keep your fingers crossed. Otherwise check usage patterns, change the model, or contact support. Common github copilot errors Some run of the mill You probably know already, just put them together as a ‘review’ : Why changing the model helps ? Changing from one model family (vendor) to another…
-
Markmap vs Mermaid for Spec-Driven Development (SDD)
Markmap vs Mermaid for Spec-Driven Development You will consider sooner or later. When You have to go “full on AI” documentation stops being a nice-to-have and becomes a must be part of the product. We need to convey a lot of information, with hopefully as little text as possible so we can easily read it and digest the information. Two popular options for Markdown documentation features are Markmap and Mermaid. They solve different problems, and the best choice depends on whether you want fast idea mapping or more structured diagrams for flows. When to use Markmap Markmap turns Markdown headings and bullet points into an interactive mind map. Useful for…
-
AI and LLM articles – links to read
Some links and articles i think are worth Your while to read and get Your own opinion. The Top 100 Gen AI Consumer Apps — 6th Edition | Andreessen Horowitz When Small Models Outperform the Giant: A Practical Guide to Picking AI Brains – DEV Community https://builtin.com/data-science/step-step-explanation-principal-component-analysis How to run mcp inspektor modelcontextprotocol/inspector: Visual testing tool for MCP servers And some more for some bed light reading 🙂 https://techtrenches.dev/p/the-great-software-quality-collapse Vertical Slice Architecture PQ4R Method: 6 Steps to Learn Effectively | 1Focus
-
Psychological safety vs producive stress. How not to go #toxic.
Psychological safety vs producive stress is a conflict of interest. People usually think that much “safety” can lead to laziness ? Don’t rest on your laurels as they say ? On the other stress and some level of danger motivates us to harder work. Workplaces need a certain level of pressure to move forward. Deadlines, feedback, and responsibility all matter. But pressure is not the same as panic, and motivation is not the same as fear. The real challenge is to create an environment where people feel safe enough to speak honestly, while still being stretched enough to grow (or just get exploited and run down the mill?). Safety leads…
-
Jevons paradox in AI workplace
Jevons paradox in AI workplace Jevons paradox in AI workplace is introduced at work with a simple promise: do more in less time. In practice, the result are messy and stack the work. Jevons paradox is the idea that when something becomes more efficient, people and organizations often end up using more of it. In the AI workplace that can mean faster tools, automated work that do not always reduce workload. They can also expand expectations, volume, and ambition to utilize the improved (AIed ?) processes. Be aware At first glance, this sounds contradictory and just wrong. If a team can draft emails, summarize meetings, and generate reports in minutes,…
-
Need to know old boy. Principle of Minimum Access for LLMs
Principle of Minimum Access for LLMs can be described by Timothy Dalton as James Bond in “The Living daylights”. Bond says the phrase “Sorry old boy, section 26, paragraph 5, need to know.” to a fellow agent and drives off escorting a VIP – very important target. Behind the scene is a practical idea that fits modern AI systems very well: an LLM or agent (as in the movie) should only be given the minimum access it needs to do its job. Not more, not less. Bare minimum. Of course Mythos probably could jailbreak anyway but still… controll is the best form of trust ? This is not just a…
