--- title: "#ai-engineering articles | Hashnode" description: "Explore 423 articles tagged #ai-engineering on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/ai-engineering" --- Tag # #ai-engineering 423 posts · 3 followers [Sotiris Zacharopoulos](https://hashnode.com/@sz-codapus-studio) · [2d ago](https://hashnode.com/posts/semantic-search-playbook-retrieval-negation/6af31c6b12d97dbc275567a9) ### [Semantic Search Found the Playbook but Missed the “Not”](https://blog.codapus.studio/semantic-search-playbook-retrieval-negation?utm_source=hashnode&utm_medium=feed) A containerised experiment compares phrase matching with semantic search, showing recovered matches, missed negation, and the trade-offs of rejection rules. 7 min read · [blog.codapus.studio](https://blog.codapus.studio/semantic-search-playbook-retrieval-negation?utm_source=hashnode&utm_medium=feed) [3](https://hashnode.com/posts/semantic-search-playbook-retrieval-negation/6af31c6b12d97dbc275567a9) [Ignacio Di Rocco](https://hashnode.com/@idirocco) · [1d ago](https://hashnode.com/posts/resume-coach-pipeline-from-20-to-90-schema-validation-and-still-produced-questionable-resumes/6af3c7109eaeb3693740f74b) ### [Resume Coach pipeline, from 20% to 90% schema validation (and still produced questionable resumes)](https://idirocco.hashnode.dev/resume-coach-pipeline-from-20-to-90-schema-validation-and-still-produced-questionable-resumes?utm_source=hashnode&utm_medium=feed) Generating Valid Synthetic Data Doesn't Mean Generating Good Data 5 min read · [idirocco.hashnode.dev](https://idirocco.hashnode.dev/resume-coach-pipeline-from-20-to-90-schema-validation-and-still-produced-questionable-resumes?utm_source=hashnode&utm_medium=feed) [Sai Ram Kotha](https://hashnode.com/@sairamkotha) · [2d ago](https://hashnode.com/posts/ai-mobile-app-testing-screenshot-feedback-loop/6af1ebafb8f3daf46907427b) ### [Automating Mobile App Testing with AI: From Test Cases to Screenshot Feedback](https://sairamkotha.hashnode.dev/ai-mobile-app-testing-screenshot-feedback-loop?utm_source=hashnode&utm_medium=feed) A practical loop for AI-assisted mobile testing: test contracts, reference screenshots, visual diffs and reviewed repairs, shown on one checkout flow. 16 min read · [sairamkotha.hashnode.dev](https://sairamkotha.hashnode.dev/ai-mobile-app-testing-screenshot-feedback-loop?utm_source=hashnode&utm_medium=feed) [Digital BB](https://hashnode.com/@buildingblocksc) · [2d ago](https://hashnode.com/posts/how-to-choose-the-right-ai-engineer-staffing-partner-for-your-business/6af2c0ff87446f8dc543d672) ### [How to Choose the Right AI Engineer Staffing Partner for Your Business](https://buildingblocksconsulting.hashnode.dev/how-to-choose-the-right-ai-engineer-staffing-partner-for-your-business?utm_source=hashnode&utm_medium=feed) Building an AI product requires more than an interesting idea. Businesses need engineers who understand software development, machine learning, data, and the practical challenges of deploying AI solut 3 min read · [buildingblocksconsulting.hashnode.dev](https://buildingblocksconsulting.hashnode.dev/how-to-choose-the-right-ai-engineer-staffing-partner-for-your-business?utm_source=hashnode&utm_medium=feed) [RONI DAS](https://hashnode.com/@ronidas) · [3d ago](https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996) ### [How Claude remembers between sessions: what Anthropic learned about agent memory](https://systemdesignacademy.hashnode.dev/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory?utm_source=hashnode&utm_medium=feed) Anthropic tested agent memory on Pokémon Red, a database quiz and 350,000 company files. Saving less worked better, a fixed rule made it worse, and an idle-time review called dreaming fixed wrong notes. Here is what they found, in plain words. 