🆕 Context Engineering in 2026: Compaction, Memory & Cost @Whats_AI, @samridhivaid and @omar_solano1 return! This workshop is about engineering the context window so rot stops happening, shown with @towards_AI's open-source AI tutor, which answers questions for students of our AI-engineering courses. Context engineering is deciding what the model sees on every single call — instructions, history, retrieved course content, memory, and tool outputs — and it's the line between a tutor that holds a coherent session and one that forgets the student's setup halfway through. We'll move in three stages, mirroring how the project actually went. The concepts: - the two root problems (a finite window, a stateless model), - the full compaction toolkit (truncation, trimming, tool-result clearing, summarization, and offloading to files — and when each actually helps), - memory that survives across sessions, skills loaded on demand, and - production-grade retrieval (chunking, metadata, course scoping, hybrid search, reranking, and evaluating). We'll cover the tutor's architecture, and the evaluation harness we used to measure every run on Gemini — tokens, cost, latency, and memory probes instead of vibe-checks. At real volume, even Gemini Flash got expensive, so we tested whether open and local models could match the quality for a fraction of the cost and match result quality. Everything is open-source and will be shared during the workshop.

I used to think context engineering was mostly an input problem. Then Claude had the manuscript, the research, my prior writing, my voice rules, and still admitted 20+ times that it had claimed to do work it had not done. That changed the failure mode I care about. The issue is not only whether the model has enough context. It is whether the system can prove the work actually happened.

Unlock the 7 context engineering secrets to transform your #AI# outputs from generic to insightful. Start mastering smarter #LLMs# today!  — @meisshaily #ArtificialIntelligence# #Context# #TechNology# #Tech# #TechNews# #Prompt#

Every AI agent depends on context. Learn how context engineering helps organizations improve answer quality, reduce retrieval costs, and optimize AI agents with Microsoft Foundry. Read more:

New blog post 📝 "Buzzword Engineering" Prompt Engineering, Context Engineering, Harness Engineering, and now Loop Engineering — at least four "Engineerings" have been born in just a few years since LLMs arrived. Why does the next name keep arriving before the previous one has matured into a real methodology? 🤔 In this post, I name and dissect this phenomenon: Buzzword Engineering — a mode of knowledge production in which methodologies are named and shipped faster than verification can digest them. The root cause is an asymmetry of speed. LLMs drove the cost of proposing methodologies to nearly zero, and are even becoming proposers themselves. Verification, however, completes only when products are used by real users — it remains rate-limited by human behavior. Proposals move at machine speed; verification moves at human speed. Names pile up in the gap as a backlog ⚙️ But this is not a piece that sneers at buzzwords. As Schumpeter's "swarms" and the hype cycle show, proliferation is written into the standard timetable of every technological revolution — it is the first step of knowledge creation, coordinating the attention of engineers worldwide. What I propose instead is a gearbox connecting two clocks: the weekly clock of methodology and the yearly clock of product value. That gearbox is xOps. Inside it: evaluation assets that compound over time, an "autonomy budget" for operating agent delegation by observation, and one norm — if you coin a name, attach falsification conditions and an eval. Methodologies depreciate; evaluation assets compound 🚀 If you're tired of chasing new names, this one is for you. #BuzzwordEngineering# #TechTrends#

Instead of treating prompts as static, Agentic Context Engineering (ACE) explores how context can evolve over time through generation, reflection, and curation. Read the paper ⬇️

I'm hosting a virtual workshop with @AnthropicAI today at 11:30am EST (9/17) We'll be covering Claude Code 101: - Preparing your repo - Context engineering and management - Skills / plugins / chains - Loops / goals - Dynamic workflows Generally, a great introduction to agentic engineering + an internal look into how @tenex_labs uses AI tools like Claude Code to do 10x more. RSVP for free here: Hope to see you there!

Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capabilities 4. Enhance dynamic harness generation where structured outputs are key The first three deliver insane ROI in cost and efficiency. For harness engineering, I'm using it as a smarter router for my meta harness. More on this soon. But honestly, I see other cool applications for improving tool calling and other context-engineering aspects of agents with this model. The fourth is something new I am currently testing but has huge potential to disrupt and enhance agent orchestration in new ways. All in all, this feels like an important primitive for improving your agents. If there is interest, I will write more about this in the coming days and share full guides. Let me know.

We're building a GTM agent for a private equity firm. It'll run outbound campaigns for all of their portfolio companies. We've built GTM agents before. But we're running a fun experiment behind the scenes for this one: We're going to build it on 5 different agent harnesses. Then give the client the one that performs best. This is AI-native engineering at it's finest. The hardest part of this project is the architecture and development plan: - Defining the desired outcome - Aligning on what good looks like - Context engineering for each port co - Making it scalable and reliable across campaigns The easiest part of this project is getting Claude Code to write the code that meets the specs of the plan. Code is abundant now. So we're taking advantage. Plan once, build 5 different versions. Throw away 4, ship 1.

Why is AI in marketing so far behind coding? @kashgupta_, founder of Hightouch, thinks most "AI for marketing" has been way too lazy. In this episode of Navigators, we dug into why sloppy teams are ruining the perception of AI marketing tools, why context engineering is so important, and what it actually takes to make AI a first-class actor in a marketing org: 2:41 Why content is the bottleneck, and why hallucination made it worse 4:32 The brand context layer: teaching LLMs your visual language through embeddings 5:09 Why Hightouch uses a coding loop on SVG, not an image generator 14:41 Going from 20% hallucination to 1% in weeks, not months 16:04 Why "bring your own database" won enterprise 18:36 The vision: five agent-generated marketing opportunities every morning 24:18 "Thickness vs thinness": what makes a real moat in marketing AI 25:52 Teams of 1-5 engineers with no PM shipping billion-dollar products 34:31 The next inflection point for AI marketing Checkout Navigators, our pod on Youtube, Spotify, and Apple Podcasts.