8 min read · [systemdesignacademy.hashnode.dev](https://systemdesignacademy.hashnode.dev/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996) [Harpreet Sahota](https://hashnode.com/@datascienceharp) · [6d ago](https://hashnode.com/posts/data-quality-feedback-loop-visual-ai/6aedf151bf50f661bd3f03be) ### [Building a Data Quality Feedback Loop for Visual AI Systems](https://hashnode.employabledatascientist.com/data-quality-feedback-loop-visual-ai?utm_source=hashnode&utm_medium=feed) Stop wasting engineering sprints tuning hyperparameters on flawed datasets. Here is how to build a 4-step data-centric evaluation loop for computer vision. 7 min read · [hashnode.employabledatascientist.com](https://hashnode.employabledatascientist.com/data-quality-feedback-loop-visual-ai?utm_source=hashnode&utm_medium=feed) [Harpreet Sahota](https://hashnode.com/@datascienceharp) · [6d ago](https://hashnode.com/posts/three-step-data-quality-preflight-check/6aef3687291dbbcf87f2441b) ### [A 3-Step Data Quality Pre-Flight Check Before Training Vision Models](https://hashnode.employabledatascientist.com/three-step-data-quality-preflight-check?utm_source=hashnode&utm_medium=feed) New architectures drop every 33 hours, but training success depends on data fundamentals. Run this 3-step audit on resolution, labels, and class balance. 6 min read · [hashnode.employabledatascientist.com](https://hashnode.employabledatascientist.com/three-step-data-quality-preflight-check?utm_source=hashnode&utm_medium=feed) [Harpreet Sahota](https://hashnode.com/@datascienceharp) · [6d ago](https://hashnode.com/posts/critical-image-quality-metrics-computer-vision/6af087ad9b5a2f02b53ea6f0) ### [Critical Image Quality Metrics That Break Computer Vision in Production](https://hashnode.employabledatascientist.com/critical-image-quality-metrics-computer-vision?utm_source=hashnode&utm_medium=feed) Vision models fail when real-world camera conditions diverge from training data. How to measure and audit blur, exposure, contrast, and compression artifacts. 6 min read · [hashnode.employabledatascientist.com](https://hashnode.employabledatascientist.com/critical-image-quality-metrics-computer-vision?utm_source=hashnode&utm_medium=feed) [Harpreet Sahota](https://hashnode.com/@datascienceharp) · [6d ago](https://hashnode.com/posts/why-squeaky-clean-datasets-fail-in-production/6af09254f375e93ad330cf8d) ### [Why Squeaky-Clean Datasets Break Production Vision Models](https://hashnode.employabledatascientist.com/why-squeaky-clean-datasets-fail-in-production?utm_source=hashnode&utm_medium=feed) Over-cleaning training data strips structured real-world noise, leaving vision models brittle. Build a data preservation list before running cleaning sprints. 5 min read · [hashnode.employabledatascientist.com](https://hashnode.employabledatascientist.com/why-squeaky-clean-datasets-fail-in-production?utm_source=hashnode&utm_medium=feed) [Harpreet Sahota](https://hashnode.com/@datascienceharp) · [6d ago](https://hashnode.com/posts/detecting-hidden-outliers-visual-ai-embeddings/6af1d909617e673905828127) ### [Detecting Hidden Outliers in Visual AI Datasets with Embeddings and UMAP](https://hashnode.employabledatascientist.com/detecting-hidden-outliers-visual-ai-embeddings?utm_source=hashnode&utm_medium=feed) Uncover silent data anomalies before production failure. How to use foundation model embeddings, Local Outlier Factor (LOF), and UMAP projections. 6 min read · [hashnode.employabledatascientist.com](https://hashnode.employabledatascientist.com/detecting-hidden-outliers-visual-ai-embeddings?utm_source=hashnode&utm_medium=feed)